Re: What's Better-R, SASR, SPSSR, or StataR?

[John F Hall]

Brian

 

Just had a quick look through your paper.  Very thought-provoking.  I particularly like your approach aimed at future employment prospects for students.  This mirrors my reasoning in setting up the Social Research Option of the BA Applied Social Studies at the then Polytechnic of North London in 1976.  In those days, given its universal adoption by academia and the public sector, plus the availability of the manual in any decent bookshop, the only sensible software option was SPSS.

 

I take your point about the constraints on course design: the final 1991-92 version of my SPSS-syntax-based undergraduate course was taken in semester 2 of their second year.  It  consisted of 13 weeks x 3 hour sessions, comprising one hour of formal teaching followed by a practical computer lab session (in two shifts of half a class each) closing with a short discussion of students’ output.  Week 14 was for assessment.  

 

On using syntax (my unashamed preference over point-and-click) see the syllabus and specimen assessment for the original course on my site. 

The examples are from 1992, but the same syllabus and assessment format was used for 10 years or so before then.  I can’t give a direct URL for them, but you can access them in pdf format from the links on:

 

http://surveyresearch.weebly.com/background-to-current-project.html

 

Survey Analysis Workshop – Syllabus

           

Syllabus for postgraduate course Survey Analysis Workshop (using SPSS) taught at Polytechnic of North London as at March 1992. Forms basis for updated course materials on this website

 

Survey Analysis Workshop: specimen assessment

 

Specimen assessment for course, as distributed to students. Gives an idea of the sort of things you should understand and have learned to do by the end of the course.

 

Students were then able to go to their professional placements in their 3^rd year with a fair degree of technical competence, but always had free access to the Polytechnic–services (data-prep, printing, computing) and to myself for professional advice and assistance.  Our students were always in great demand and some very impressive research was done for their placement agencies, some resulting in professional publications with the student as first author.  Many of our students were offered jobs in these agencies before they even came back for their 4^th year in college.

 

The undergraduate course was originally in the 4^th year, and therefore not first taught until 1980, but was brought forward into year 2 in around 1982.  It was effectively the same as the highly acclaimed and much sought-after Survey Analysis Workshop, a postgraduate course (practice-oriented, hands-on, part-time, evening) I started in 1976.  Great students, great fun.  Materials from the latter have now been converted, updated and greatly expanded as a Teach-Yourself course using SPSS (19) for Windows.  The full course is now available on: http://surveyresearch.weebly.com/1-survey-analysis-workshop.html but I still have a lot more tutorials and exercises to write, check, upload.

 

On looking at your table comparing the capabilities of R, SAS, Stata and SPSS, I’m not sure you’re right about SPSS and large files.  I’ve recently been using SPSS19 on files with 35,600  (European Social Survey) and 163,200 respondents (National Well-Being Survey).  Your table also shows SPSS having limitations for simple recode/syntax procedures.  I disagree: this is where SPSS reigns supreme (at least if it’s used in syntax mode).  Lower down the table you indicate limitations in SPSS for handling different data formats and for export to Excel etc.  Colleagues on the SPSS-X list-server are better able to comment on that.

 

What is the copyright position for wider distribution of your article?  Is it yours or does it reside with Sage?  I think you/they should consider circulating it to the SPSS-X listerver and the Quantitative methods teaching group and also to user-groups for SAS, R and Stata.  This should result in a cascade of responses from a range of very experienced users (and programmers) which you could use in a follow-up article.

 

Meanwhile I’ll dig out a few simple exercises from my tutorials and ask colleagues versed in R, Stata (*and SAS?) to replicate them: I’d still like to see them side-by-side with notes of how easy/hard they are and how long they take to do.

 

Best wishes, and thanks again for the sight of your article.

 

John

 

 

John F Hall (Mr)

[retired academic survey researcher]

 

Email:     [hidden email]

Website: www.surveyresearch.weebly.com

 

 

 

 

 

From: John F Hall [mailto:[hidden email]]
Sent: 19 February 2013 08:37
To: 'Brian Ward'
Subject: RE: What's Better-R, SASR, SPSSR, or StataR?

 

Brian

 

Many thanks for this.  I’ll check it out as soon as I’ve had my breakfast and get back to you. 

 

Your students may find my website useful: everything is freely downloadable.

 

John

 

From: Brian Ward [[hidden email]]
Sent: 19 February 2013 05:25
To: John F Hall
Subject: Re: What's Better-R, SASR, SPSSR, or StataR?

 

John,

 

I would be happy to send you a copy of my manuscript (see attached). However, it is a very brief teaching note (truncated by the request of the journal) that was meant to simply encourage conversation among college instructors on what statistical software to use. It is non-technical, and based on your conversation below, it may not be precisely what you are looking for. Regardless, I hope it may help to some extent.

 

All the best,

Brian

On Sun, Feb 17, 2013 at 4:44 AM, John F Hall <[hidden email]> wrote:

Dear Brian

 

Your recent JASS paper What’s Better—R, SAS^®, SPSS^®, or Stata^®? Thoughts for Instructors of Statistics and Research Methods Courses was highlighted in a recent discussion between teachers of quantitative methods in the social sciences for which significant funding has been allocated by the Nuffield Foundation, the Higher Education Academy and the Economic and Social Research Council.  

 

There are currently several discussions on the SPSS-X listserver, the QM teachers forum and the above Natcen hosted site.  The first theme centres on the use of syntax vs GUI in SPSS; the second has champions of R, Stata etc. over SPSS (for survey analysis); the third reveals significant differences between disciplines in what should be taught, and how (including trawls for recommended introductory teaching materials).

 

http://www.quantitativemethods.ac.uk

 

*****************************************************************

QM Teachers' Mailing list

subscribe at [hidden email]

*****************************************************************

QM teaching blog:   http://qmteaching.wordpress.com/

 

*****************************************************************

Resources for teaching QM available at:

http://www.esrc.ac.uk/funding-and-guidance/tools-and-resources/undergraduate-QM/index.aspx

******************************************************************

 

Here is my initial message to the new Natcen-hosted group:

 

I've just joined this group, so feeling my way tentatively around.

Members may like to look at my website, Journeys in Survey Research, based on almost 50 years working in survey research and teaching research methods.

The site has three main components:

1: Survey Analysis Workshop (SPSS)
2: Survey Research Practice
3: Subjective Social Indicators (Quality of Life)

The first derives from the SPSS-based courses in data management and analysis I designed and taught at SSRC Summer Schools from 1972 to 1976 and to postgrads and undergrads at the then Polytechnic of North London from 1976 to 1992, when I took early retirement. Learning materials from these courses have now been converted, updated and greatly revised for use with SPSS for Windows. So far there are 450+ pages of teach-youself tutorias with not an equation yet in sight. They are syntax-based (but many examples and exercises are repeated using the GUI menus. They are aimed at total newbies, and assume no previous experience, but even experienced researchers and teachers may learn a thing or two from them.

The second contains links to useful on-line resources for survey research plus a wealth of (not easily available, if at all) materials from my time at the then SSRC Survey Unit and my own Survey research Unit at the Polytechnic of North London.

The third is a new section created when the contents grew too large for the second. It covers all the Quality of Life in Britain surveys I did with Mark Abrams from 1971 to 1975 and links to other previous and ccurrent subjective social indicator work in UK, Europe and the USA.

Whilst not explicitly oriented to the teaching of quantitative methods, my own students found they learned more statistics from my courses than they did from the offical stats course.

Indeed the new degree I was appointed to design and head up at PNL in 1976 (BA Applied Social Studies, Social Research Option) was openly intended to remedy the pathetic state of QM teaching to social science students in UK universities, the bulk of which could be attributed to the poor quality of supervisors, anti-pathy to empiricism, but most of all to a lack of numeracy in undergraduates.

Feedback on the site from colleagues and students has been very positive: hopefully members will feel the same.

I’m particularly interested in comparisons of SPSS with other software to perform the same tasks as those in the SPSS syntax-based tutorials on my website, particularly the very early ones.  I have been in correspondence with Laurie Moseley (Emeritus Pofessor, Health Services Research, Glamorgan) about R, which I downloaded two days ago to check it out.  Here’s an extract from what I said to him:

---

There are three main issues for me: first that some people (mainly statisticians, psychologists and econometricians) don’t seem to be able to think outside their disciplinary box; second, that they misunderstand my approach using SPSS syntax as a route to understanding the language and logic of (survey) data analysis and to acquiring marketable technical and quantitative skills; third that they seem to define survey analysis as dealing with complex sample designs, imputed data, survey error etc (look at the course outlines) and miss the original point of the research question.  As John Tukey once said, “All the statistics in the world won’t save you if you asked the wrong question in the first place!”

 

Some listers recommend R over SPSS: I just downloaded it and barely got past page 1 of the manual.  For my kind of students it’s complete gobble-de-gook.  Others recommend Stata (mainly because of the price differential) but I’ve never seen side-by-side examples of Stata and SPSS syntax for the same exercise, but I have neither time nor inclination to learn yet another software application.

 

I’m sticking with SPSS (and with the substantive content of the surveys I’m working with).  My pedagogic approach was always learning by doing, with a view to eventual employment as social researchers.  I always used actual data from real surveys and peppered my classes with anecdotes from years of field experience: I doubt if many current tutors have much of the latter, if any.  My course was, and still is, unique, and probably more fun.  Aged 72, I just want to get the rest of it finished before I pop my clogs.

---

 

I checked the link to your paper, but only got the abstract.  As an early retired academic on a fractional pension, I can’t afford to subscribe to journals: is there any chance you could let me have a copy of the paper so that I can see the side-by-side examples? 

 

I’m more than happy to collaborate using the exercises on my site.

 

Thanks in advance

 

John Hall

 

John F Hall (Mr)

[retired academic survey researcher]

 

Email:     [hidden email]

Website: www.surveyresearch.weebly.com

 

 

 

 

 

 

[Art Kendall]

I don't see the original post to which this is a reply.
On 2/19/2013 4:55 AM, John F Hall wrote:

Brian

 

Just had a quick look through your paper.  Very thought-provoking.  I particularly like your approach aimed at future employment prospects for students.  This mirrors my reasoning in setting up the Social Research Option of the BA Applied Social Studies at the then Polytechnic of North London in 1976.  In those days, given its universal adoption by academia and the public sector, plus the availability of the manual in any decent bookshop, the only sensible software option was SPSS.

 

I take your point about the constraints on course design: the final 1991-92 version of my SPSS-syntax-based undergraduate course was taken in semester 2 of their second year.  It  consisted of 13 weeks x 3 hour sessions, comprising one hour of formal teaching followed by a practical computer lab session (in two shifts of half a class each) closing with a short discussion of students’ output.  Week 14 was for assessment.  

 

On using syntax (my unashamed preference over point-and-click) see the syllabus and specimen assessment for the original course on my site. 

The examples are from 1992, but the same syllabus and assessment format was used for 10 years or so before then.  I can’t give a direct URL for them, but you can access them in pdf format from the links on:

 

http://surveyresearch.weebly.com/background-to-current-project.html

 

Survey Analysis Workshop – Syllabus

           

Syllabus for postgraduate course Survey Analysis Workshop (using SPSS) taught at Polytechnic of North London as at March 1992. Forms basis for updated course materials on this website

 

Survey Analysis Workshop: specimen assessment

 

Specimen assessment for course, as distributed to students. Gives an idea of the sort of things you should understand and have learned to do by the end of the course.

 

Students were then able to go to their professional placements in their 3^rd year with a fair degree of technical competence, but always had free access to the Polytechnic–services (data-prep, printing, computing) and to myself for professional advice and assistance.  Our students were always in great demand and some very impressive research was done for their placement agencies, some resulting in professional publications with the student as first author.  Many of our students were offered jobs in these agencies before they even came back for their 4^th year in college.

 

The undergraduate course was originally in the 4^th year, and therefore not first taught until 1980, but was brought forward into year 2 in around 1982.  It was effectively the same as the highly acclaimed and much sought-after Survey Analysis Workshop, a postgraduate course (practice-oriented, hands-on, part-time, evening) I started in 1976.  Great students, great fun.  Materials from the latter have now been converted, updated and greatly expanded as a Teach-Yourself course using SPSS (19) for Windows.  The full course is now available on: http://surveyresearch.weebly.com/1-survey-analysis-workshop.html but I still have a lot more tutorials and exercises to write, check, upload.

 

On looking at your table comparing the capabilities of R, SAS, Stata and SPSS, I’m not sure you’re right about SPSS and large files.  I’ve recently been using SPSS19 on files with 35,600  (European Social Survey) and 163,200 respondents (National Well-Being Survey).  Your table also shows SPSS having limitations for simple recode/syntax procedures.  I disagree: this is where SPSS reigns supreme (at least if it’s used in syntax mode).  Lower down the table you indicate limitations in SPSS for handling different data formats and for export to Excel etc.  Colleagues on the SPSS-X list-server are better able to comment on that.

 

What is the copyright position for wider distribution of your article?  Is it yours or does it reside with Sage?  I think you/they should consider circulating it to the SPSS-X listerver and the Quantitative methods teaching group and also to user-groups for SAS, R and Stata.  This should result in a cascade of responses from a range of very experienced users (and programmers) which you could use in a follow-up article.

 

Meanwhile I’ll dig out a few simple exercises from my tutorials and ask colleagues versed in R, Stata (*and SAS?) to replicate them: I’d still like to see them side-by-side with notes of how easy/hard they are and how long they take to do.

 

Best wishes, and thanks again for the sight of your article.

 

John

 

 

John F Hall (Mr)

[retired academic survey researcher]

 

Email:     [hidden email]

Website: www.surveyresearch.weebly.com

 

 

 

 

 

From: John F Hall [[hidden email]]
Sent: 19 February 2013 08:37
To: 'Brian Ward'
Subject: RE: What's Better-R, SASR, SPSSR, or StataR?

 

Brian

 

Many thanks for this.  I’ll check it out as soon as I’ve had my breakfast and get back to you. 

 

Your students may find my website useful: everything is freely downloadable.

 

John

 

From: Brian Ward [[hidden email]]
Sent: 19 February 2013 05:25
To: John F Hall
Subject: Re: What's Better-R, SASR, SPSSR, or StataR?

 

John,

 

I would be happy to send you a copy of my manuscript (see attached). However, it is a very brief teaching note (truncated by the request of the journal) that was meant to simply encourage conversation among college instructors on what statistical software to use. It is non-technical, and based on your conversation below, it may not be precisely what you are looking for. Regardless, I hope it may help to some extent.

 

All the best,

Brian

On Sun, Feb 17, 2013 at 4:44 AM, John F Hall <[hidden email]> wrote:

Dear Brian

 

Your recent JASS paper What’s Better—R, SAS^®, SPSS^®, or Stata^®? Thoughts for Instructors of Statistics and Research Methods Courses was highlighted in a recent discussion between teachers of quantitative methods in the social sciences for which significant funding has been allocated by the Nuffield Foundation, the Higher Education Academy and the Economic and Social Research Council.  

 

There are currently several discussions on the SPSS-X listserver, the QM teachers forum and the above Natcen hosted site.  The first theme centres on the use of syntax vs GUI in SPSS; the second has champions of R, Stata etc. over SPSS (for survey analysis); the third reveals significant differences between disciplines in what should be taught, and how (including trawls for recommended introductory teaching materials).

 

http://www.quantitativemethods.ac.uk

 

*****************************************************************

QM Teachers' Mailing list

subscribe at [hidden email]

*****************************************************************

QM teaching blog:   http://qmteaching.wordpress.com/

 

*****************************************************************

Resources for teaching QM available at:

http://www.esrc.ac.uk/funding-and-guidance/tools-and-resources/undergraduate-QM/index.aspx

******************************************************************

 

Here is my initial message to the new Natcen-hosted group:

 

I've just joined this group, so feeling my way tentatively around.

Members may like to look at my website, Journeys in Survey Research, based on almost 50 years working in survey research and teaching research methods.

The site has three main components:

1: Survey Analysis Workshop (SPSS)
2: Survey Research Practice
3: Subjective Social Indicators (Quality of Life)

The first derives from the SPSS-based courses in data management and analysis I designed and taught at SSRC Summer Schools from 1972 to 1976 and to postgrads and undergrads at the then Polytechnic of North London from 1976 to 1992, when I took early retirement. Learning materials from these courses have now been converted, updated and greatly revised for use with SPSS for Windows. So far there are 450+ pages of teach-youself tutorias with not an equation yet in sight. They are syntax-based (but many examples and exercises are repeated using the GUI menus. They are aimed at total newbies, and assume no previous experience, but even experienced researchers and teachers may learn a thing or two from them.

The second contains links to useful on-line resources for survey research plus a wealth of (not easily available, if at all) materials from my time at the then SSRC Survey Unit and my own Survey research Unit at the Polytechnic of North London.

The third is a new section created when the contents grew too large for the second. It covers all the Quality of Life in Britain surveys I did with Mark Abrams from 1971 to 1975 and links to other previous and ccurrent subjective social indicator work in UK, Europe and the USA.

Whilst not explicitly oriented to the teaching of quantitative methods, my own students found they learned more statistics from my courses than they did from the offical stats course.

Indeed the new degree I was appointed to design and head up at PNL in 1976 (BA Applied Social Studies, Social Research Option) was openly intended to remedy the pathetic state of QM teaching to social science students in UK universities, the bulk of which could be attributed to the poor quality of supervisors, anti-pathy to empiricism, but most of all to a lack of numeracy in undergraduates.

Feedback on the site from colleagues and students has been very positive: hopefully members will feel the same.

I’m particularly interested in comparisons of SPSS with other software to perform the same tasks as those in the SPSS syntax-based tutorials on my website, particularly the very early ones.  I have been in correspondence with Laurie Moseley (Emeritus Pofessor, Health Services Research, Glamorgan) about R, which I downloaded two days ago to check it out.  Here’s an extract from what I said to him:

---

There are three main issues for me: first that some people (mainly statisticians, psychologists and econometricians) don’t seem to be able to think outside their disciplinary box; second, that they misunderstand my approach using SPSS syntax as a route to understanding the language and logic of (survey) data analysis and to acquiring marketable technical and quantitative skills; third that they seem to define survey analysis as dealing with complex sample designs, imputed data, survey error etc (look at the course outlines) and miss the original point of the research question.  As John Tukey once said, “All the statistics in the world won’t save you if you asked the wrong question in the first place!”

 

Some listers recommend R over SPSS: I just downloaded it and barely got past page 1 of the manual.  For my kind of students it’s complete gobble-de-gook.  Others recommend Stata (mainly because of the price differential) but I’ve never seen side-by-side examples of Stata and SPSS syntax for the same exercise, but I have neither time nor inclination to learn yet another software application.

 

I’m sticking with SPSS (and with the substantive content of the surveys I’m working with).  My pedagogic approach was always learning by doing, with a view to eventual employment as social researchers.  I always used actual data from real surveys and peppered my classes with anecdotes from years of field experience: I doubt if many current tutors have much of the latter, if any.  My course was, and still is, unique, and probably more fun.  Aged 72, I just want to get the rest of it finished before I pop my clogs.

---

 

I checked the link to your paper, but only got the abstract.  As an early retired academic on a fractional pension, I can’t afford to subscribe to journals: is there any chance you could let me have a copy of the paper so that I can see the side-by-side examples? 

 

I’m more than happy to collaborate using the exercises on my site.

 

Thanks in advance

 

John Hall

 

John F Hall (Mr)

[retired academic survey researcher]

 

Email:     [hidden email]

Website: www.surveyresearch.weebly.com

 

 

 

 

 

 

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

[J. R. Carroll-3]

I don't think there is one.  I think John took an off-list conversation to the list as a way to solicit responses for Brian's paper.

My apologies if I assumed too much, John.

-j

 

----


J. R. Carroll

Independent Researcher through Hurtz Labs

Research Methods, Test Development, and Statistics

www.jrcresearch.net

www.ontvp.com

Cell:  [phone]

Email: [hidden email]

          [hidden email]

          [hidden email]

On Tue, Feb 19, 2013 at 9:55 AM, Art Kendall <[hidden email]> wrote:

I don't see the original post to which this is a reply.

Art Kendall
Social Research Consultants

On 2/19/2013 4:55 AM, John F Hall wrote:

Brian

 

Just had a quick look through your paper.  Very thought-provoking.  I particularly like your approach aimed at future employment prospects for students.  This mirrors my reasoning in setting up the Social Research Option of the BA Applied Social Studies at the then Polytechnic of North London in 1976.  In those days, given its universal adoption by academia and the public sector, plus the availability of the manual in any decent bookshop, the only sensible software option was SPSS.

 

I take your point about the constraints on course design: the final 1991-92 version of my SPSS-syntax-based undergraduate course was taken in semester 2 of their second year.  It  consisted of 13 weeks x 3 hour sessions, comprising one hour of formal teaching followed by a practical computer lab session (in two shifts of half a class each) closing with a short discussion of students’ output.  Week 14 was for assessment.  

 

On using syntax (my unashamed preference over point-and-click) see the syllabus and specimen assessment for the original course on my site. 

The examples are from 1992, but the same syllabus and assessment format was used for 10 years or so before then.  I can’t give a direct URL for them, but you can access them in pdf format from the links on:

 

http://surveyresearch.weebly.com/background-to-current-project.html

 

Survey Analysis Workshop – Syllabus

           

Syllabus for postgraduate course Survey Analysis Workshop (using SPSS) taught at Polytechnic of North London as at March 1992. Forms basis for updated course materials on this website

 

Survey Analysis Workshop: specimen assessment

 

Specimen assessment for course, as distributed to students. Gives an idea of the sort of things you should understand and have learned to do by the end of the course.

 

Students were then able to go to their professional placements in their 3^rd year with a fair degree of technical competence, but always had free access to the Polytechnic–services (data-prep, printing, computing) and to myself for professional advice and assistance.  Our students were always in great demand and some very impressive research was done for their placement agencies, some resulting in professional publications with the student as first author.  Many of our students were offered jobs in these agencies before they even came back for their 4^th year in college.

 

The undergraduate course was originally in the 4^th year, and therefore not first taught until 1980, but was brought forward into year 2 in around 1982.  It was effectively the same as the highly acclaimed and much sought-after Survey Analysis Workshop, a postgraduate course (practice-oriented, hands-on, part-time, evening) I started in 1976.  Great students, great fun.  Materials from the latter have now been converted, updated and greatly expanded as a Teach-Yourself course using SPSS (19) for Windows.  The full course is now available on: http://surveyresearch.weebly.com/1-survey-analysis-workshop.html but I still have a lot more tutorials and exercises to write, check, upload.

 

On looking at your table comparing the capabilities of R, SAS, Stata and SPSS, I’m not sure you’re right about SPSS and large files.  I’ve recently been using SPSS19 on files with 35,600  (European Social Survey) and 163,200 respondents (National Well-Being Survey).  Your table also shows SPSS having limitations for simple recode/syntax procedures.  I disagree: this is where SPSS reigns supreme (at least if it’s used in syntax mode).  Lower down the table you indicate limitations in SPSS for handling different data formats and for export to Excel etc.  Colleagues on the SPSS-X list-server are better able to comment on that.

 

What is the copyright position for wider distribution of your article?  Is it yours or does it reside with Sage?  I think you/they should consider circulating it to the SPSS-X listerver and the Quantitative methods teaching group and also to user-groups for SAS, R and Stata.  This should result in a cascade of responses from a range of very experienced users (and programmers) which you could use in a follow-up article.

 

Meanwhile I’ll dig out a few simple exercises from my tutorials and ask colleagues versed in R, Stata (*and SAS?) to replicate them: I’d still like to see them side-by-side with notes of how easy/hard they are and how long they take to do.

 

Best wishes, and thanks again for the sight of your article.

 

John

 

 

John F Hall (Mr)

[retired academic survey researcher]

 

Email:     [hidden email]

Website: www.surveyresearch.weebly.com

 

 

 

 

 

From: John F Hall [[hidden email]]
Sent: 19 February 2013 08:37
To: 'Brian Ward'
Subject: RE: What's Better-R, SASR, SPSSR, or StataR?

 

Brian

 

Many thanks for this.  I’ll check it out as soon as I’ve had my breakfast and get back to you. 

 

Your students may find my website useful: everything is freely downloadable.

 

John

 

From: Brian Ward [[hidden email]]
Sent: 19 February 2013 05:25
To: John F Hall
Subject: Re: What's Better-R, SASR, SPSSR, or StataR?

 

John,

 

I would be happy to send you a copy of my manuscript (see attached). However, it is a very brief teaching note (truncated by the request of the journal) that was meant to simply encourage conversation among college instructors on what statistical software to use. It is non-technical, and based on your conversation below, it may not be precisely what you are looking for. Regardless, I hope it may help to some extent.

 

All the best,

Brian

On Sun, Feb 17, 2013 at 4:44 AM, John F Hall <[hidden email]> wrote:

Dear Brian

 

Your recent JASS paper What’s Better—R, SAS^®, SPSS^®, or Stata^®? Thoughts for Instructors of Statistics and Research Methods Courses was highlighted in a recent discussion between teachers of quantitative methods in the social sciences for which significant funding has been allocated by the Nuffield Foundation, the Higher Education Academy and the Economic and Social Research Council.  

 

There are currently several discussions on the SPSS-X listserver, the QM teachers forum and the above Natcen hosted site.  The first theme centres on the use of syntax vs GUI in SPSS; the second has champions of R, Stata etc. over SPSS (for survey analysis); the third reveals significant differences between disciplines in what should be taught, and how (including trawls for recommended introductory teaching materials).

 

http://www.quantitativemethods.ac.uk

 

*****************************************************************

QM Teachers' Mailing list

subscribe at [hidden email]

*****************************************************************

QM teaching blog:   http://qmteaching.wordpress.com/

 

*****************************************************************

Resources for teaching QM available at:

http://www.esrc.ac.uk/funding-and-guidance/tools-and-resources/undergraduate-QM/index.aspx

******************************************************************

 

Here is my initial message to the new Natcen-hosted group:

 

I've just joined this group, so feeling my way tentatively around.

Members may like to look at my website, Journeys in Survey Research, based on almost 50 years working in survey research and teaching research methods.

The site has three main components:

1: Survey Analysis Workshop (SPSS)
2: Survey Research Practice
3: Subjective Social Indicators (Quality of Life)

The first derives from the SPSS-based courses in data management and analysis I designed and taught at SSRC Summer Schools from 1972 to 1976 and to postgrads and undergrads at the then Polytechnic of North London from 1976 to 1992, when I took early retirement. Learning materials from these courses have now been converted, updated and greatly revised for use with SPSS for Windows. So far there are 450+ pages of teach-youself tutorias with not an equation yet in sight. They are syntax-based (but many examples and exercises are repeated using the GUI menus. They are aimed at total newbies, and assume no previous experience, but even experienced researchers and teachers may learn a thing or two from them.

The second contains links to useful on-line resources for survey research plus a wealth of (not easily available, if at all) materials from my time at the then SSRC Survey Unit and my own Survey research Unit at the Polytechnic of North London.

The third is a new section created when the contents grew too large for the second. It covers all the Quality of Life in Britain surveys I did with Mark Abrams from 1971 to 1975 and links to other previous and ccurrent subjective social indicator work in UK, Europe and the USA.

Whilst not explicitly oriented to the teaching of quantitative methods, my own students found they learned more statistics from my courses than they did from the offical stats course.

Indeed the new degree I was appointed to design and head up at PNL in 1976 (BA Applied Social Studies, Social Research Option) was openly intended to remedy the pathetic state of QM teaching to social science students in UK universities, the bulk of which could be attributed to the poor quality of supervisors, anti-pathy to empiricism, but most of all to a lack of numeracy in undergraduates.

Feedback on the site from colleagues and students has been very positive: hopefully members will feel the same.

I’m particularly interested in comparisons of SPSS with other software to perform the same tasks as those in the SPSS syntax-based tutorials on my website, particularly the very early ones.  I have been in correspondence with Laurie Moseley (Emeritus Pofessor, Health Services Research, Glamorgan) about R, which I downloaded two days ago to check it out.  Here’s an extract from what I said to him:

---

There are three main issues for me: first that some people (mainly statisticians, psychologists and econometricians) don’t seem to be able to think outside their disciplinary box; second, that they misunderstand my approach using SPSS syntax as a route to understanding the language and logic of (survey) data analysis and to acquiring marketable technical and quantitative skills; third that they seem to define survey analysis as dealing with complex sample designs, imputed data, survey error etc (look at the course outlines) and miss the original point of the research question.  As John Tukey once said, “All the statistics in the world won’t save you if you asked the wrong question in the first place!”

 

Some listers recommend R over SPSS: I just downloaded it and barely got past page 1 of the manual.  For my kind of students it’s complete gobble-de-gook.  Others recommend Stata (mainly because of the price differential) but I’ve never seen side-by-side examples of Stata and SPSS syntax for the same exercise, but I have neither time nor inclination to learn yet another software application.

 

I’m sticking with SPSS (and with the substantive content of the surveys I’m working with).  My pedagogic approach was always learning by doing, with a view to eventual employment as social researchers.  I always used actual data from real surveys and peppered my classes with anecdotes from years of field experience: I doubt if many current tutors have much of the latter, if any.  My course was, and still is, unique, and probably more fun.  Aged 72, I just want to get the rest of it finished before I pop my clogs.

---

 

I checked the link to your paper, but only got the abstract.  As an early retired academic on a fractional pension, I can’t afford to subscribe to journals: is there any chance you could let me have a copy of the paper so that I can see the side-by-side examples? 

 

I’m more than happy to collaborate using the exercises on my site.

 

Thanks in advance

 

John Hall

 

John F Hall (Mr)

[retired academic survey researcher]

 

Email:     [hidden email]

Website: www.surveyresearch.weebly.com

 

 

 

 

 

 

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

[David Marso]

Hard to read a paper when there is only an abstract ;-(
--

J. R. Carroll-3 wrote

I don't think there is one.  I think John took an off-list conversation to
the list as a way to solicit responses for Brian's paper.

My apologies if I assumed too much, John.

-j


----


J. R. Carroll
Independent Researcher through Hurtz Labs
Research Methods, Test Development, and Statistics
www.jrcresearch.net
www.ontvp.com
Cell:  [phone]
Email: [hidden email]
          [hidden email]
          [hidden email]
<https://www.facebook.com/J.R.Car>
<https://twitter.com/jNammer><http://www.linkedin.com/in/jrcarroll>



On Tue, Feb 19, 2013 at 9:55 AM, Art Kendall <[hidden email]> wrote:

>  I don't see the original post to which this is a reply.
>
> Art Kendall
> Social Research Consultants
>
> On 2/19/2013 4:55 AM, John F Hall wrote:
>
>  Brian****
>
> ** **
>
> Just had a quick look through your paper.  Very thought-provoking.  I
> particularly like your approach aimed at future employment prospects for
> students.  This mirrors my reasoning in setting up the Social Research
> Option of the BA Applied Social Studies at the then Polytechnic of North
> London in 1976.  In those days, given its universal adoption by academia
> and the public sector, plus the availability of the manual in any decent
> bookshop, the only sensible software option was SPSS.****
>
> ** **
>
> I take your point about the constraints on course design: the final
> 1991-92 version of my SPSS-syntax-based undergraduate course was taken in
> semester 2 of their second year.  It  consisted of 13 weeks x 3 hour
> sessions, comprising one hour of formal teaching followed by a practical
> computer lab session (in two shifts of half a class each) closing with a
> short discussion of students’ output.  Week 14 was for assessment.  ****
>
> ** **
>
> On using syntax (my unashamed preference over point-and-click) see the
> syllabus and specimen assessment for the original course on my site.  ****
>
> The examples are from 1992, but the same syllabus and assessment format
> was used for 10 years or so before then.  I can’t give a direct URL for
> them, but you can access them in pdf format from the links on:****
>
> ** **
>
> http://surveyresearch.weebly.com/background-to-current-project.html****
>
> ** **
>
> *Survey Analysis Workshop – Syllabus*
>
> *            ***
>
> Syllabus for postgraduate course Survey Analysis Workshop (using SPSS)
> taught at Polytechnic of North London as at March 1992. Forms basis for
> updated course materials on this website****
>
> ** **
>
> *Survey Analysis Workshop: specimen assessment*
>
> * *
>
> Specimen assessment for course, as distributed to students. Gives an idea
> of the sort of things you should understand and have learned to do by the
> end of the course.****
>
> ** **
>
> Students were then able to go to their professional placements in their 3
> rd year with a fair degree of technical competence, but always had free
> access to the Polytechnic–services (data-prep, printing, computing) and to
> myself for professional advice and assistance.  Our students were always
> in great demand and some very impressive research was done for their
> placement agencies, some resulting in professional publications with the
> student as first author.  Many of our students were offered jobs in these
> agencies before they even came back for their 4th year in college.****
>
> ** **
>
> The undergraduate course was originally in the 4th year, and therefore
> not first taught until 1980, but was brought forward into year 2 in around
> 1982.  It was effectively the same as the highly acclaimed and much
> sought-after *Survey Analysis Workshop*, a postgraduate course
> (practice-oriented, hands-on, part-time, evening) I started in 1976.  Great
> students, great fun.  Materials from the latter have now been converted,
> updated and greatly expanded as a Teach-Yourself course using SPSS (19) for
> Windows.  The full course is now available on:
> http://surveyresearch.weebly.com/1-survey-analysis-workshop.html but I
> still have a lot more tutorials and exercises to write, check, upload.****
>
> ** **
>
> On looking at your table comparing the capabilities of R, SAS, Stata and
> SPSS, I’m not sure you’re right about SPSS and large files.  I’ve
> recently been using SPSS19 on files with 35,600  (European Social Survey)
> and 163,200 respondents (National Well-Being Survey).  Your table also
> shows SPSS having limitations for simple recode/syntax procedures.  I
> disagree: this is where SPSS reigns supreme (at least if it’s used in
> syntax mode).  Lower down the table you indicate limitations in SPSS for
> handling different data formats and for export to Excel etc.  Colleagues
> on the SPSS-X list-server are better able to comment on that.****
>
> ** **
>
> What is the copyright position for wider distribution of your article?  Is
> it yours or does it reside with Sage?  I think you/they should consider
> circulating it to the SPSS-X listerver and the Quantitative methods
> teaching group and also to user-groups for SAS, R and Stata.  This should
> result in a cascade of responses from a range of very experienced users
> (and programmers) which you could use in a follow-up article.****
>
> ** **
>
> Meanwhile I’ll dig out a few simple exercises from my tutorials and ask
> colleagues versed in R, Stata (*and SAS?) to replicate them: I’d still
> like to see them side-by-side with notes of how easy/hard they are and how
> long they take to do.****
>
> ** **
>
> Best wishes, and thanks again for the sight of your article.****
>
> ** **
>
> John****
>
> ** **
>
> ** **
>
> John F Hall (Mr)****
>
> [retired academic survey researcher]****
>
> ** **
>
> Email:     [hidden email] ****
>
> Website: www.surveyresearch.weebly.com <http://surveyresearch.weebly.com/>
> ****
>
> ** **
>
> ** **
>
> ** **
>
> ** **
>
> ** **
>
> *From:* John F Hall [mailto:[hidden email] <[hidden email]>]
> *Sent:* 19 February 2013 08:37
> *To:* 'Brian Ward'
> *Subject:* RE: What's Better-R, SASR, SPSSR, or StataR?****
>
> ** **
>
> Brian****
>
> ** **
>
> Many thanks for this.  I’ll check it out as soon as I’ve had my breakfast
> and get back to you.  ****
>
> ** **
>
> Your students may find my website useful: everything is freely
> downloadable.****
>
> ** **
>
> John****
>
> ** **
>
> *From:* Brian Ward [mailto:[hidden email] <[hidden email]>]
> *Sent:* 19 February 2013 05:25
> *To:* John F Hall
> *Subject:* Re: What's Better-R, SASR, SPSSR, or StataR?****
>
> ** **
>
> John,****
>
>  ****
>
> I would be happy to send you a copy of my manuscript (see attached).
> However, it is a very brief teaching note (truncated by the request of the
> journal) that was meant to simply encourage conversation among college
> instructors on what statistical software to use. It is non-technical, and
> based on your conversation below, it may not be precisely what you are
> looking for. Regardless, I hope it may help to some extent.****
>
>  ****
>
> All the best,****
>
> Brian****
>
> On Sun, Feb 17, 2013 at 4:44 AM, John F Hall <[hidden email]> wrote:*
> ***
>
> Dear Brian****
>
>  ****
>
> Your recent JASS paper *What’s Better—R, SAS®, SPSS®, or Stata®? Thoughts
> for Instructors of Statistics and Research Methods Courses<http://jax.sagepub.com/content/early/2013/01/21/1936724412450570.abstract?utm_content=Visibility_and_reach_O&utm_medium=social_Twitter&utm_campaign=G_ALL_T_2012&utm_source=open&keytype=ref&siteid=spjax&utm_term=Sociology&ijkey=YyG8yvdawCyw6>
> * was highlighted in a recent discussion<http://natcenlearning.ning.com/group/makingresearchreal/forum/topics/spss-sas-stata-or-r-what-s-best-for-teaching>between teachers of quantitative methods in the social sciences for which
> significant funding has been allocated by the Nuffield Foundation, the
> Higher Education Academy and the Economic and Social Research Council.  **
> **
>
>  ****
>
> There are currently several discussions on the SPSS-X listserver, the QM
> teachers forum and the above Natcen hosted site.  The first theme centres
> on the use of syntax vs GUI in SPSS; the second has champions of R, Stata
> etc. over SPSS (for survey analysis); the third reveals significant
> differences between disciplines in what should be taught, and how
> (including trawls for recommended introductory teaching materials).****
>
>  ****
>
> http://www.quantitativemethods.ac.uk****
>
>  ****
>
> *********************************************************************
>
> QM Teachers' Mailing list****
>
> subscribe at [hidden email]****
>
> *********************************************************************
>
> QM teaching blog:   http://qmteaching.wordpress.com/****
>
>  ****
>
> *********************************************************************
>
> Resources for teaching QM available at:****
>
>
> http://www.esrc.ac.uk/funding-and-guidance/tools-and-resources/undergraduate-QM/index.aspx
> ****
>
> **********************************************************************
>
>  ****
>
> Here is my initial message to the new Natcen-hosted group:****
>
>  ****
>
> I've just joined this group, so feeling my way tentatively around.****
>
> Members may like to look at my website, Journeys in Survey Research,<http://surveyresearch.weebly.com/index.html>based on almost 50 years working in survey research and teaching research
> methods. ****
>
> The site has three main components:
>
> *1:* <http://natcenlearning.ning.com/1-survey-analysis-workshop.html>*Survey
> Analysis Workshop (SPSS)*<http://natcenlearning.ning.com/1-survey-analysis-workshop.html>
> *2: **Survey Research Practice*<http://natcenlearning.ning.com/2-survey-research-practice.html>
> *3: **Subjective Social Indicators (Quality of Life)*<http://natcenlearning.ning.com/3-subjective-social-indicators-quality-of-life.html>
> ****
>
> The first derives from the SPSS-based courses in data management and
> analysis I designed and taught at SSRC Summer Schools from 1972 to 1976 and
> to postgrads and undergrads at the then Polytechnic of North London from
> 1976 to 1992, when I took early retirement. Learning materials from these
> courses have now been converted, updated and greatly revised for use with
> SPSS for Windows. So far there are 450+ pages of teach-youself tutorias
> with not an equation yet in sight. They are syntax-based (but many examples
> and exercises are repeated using the GUI menus. They are aimed at total
> newbies, and assume no previous experience, but even experienced
> researchers and teachers may learn a thing or two from them.****
>
> The second contains links to useful on-line resources for survey research
> plus a wealth of (not easily available, if at all) materials from my time
> at the then SSRC Survey Unit and my own Survey research Unit at the
> Polytechnic of North London.****
>
> The third is a new section created when the contents grew too large for
> the second. It covers all the Quality of Life in Britain surveys I did with
> Mark Abrams from 1971 to 1975 and links to other previous and ccurrent
> subjective social indicator work in UK, Europe and the USA.****
>
> Whilst not explicitly oriented to the teaching of quantitative methods, my
> own students found they learned more statistics from my courses than they
> did from the offical stats course. ****
>
> Indeed the new degree I was appointed to design and head up at PNL in 1976
> (BA Applied Social Studies, Social Research Option) was openly intended to
> remedy the pathetic state of QM teaching to social science students in UK
> universities, the bulk of which could be attributed to the poor quality of
> supervisors, anti-pathy to empiricism, but most of all to a lack of
> numeracy in undergraduates.****
>
> Feedback on the site from colleagues and students has been very positive:
> hopefully members will feel the same.****
>
> I’m particularly interested in comparisons of SPSS with other software to
> perform the same tasks as those in the SPSS syntax-based tutorials on my
> website, particularly the very early ones.  I have been in correspondence
> with Laurie Moseley (Emeritus Pofessor, Health Services Research,
> Glamorgan) about R, which I downloaded two days ago to check it out.
> Here’s an extract from what I said to him:****
>  ------------------------------
>
> *There are three main issues for me: first that some people (mainly
> statisticians, psychologists and econometricians) don’t seem to be able to
> think outside their disciplinary box; second, that they misunderstand my
> approach using SPSS syntax as a route to understanding the language and
> logic of (survey) data analysis and to acquiring marketable technical and
> quantitative skills; third that they seem to define survey analysis as
> dealing with complex sample designs, imputed data, survey error etc (look
> at the course outlines) and miss the original point of the research
> question.  As John Tukey once said, “All the statistics in the world won’t
> save you if you asked the wrong question in the first place!”*****
>
> * *****
>
> *Some listers recommend R over SPSS: I just downloaded it and barely got
> past page 1 of the manual.  For my kind of students it’s complete
> gobble-de-gook.  Others recommend Stata (mainly because of the price
> differential) but I’ve never seen side-by-side examples of Stata and SPSS
> syntax for the same exercise, but I have neither time nor inclination to
> learn yet another software application.*****
>
> * *****
>
> *I’m sticking with SPSS (and with the substantive content of the surveys
> I’m working with).  My pedagogic approach was always learning by doing,
> with a view to eventual employment as social researchers.  I always used
> actual data from real surveys and peppered my classes with anecdotes from
> years of field experience: I doubt if many current tutors have much of the
> latter, if any.  My course was, and still is, unique, and probably more
> fun.  Aged 72, I just want to get the rest of it finished before I pop my
> clogs.*****
>  ------------------------------
>
>  ****
>
> I checked the link to your paper, but only got the abstract.  As an early
> retired academic on a fractional pension, I can’t afford to subscribe to
> journals: is there any chance you could let me have a copy of the paper so
> that I can see the side-by-side examples?  ****
>
>  ****
>
> I’m more than happy to collaborate using the exercises on my site.****
>
>  ****
>
> Thanks in advance****
>
>  ****
>
> John Hall****
>
>  ****
>
> John F Hall (Mr)****
>
> [retired academic survey researcher]****
>
>  ****
>
> Email:     [hidden email] ****
>
> Website: www.surveyresearch.weebly.com <http://surveyresearch.weebly.com/>
> ****
>
>  ****
>
>  ****
>
>  ****
>
>  ****
>
>  ****
>
> ** **
>
>
>  ===================== To manage your subscription to SPSSX-L, send a
> message to [hidden email] (not to SPSSX-L), with no body text
> except the command. To leave the list, send the command SIGNOFF SPSSX-L For
> a list of commands to manage subscriptions, send the command INFO REFCARD

[J. R. Carroll-3]

meh, I probably should have said "to solicit interest from the listserv to pester Brian to give it to us"

And by "pester", I jest.

But, I agree - the paper should be sent next round.  I always enjoy free scholarly papers :P

-J

----


J. R. Carroll

Independent Researcher through Hurtz Labs

Research Methods, Test Development, and Statistics

www.jrcresearch.net

www.ontvp.com

Cell:  [phone]

Email: [hidden email]

          [hidden email]

          [hidden email]

On Tue, Feb 19, 2013 at 12:47 PM, David Marso <[hidden email]> wrote:

Hard to read a paper when there is only an abstract ;-(
--

J. R. Carroll-3 wrote

> I don't think there is one.  I think John took an off-list conversation to
> the list as a way to solicit responses for Brian's paper.
>
> My apologies if I assumed too much, John.
>
> -j
>
>
> ----
>
>

> J. R. Carroll
> Independent Researcher through Hurtz Labs
> Research Methods, Test Development, and Statistics
> www.jrcresearch.net
> www.ontvp.com
> Cell:  <a href="tel:%28650%29%20776-6613" value="[phone]">[phone]
> Email:

> jrcarroll@

>

> jrcarroll@

>

> jrc.csus@

> &lt;https://www.facebook.com/J.R.Car&gt;
> &lt;https://twitter.com/jNammer&gt;&lt;http://www.linkedin.com/in/jrcarroll&gt;
>
>
>
> On Tue, Feb 19, 2013 at 9:55 AM, Art Kendall &lt;

> Art@

> &gt; wrote:
>
>>  I don't see the original post to which this is a reply.
>>
>> Art Kendall
>> Social Research Consultants
>>
>> On 2/19/2013 4:55 AM, John F Hall wrote:
>>

>>  Brian****
>>
>> ** **

>>
>> Just had a quick look through your paper.  Very thought-provoking.  I
>> particularly like your approach aimed at future employment prospects for
>> students.  This mirrors my reasoning in setting up the Social Research
>> Option of the BA Applied Social Studies at the then Polytechnic of North
>> London in 1976.  In those days, given its universal adoption by academia
>> and the public sector, plus the availability of the manual in any decent

>> bookshop, the only sensible software option was SPSS.****
>>
>> ** **

>>
>> I take your point about the constraints on course design: the final
>> 1991-92 version of my SPSS-syntax-based undergraduate course was taken in
>> semester 2 of their second year.  It  consisted of 13 weeks x 3 hour
>> sessions, comprising one hour of formal teaching followed by a practical
>> computer lab session (in two shifts of half a class each) closing with a

>> short discussion of students’ output.  Week 14 was for assessment.  ****
>>
>> ** **

>>
>> On using syntax (my unashamed preference over point-and-click) see the
>> syllabus and specimen assessment for the original course on my site.

>> ****

>>
>> The examples are from 1992, but the same syllabus and assessment format
>> was used for 10 years or so before then.  I can’t give a direct URL for

>> them, but you can access them in pdf format from the links on:****
>>
>> ** **
>>
>> http://surveyresearch.weebly.com/background-to-current-project.html****
>>
>> ** **
>>
>> *Survey Analysis Workshop – Syllabus*
>>
>> *            ***

>>
>> Syllabus for postgraduate course Survey Analysis Workshop (using SPSS)
>> taught at Polytechnic of North London as at March 1992. Forms basis for

>> updated course materials on this website****
>>
>> ** **
>>
>> *Survey Analysis Workshop: specimen assessment*
>>
>> * *

>>
>> Specimen assessment for course, as distributed to students. Gives an idea
>> of the sort of things you should understand and have learned to do by the

>> end of the course.****
>>
>> ** **

>>
>> Students were then able to go to their professional placements in their 3
>> rd year with a fair degree of technical competence, but always had free
>> access to the Polytechnic–services (data-prep, printing, computing) and
>> to
>> myself for professional advice and assistance.  Our students were always
>> in great demand and some very impressive research was done for their
>> placement agencies, some resulting in professional publications with the
>> student as first author.  Many of our students were offered jobs in these

>> agencies before they even came back for their 4th year in college.****
>>
>> ** **

>>
>> The undergraduate course was originally in the 4th year, and therefore
>> not first taught until 1980, but was brought forward into year 2 in
>> around
>> 1982.  It was effectively the same as the highly acclaimed and much

>> sought-after *Survey Analysis Workshop*, a postgraduate course

>> (practice-oriented, hands-on, part-time, evening) I started in 1976.
>> Great
>> students, great fun.  Materials from the latter have now been converted,
>> updated and greatly expanded as a Teach-Yourself course using SPSS (19)
>> for
>> Windows.  The full course is now available on:
>> http://surveyresearch.weebly.com/1-survey-analysis-workshop.html but I
>> still have a lot more tutorials and exercises to write, check,

>> upload.****
>>
>> ** **

>>
>> On looking at your table comparing the capabilities of R, SAS, Stata and
>> SPSS, I’m not sure you’re right about SPSS and large files.  I’ve
>> recently been using SPSS19 on files with 35,600  (European Social Survey)
>> and 163,200 respondents (National Well-Being Survey).  Your table also
>> shows SPSS having limitations for simple recode/syntax procedures.  I
>> disagree: this is where SPSS reigns supreme (at least if it’s used in
>> syntax mode).  Lower down the table you indicate limitations in SPSS for
>> handling different data formats and for export to Excel etc.  Colleagues

>> on the SPSS-X list-server are better able to comment on that.****
>>
>> ** **

>>
>> What is the copyright position for wider distribution of your article?
>> Is
>> it yours or does it reside with Sage?  I think you/they should consider
>> circulating it to the SPSS-X listerver and the Quantitative methods
>> teaching group and also to user-groups for SAS, R and Stata.  This should
>> result in a cascade of responses from a range of very experienced users

>> (and programmers) which you could use in a follow-up article.****
>>
>> ** **

>>
>> Meanwhile I’ll dig out a few simple exercises from my tutorials and ask
>> colleagues versed in R, Stata (*and SAS?) to replicate them: I’d still
>> like to see them side-by-side with notes of how easy/hard they are and
>> how

>> long they take to do.****
>>
>> ** **
>>
>> Best wishes, and thanks again for the sight of your article.****
>>
>> ** **
>>
>> John****
>>
>> ** **
>>
>> ** **
>>
>> John F Hall (Mr)****
>>
>> [retired academic survey researcher]****
>>
>> ** **
>>
>> Email:

> johnfhall@

>  ****
>>
>> Website: www.surveyresearch.weebly.com
>> &lt;http://surveyresearch.weebly.com/&gt;
>> ****
>>
>> ** **
>>
>> ** **
>>
>> ** **
>>
>> ** **
>>
>> ** **
>>
>> *From:* John F Hall [mailto:

> johnfhall@

>  &lt;

> johnfhall@

> &gt;]
>> *Sent:* 19 February 2013 08:37
>> *To:* 'Brian Ward'
>> *Subject:* RE: What's Better-R, SASR, SPSSR, or StataR?****
>>
>> ** **
>>
>> Brian****
>>
>> ** **

>>
>> Many thanks for this.  I’ll check it out as soon as I’ve had my breakfast

>> and get back to you.  ****
>>
>> ** **

>>
>> Your students may find my website useful: everything is freely

>> downloadable.****
>>
>> ** **
>>
>> John****
>>
>> ** **
>>
>> *From:* Brian Ward [mailto:

> bwward3@

>  &lt;

> bwward3@

> &gt;]
>> *Sent:* 19 February 2013 05:25
>> *To:* John F Hall
>> *Subject:* Re: What's Better-R, SASR, SPSSR, or StataR?****
>>
>> ** **
>>
>> John,****
>>
>>  ****

>>
>> I would be happy to send you a copy of my manuscript (see attached).
>> However, it is a very brief teaching note (truncated by the request of
>> the
>> journal) that was meant to simply encourage conversation among college
>> instructors on what statistical software to use. It is non-technical, and
>> based on your conversation below, it may not be precisely what you are

>> looking for. Regardless, I hope it may help to some extent.****
>>
>>  ****
>>
>> All the best,****
>>
>> Brian****
>>
>> On Sun, Feb 17, 2013 at 4:44 AM, John F Hall &lt;

> johnfhall@

> &gt; wrote:*
>> ***
>>
>> Dear Brian****
>>
>>  ****
>>
>> Your recent JASS paper *What’s Better—R, SAS®, SPSS®, or Stata®? Thoughts

>> for Instructors of Statistics and Research Methods

>> Courses&lt;http://jax.sagepub.com/content/early/2013/01/21/1936724412450570.abstract?utm_content=Visibility_and_reach_O&amp;utm_medium=social_Twitter&amp;utm_campaign=G_ALL_T_2012&amp;utm_source=open&amp;keytype=ref&amp;siteid=spjax&amp;utm_term=Sociology&amp;ijkey=YyG8yvdawCyw6&gt;

>> * was highlighted in a recent

>> discussion&lt;http://natcenlearning.ning.com/group/makingresearchreal/forum/topics/spss-sas-stata-or-r-what-s-best-for-teaching&gt;between

>> teachers of quantitative methods in the social sciences for which
>> significant funding has been allocated by the Nuffield Foundation, the
>> Higher Education Academy and the Economic and Social Research Council.

>> **
>> **
>>
>>  ****

>>
>> There are currently several discussions on the SPSS-X listserver, the QM
>> teachers forum and the above Natcen hosted site.  The first theme centres
>> on the use of syntax vs GUI in SPSS; the second has champions of R, Stata
>> etc. over SPSS (for survey analysis); the third reveals significant
>> differences between disciplines in what should be taught, and how

>> (including trawls for recommended introductory teaching materials).****
>>
>>  ****
>>
>> http://www.quantitativemethods.ac.uk****
>>
>>  ****
>>
>> *********************************************************************
>>
>> QM Teachers' Mailing list****
>>
>> subscribe at

> quantitative_methods_teaching-join@.ac

> ****
>>
>> *********************************************************************
>>
>> QM teaching blog:   http://qmteaching.wordpress.com/****
>>
>>  ****
>>
>> *********************************************************************
>>
>> Resources for teaching QM available at:****
>>
>>
>> http://www.esrc.ac.uk/funding-and-guidance/tools-and-resources/undergraduate-QM/index.aspx
>> ****
>>
>> **********************************************************************
>>
>>  ****
>>
>> Here is my initial message to the new Natcen-hosted group:****
>>
>>  ****
>>
>> I've just joined this group, so feeling my way tentatively around.****

>>
>> Members may like to look at my website, Journeys in Survey

>> Research,&lt;http://surveyresearch.weebly.com/index.html&gt;based on

>> almost 50 years working in survey research and teaching research

>> methods. ****

>>
>> The site has three main components:
>>

>> *1:*
>> &lt;http://natcenlearning.ning.com/1-survey-analysis-workshop.html&gt;*Survey
>> Analysis Workshop
>> (SPSS)*&lt;http://natcenlearning.ning.com/1-survey-analysis-workshop.html&gt;
>> *2: **Survey Research
>> Practice*&lt;http://natcenlearning.ning.com/2-survey-research-practice.html&gt;
>> *3: **Subjective Social Indicators (Quality of
>> Life)*&lt;http://natcenlearning.ning.com/3-subjective-social-indicators-quality-of-life.html&gt;
>> ****

>>
>> The first derives from the SPSS-based courses in data management and
>> analysis I designed and taught at SSRC Summer Schools from 1972 to 1976
>> and
>> to postgrads and undergrads at the then Polytechnic of North London from
>> 1976 to 1992, when I took early retirement. Learning materials from these
>> courses have now been converted, updated and greatly revised for use with
>> SPSS for Windows. So far there are 450+ pages of teach-youself tutorias
>> with not an equation yet in sight. They are syntax-based (but many
>> examples
>> and exercises are repeated using the GUI menus. They are aimed at total
>> newbies, and assume no previous experience, but even experienced

>> researchers and teachers may learn a thing or two from them.****

>>
>> The second contains links to useful on-line resources for survey research
>> plus a wealth of (not easily available, if at all) materials from my time
>> at the then SSRC Survey Unit and my own Survey research Unit at the

>> Polytechnic of North London.****

>>
>> The third is a new section created when the contents grew too large for
>> the second. It covers all the Quality of Life in Britain surveys I did
>> with
>> Mark Abrams from 1971 to 1975 and links to other previous and ccurrent

>> subjective social indicator work in UK, Europe and the USA.****

>>
>> Whilst not explicitly oriented to the teaching of quantitative methods,
>> my
>> own students found they learned more statistics from my courses than they

>> did from the offical stats course. ****

>>
>> Indeed the new degree I was appointed to design and head up at PNL in
>> 1976
>> (BA Applied Social Studies, Social Research Option) was openly intended
>> to
>> remedy the pathetic state of QM teaching to social science students in UK
>> universities, the bulk of which could be attributed to the poor quality
>> of
>> supervisors, anti-pathy to empiricism, but most of all to a lack of

>> numeracy in undergraduates.****

>>
>> Feedback on the site from colleagues and students has been very positive:

>> hopefully members will feel the same.****

>>
>> I’m particularly interested in comparisons of SPSS with other software to
>> perform the same tasks as those in the SPSS syntax-based tutorials on my
>> website, particularly the very early ones.  I have been in correspondence
>> with Laurie Moseley (Emeritus Pofessor, Health Services Research,
>> Glamorgan) about R, which I downloaded two days ago to check it out.

>> Here’s an extract from what I said to him:****
>>  ------------------------------
>>
>> *There are three main issues for me: first that some people (mainly

>> statisticians, psychologists and econometricians) don’t seem to be able
>> to
>> think outside their disciplinary box; second, that they misunderstand my
>> approach using SPSS syntax as a route to understanding the language and
>> logic of (survey) data analysis and to acquiring marketable technical and
>> quantitative skills; third that they seem to define survey analysis as
>> dealing with complex sample designs, imputed data, survey error etc (look
>> at the course outlines) and miss the original point of the research
>> question.  As John Tukey once said, “All the statistics in the world
>> won’t

>> save you if you asked the wrong question in the first place!”*****
>>
>> * *****
>>
>> *Some listers recommend R over SPSS: I just downloaded it and barely got

>> past page 1 of the manual.  For my kind of students it’s complete
>> gobble-de-gook.  Others recommend Stata (mainly because of the price
>> differential) but I’ve never seen side-by-side examples of Stata and SPSS
>> syntax for the same exercise, but I have neither time nor inclination to

>> learn yet another software application.*****
>>
>> * *****
>>
>> *I’m sticking with SPSS (and with the substantive content of the surveys

>> I’m working with).  My pedagogic approach was always learning by doing,
>> with a view to eventual employment as social researchers.  I always used
>> actual data from real surveys and peppered my classes with anecdotes from
>> years of field experience: I doubt if many current tutors have much of
>> the
>> latter, if any.  My course was, and still is, unique, and probably more
>> fun.  Aged 72, I just want to get the rest of it finished before I pop my

>> clogs.*****
>>  ------------------------------
>>
>>  ****

>>
>> I checked the link to your paper, but only got the abstract.  As an early
>> retired academic on a fractional pension, I can’t afford to subscribe to
>> journals: is there any chance you could let me have a copy of the paper
>> so

>> that I can see the side-by-side examples?  ****
>>
>>  ****
>>
>> I’m more than happy to collaborate using the exercises on my site.****
>>
>>  ****
>>
>> Thanks in advance****
>>
>>  ****
>>
>> John Hall****
>>
>>  ****
>>
>> John F Hall (Mr)****
>>
>> [retired academic survey researcher]****
>>
>>  ****
>>
>> Email:

> johnfhall@

>  ****
>>
>> Website: www.surveyresearch.weebly.com
>> &lt;http://surveyresearch.weebly.com/&gt;
>> ****
>>
>>  ****
>>
>>  ****
>>
>>  ****
>>
>>  ****
>>
>>  ****
>>
>> ** **

>>
>>
>>  ===================== To manage your subscription to SPSSX-L, send a
>> message to

> LISTSERV@.UGA

>  (not to SPSSX-L), with no body text
>> except the command. To leave the list, send the command SIGNOFF SPSSX-L
>> For
>> a list of commands to manage subscriptions, send the command INFO REFCARD

-----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Re-What-s-Better-R-SASR-SPSSR-or-StataR-tp5718122p5718129.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Marta Garcia-Granero]

I got it (using the University library resources).

I don't agree with some "-" or "-/+" SPSS gets in table 1.

Regards,
Marta

El 19/02/2013 18:51, J. R. Carroll escribió:

meh, I probably should have said "to solicit interest from the listserv to pester Brian to give it to us"

And by "pester", I jest.

But, I agree - the paper should be sent next round. I always enjoy free scholarly papers :P

-J

----


J. R. Carroll

Independent Researcher through Hurtz Labs

Research Methods, Test Development, and Statistics

www.jrcresearch.net

www.ontvp.com

Cell: [phone]

Email: [hidden email]

[hidden email]

[hidden email]

On Tue, Feb 19, 2013 at 12:47 PM, David Marso <[hidden email]> wrote:

Hard to read a paper when there is only an abstract ;-(
--

J. R. Carroll-3 wrote

> I don't think there is one. I think John took an off-list conversation to
> the list as a way to solicit responses for Brian's paper.
>
> My apologies if I assumed too much, John.
>
> -j
>
>
> ----
>
>

> J. R. Carroll
> Independent Researcher through Hurtz Labs
> Research Methods, Test Development, and Statistics
> www.jrcresearch.net
> www.ontvp.com
> Cell: <a moz-do-not-send="true" href="tel:%28650%29%20776-6613" value="[phone]">[phone]
> Email:

> jrcarroll@

>

> jrcarroll@

>

> jrc.csus@

> &lt;https://www.facebook.com/J.R.Car&gt;
> &lt;https://twitter.com/jNammer&gt;&lt;http://www.linkedin.com/in/jrcarroll&gt;
>
>
>
> On Tue, Feb 19, 2013 at 9:55 AM, Art Kendall &lt;

> Art@

> &gt; wrote:
>
>> I don't see the original post to which this is a reply.
>>
>> Art Kendall
>> Social Research Consultants
>>
>> On 2/19/2013 4:55 AM, John F Hall wrote:
>>

>> Brian****
>>
>> ** **

>>
>> Just had a quick look through your paper. Very thought-provoking. I
>> particularly like your approach aimed at future employment prospects for
>> students. This mirrors my reasoning in setting up the Social Research
>> Option of the BA Applied Social Studies at the then Polytechnic of North
>> London in 1976. In those days, given its universal adoption by academia
>> and the public sector, plus the availability of the manual in any decent

>> bookshop, the only sensible software option was SPSS.****
>>
>> ** **

>>
>> I take your point about the constraints on course design: the final
>> 1991-92 version of my SPSS-syntax-based undergraduate course was taken in
>> semester 2 of their second year. It consisted of 13 weeks x 3 hour
>> sessions, comprising one hour of formal teaching followed by a practical
>> computer lab session (in two shifts of half a class each) closing with a

>> short discussion of students’ output. Week 14 was for assessment. ****
>>
>> ** **

>>
>> On using syntax (my unashamed preference over point-and-click) see the
>> syllabus and specimen assessment for the original course on my site.

>> ****

>>
>> The examples are from 1992, but the same syllabus and assessment format
>> was used for 10 years or so before then. I can’t give a direct URL for

>> them, but you can access them in pdf format from the links on:****
>>
>> ** **
>>
>> http://surveyresearch.weebly.com/background-to-current-project.html****
>>
>> ** **
>>
>> *Survey Analysis Workshop – Syllabus*
>>
>> * ***

>>
>> Syllabus for postgraduate course Survey Analysis Workshop (using SPSS)
>> taught at Polytechnic of North London as at March 1992. Forms basis for

>> updated course materials on this website****
>>
>> ** **
>>
>> *Survey Analysis Workshop: specimen assessment*
>>
>> * *

>>
>> Specimen assessment for course, as distributed to students. Gives an idea
>> of the sort of things you should understand and have learned to do by the

>> end of the course.****
>>
>> ** **

>>
>> Students were then able to go to their professional placements in their 3
>> rd year with a fair degree of technical competence, but always had free
>> access to the Polytechnic–services (data-prep, printing, computing) and
>> to
>> myself for professional advice and assistance. Our students were always
>> in great demand and some very impressive research was done for their
>> placement agencies, some resulting in professional publications with the
>> student as first author. Many of our students were offered jobs in these

>> agencies before they even came back for their 4th year in college.****
>>
>> ** **

>>
>> The undergraduate course was originally in the 4th year, and therefore
>> not first taught until 1980, but was brought forward into year 2 in
>> around
>> 1982. It was effectively the same as the highly acclaimed and much

>> sought-after *Survey Analysis Workshop*, a postgraduate course

>> (practice-oriented, hands-on, part-time, evening) I started in 1976.
>> Great
>> students, great fun. Materials from the latter have now been converted,
>> updated and greatly expanded as a Teach-Yourself course using SPSS (19)
>> for
>> Windows. The full course is now available on:
>> http://surveyresearch.weebly.com/1-survey-analysis-workshop.html but I
>> still have a lot more tutorials and exercises to write, check,

>> upload.****
>>
>> ** **

>>
>> On looking at your table comparing the capabilities of R, SAS, Stata and
>> SPSS, I’m not sure you’re right about SPSS and large files. I’ve
>> recently been using SPSS19 on files with 35,600 (European Social Survey)
>> and 163,200 respondents (National Well-Being Survey). Your table also
>> shows SPSS having limitations for simple recode/syntax procedures. I
>> disagree: this is where SPSS reigns supreme (at least if it’s used in
>> syntax mode). Lower down the table you indicate limitations in SPSS for
>> handling different data formats and for export to Excel etc. Colleagues

>> on the SPSS-X list-server are better able to comment on that.****
>>
>> ** **

>>
>> What is the copyright position for wider distribution of your article?
>> Is
>> it yours or does it reside with Sage? I think you/they should consider
>> circulating it to the SPSS-X listerver and the Quantitative methods
>> teaching group and also to user-groups for SAS, R and Stata. This should
>> result in a cascade of responses from a range of very experienced users

>> (and programmers) which you could use in a follow-up article.****
>>
>> ** **

>>
>> Meanwhile I’ll dig out a few simple exercises from my tutorials and ask
>> colleagues versed in R, Stata (*and SAS?) to replicate them: I’d still
>> like to see them side-by-side with notes of how easy/hard they are and
>> how

>> long they take to do.****
>>
>> ** **
>>
>> Best wishes, and thanks again for the sight of your article.****
>>
>> ** **
>>
>> John****
>>
>> ** **
>>
>> ** **
>>
>> John F Hall (Mr)****
>>
>> [retired academic survey researcher]****
>>
>> ** **
>>
>> Email:

> johnfhall@

> ****
>>
>> Website: www.surveyresearch.weebly.com
>> &lt;http://surveyresearch.weebly.com/&gt;
>> ****
>>
>> ** **
>>
>> ** **
>>
>> ** **
>>
>> ** **
>>
>> ** **
>>
>> *From:* John F Hall [mailto:

> johnfhall@

> &lt;

> johnfhall@

> &gt;]
>> *Sent:* 19 February 2013 08:37
>> *To:* 'Brian Ward'
>> *Subject:* RE: What's Better-R, SASR, SPSSR, or StataR?****
>>
>> ** **
>>
>> Brian****
>>
>> ** **

>>
>> Many thanks for this. I’ll check it out as soon as I’ve had my breakfast

>> and get back to you. ****
>>
>> ** **

>>
>> Your students may find my website useful: everything is freely

>> downloadable.****
>>
>> ** **
>>
>> John****
>>
>> ** **
>>
>> *From:* Brian Ward [mailto:

> bwward3@

> &lt;

> bwward3@

> &gt;]
>> *Sent:* 19 February 2013 05:25
>> *To:* John F Hall
>> *Subject:* Re: What's Better-R, SASR, SPSSR, or StataR?****
>>
>> ** **
>>
>> John,****
>>
>> ****

>>
>> I would be happy to send you a copy of my manuscript (see attached).
>> However, it is a very brief teaching note (truncated by the request of
>> the
>> journal) that was meant to simply encourage conversation among college
>> instructors on what statistical software to use. It is non-technical, and
>> based on your conversation below, it may not be precisely what you are

>> looking for. Regardless, I hope it may help to some extent.****
>>
>> ****
>>
>> All the best,****
>>
>> Brian****
>>
>> On Sun, Feb 17, 2013 at 4:44 AM, John F Hall &lt;

> johnfhall@

> &gt; wrote:*
>> ***
>>
>> Dear Brian****
>>
>> ****
>>
>> Your recent JASS paper *What’s Better—R, SAS®, SPSS®, or Stata®? Thoughts

>> for Instructors of Statistics and Research Methods

>> Courses&lt;http://jax.sagepub.com/content/early/2013/01/21/1936724412450570.abstract?utm_content=Visibility_and_reach_O&amp;utm_medium=social_Twitter&amp;utm_campaign=G_ALL_T_2012&amp;utm_source=open&amp;keytype=ref&amp;siteid=spjax&amp;utm_term=Sociology&amp;ijkey=YyG8yvdawCyw6&gt;

>> * was highlighted in a recent

>> discussion&lt;http://natcenlearning.ning.com/group/makingresearchreal/forum/topics/spss-sas-stata-or-r-what-s-best-for-teaching&gt;between

>> teachers of quantitative methods in the social sciences for which
>> significant funding has been allocated by the Nuffield Foundation, the
>> Higher Education Academy and the Economic and Social Research Council.

>> **
>> **
>>
>> ****

>>
>> There are currently several discussions on the SPSS-X listserver, the QM
>> teachers forum and the above Natcen hosted site. The first theme centres
>> on the use of syntax vs GUI in SPSS; the second has champions of R, Stata
>> etc. over SPSS (for survey analysis); the third reveals significant
>> differences between disciplines in what should be taught, and how

>> (including trawls for recommended introductory teaching materials).****
>>
>> ****
>>
>> http://www.quantitativemethods.ac.uk****
>>
>> ****
>>
>> *********************************************************************
>>
>> QM Teachers' Mailing list****
>>
>> subscribe at

> [hidden email]

> ****
>>
>> *********************************************************************
>>
>> QM teaching blog: http://qmteaching.wordpress.com/****
>>
>> ****
>>
>> *********************************************************************
>>
>> Resources for teaching QM available at:****
>>
>>
>> http://www.esrc.ac.uk/funding-and-guidance/tools-and-resources/undergraduate-QM/index.aspx
>> ****
>>
>> **********************************************************************
>>
>> ****
>>
>> Here is my initial message to the new Natcen-hosted group:****
>>
>> ****
>>
>> I've just joined this group, so feeling my way tentatively around.****

>>
>> Members may like to look at my website, Journeys in Survey

>> Research,&lt;http://surveyresearch.weebly.com/index.html&gt;based on

>> almost 50 years working in survey research and teaching research

>> methods. ****

>>
>> The site has three main components:
>>

>> *1:*
>> &lt;http://natcenlearning.ning.com/1-survey-analysis-workshop.html&gt;*Survey
>> Analysis Workshop
>> (SPSS)*&lt;http://natcenlearning.ning.com/1-survey-analysis-workshop.html&gt;
>> *2: **Survey Research
>> Practice*&lt;http://natcenlearning.ning.com/2-survey-research-practice.html&gt;
>> *3: **Subjective Social Indicators (Quality of
>> Life)*&lt;http://natcenlearning.ning.com/3-subjective-social-indicators-quality-of-life.html&gt;
>> ****

>>
>> The first derives from the SPSS-based courses in data management and
>> analysis I designed and taught at SSRC Summer Schools from 1972 to 1976
>> and
>> to postgrads and undergrads at the then Polytechnic of North London from
>> 1976 to 1992, when I took early retirement. Learning materials from these
>> courses have now been converted, updated and greatly revised for use with
>> SPSS for Windows. So far there are 450+ pages of teach-youself tutorias
>> with not an equation yet in sight. They are syntax-based (but many
>> examples
>> and exercises are repeated using the GUI menus. They are aimed at total
>> newbies, and assume no previous experience, but even experienced

>> researchers and teachers may learn a thing or two from them.****

>>
>> The second contains links to useful on-line resources for survey research
>> plus a wealth of (not easily available, if at all) materials from my time
>> at the then SSRC Survey Unit and my own Survey research Unit at the

>> Polytechnic of North London.****

>>
>> The third is a new section created when the contents grew too large for
>> the second. It covers all the Quality of Life in Britain surveys I did
>> with
>> Mark Abrams from 1971 to 1975 and links to other previous and ccurrent

>> subjective social indicator work in UK, Europe and the USA.****

>>
>> Whilst not explicitly oriented to the teaching of quantitative methods,
>> my
>> own students found they learned more statistics from my courses than they

>> did from the offical stats course. ****

>>
>> Indeed the new degree I was appointed to design and head up at PNL in
>> 1976
>> (BA Applied Social Studies, Social Research Option) was openly intended
>> to
>> remedy the pathetic state of QM teaching to social science students in UK
>> universities, the bulk of which could be attributed to the poor quality
>> of
>> supervisors, anti-pathy to empiricism, but most of all to a lack of

>> numeracy in undergraduates.****

>>
>> Feedback on the site from colleagues and students has been very positive:

>> hopefully members will feel the same.****

>>
>> I’m particularly interested in comparisons of SPSS with other software to
>> perform the same tasks as those in the SPSS syntax-based tutorials on my
>> website, particularly the very early ones. I have been in correspondence
>> with Laurie Moseley (Emeritus Pofessor, Health Services Research,
>> Glamorgan) about R, which I downloaded two days ago to check it out.

>> Here’s an extract from what I said to him:****
>> ------------------------------
>>
>> *There are three main issues for me: first that some people (mainly

>> statisticians, psychologists and econometricians) don’t seem to be able
>> to
>> think outside their disciplinary box; second, that they misunderstand my
>> approach using SPSS syntax as a route to understanding the language and
>> logic of (survey) data analysis and to acquiring marketable technical and
>> quantitative skills; third that they seem to define survey analysis as
>> dealing with complex sample designs, imputed data, survey error etc (look
>> at the course outlines) and miss the original point of the research
>> question. As John Tukey once said, “All the statistics in the world
>> won’t

>> save you if you asked the wrong question in the first place!”*****
>>
>> * *****
>>
>> *Some listers recommend R over SPSS: I just downloaded it and barely got

>> past page 1 of the manual. For my kind of students it’s complete
>> gobble-de-gook. Others recommend Stata (mainly because of the price
>> differential) but I’ve never seen side-by-side examples of Stata and SPSS
>> syntax for the same exercise, but I have neither time nor inclination to

>> learn yet another software application.*****
>>
>> * *****
>>
>> *I’m sticking with SPSS (and with the substantive content of the surveys

>> I’m working with). My pedagogic approach was always learning by doing,
>> with a view to eventual employment as social researchers. I always used
>> actual data from real surveys and peppered my classes with anecdotes from
>> years of field experience: I doubt if many current tutors have much of
>> the
>> latter, if any. My course was, and still is, unique, and probably more
>> fun. Aged 72, I just want to get the rest of it finished before I pop my

>> clogs.*****
>> ------------------------------
>>
>> ****

>>
>> I checked the link to your paper, but only got the abstract. As an early
>> retired academic on a fractional pension, I can’t afford to subscribe to
>> journals: is there any chance you could let me have a copy of the paper
>> so

>> that I can see the side-by-side examples? ****
>>
>> ****
>>
>> I’m more than happy to collaborate using the exercises on my site.****
>>
>> ****
>>
>> Thanks in advance****
>>
>> ****
>>
>> John Hall****
>>
>> ****
>>
>> John F Hall (Mr)****
>>
>> [retired academic survey researcher]****
>>
>> ****
>>
>> Email:

> johnfhall@

> ****
>>
>> Website: www.surveyresearch.weebly.com
>> &lt;http://surveyresearch.weebly.com/&gt;
>> ****
>>
>> ****
>>
>> ****
>>
>> ****
>>
>> ****
>>
>> ****
>>
>> ** **

>>
>>
>> ===================== To manage your subscription to SPSSX-L, send a
>> message to

> [hidden email]

> (not to SPSSX-L), with no body text
>> except the command. To leave the list, send the command SIGNOFF SPSSX-L
>> For
>> a list of commands to manage subscriptions, send the command INFO REFCARD

-----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me.
--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Re-What-s-Better-R-SASR-SPSSR-or-StataR-tp5718122p5718129.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[Bruce Weaver]

I also do not agree with all of the pluses and minuses in Table 1.  E.g., SPSS is given a minus for "Simple recode syntax/procedures".  The RECODE syntax could not be much simpler, IMO.  Perhaps Ward is referring more to the GUI dialog for RECODE.  ;-)

It's not clear to me from the article how much actual experience Ward has with each of these packages.  The review by Mitchell (from UCLA Statistical Computing) that appeared a few years ago is now dated -- e.g., I think SPSS did not even have GENLIN when he wrote it.  But the think I liked about it was that Mitchell clearly had lots of hands-on experience with all the packages he discussed.  IIRC, they included SPSS, SAS, Stata and maybe R.

Cheers,
Bruce

Marta García-Granero-2 wrote

I got it (using the University library resources).

I don't agree with some "-" or "-/+" SPSS gets in table 1.

Regards,
Marta

El 19/02/2013 18:51, J. R. Carroll escribió:
> meh, I probably should have said "to solicit interest from the
> listserv to pester Brian to give it to us"
>
> And by "pester", I jest.
>
> But, I agree - the paper should be sent next round.  I always enjoy
> free scholarly papers :P
>
>
> -J
>
>
> ----
>
>
> J. R. Carroll
> Independent Researcher through Hurtz Labs
> Research Methods, Test Development, and Statistics
> www.jrcresearch.net <http://www.jrcresearch.net/>
> www.ontvp.com <http://www.ontvp.com>
> Cell:  [phone]
> Email: [hidden email] <mailto:[hidden email]>
> [hidden email] <mailto:[hidden email]>
> [hidden email] <mailto:[hidden email]>
> <https://www.facebook.com/J.R.Car><https://twitter.com/jNammer><http://www.linkedin.com/in/jrcarroll>
>
>
>
> On Tue, Feb 19, 2013 at 12:47 PM, David Marso <[hidden email]
> <mailto:[hidden email]>> wrote:
>
>     Hard to read a paper when there is only an abstract ;-(
>     --
>
>     J. R. Carroll-3 wrote
>     > I don't think there is one.  I think John took an off-list
>     conversation to
>     > the list as a way to solicit responses for Brian's paper.
>     >
>     > My apologies if I assumed too much, John.
>     >
>     > -j
>     >
>     >
>     > ----
>     >
>     >
>     > J. R. Carroll
>     > Independent Researcher through Hurtz Labs
>     > Research Methods, Test Development, and Statistics
>     > www.jrcresearch.net <http://www.jrcresearch.net>
>     > www.ontvp.com <http://www.ontvp.com>
>     > Cell: [phone] <tel:%28650%29%20776-6613>
>     > Email:
>
>     > jrcarroll@
>
>     >
>
>     > jrcarroll@
>
>     >
>
>     > jrc.csus@
>
>     > <https://www.facebook.com/J.R.Car>
>     >
>     <https://twitter.com/jNammer><http://www.linkedin.com/in/jrcarroll>
>     >
>     >
>     >
>     > On Tue, Feb 19, 2013 at 9:55 AM, Art Kendall <
>
>     > Art@
>
>     > > wrote:
>     >
>     >>  I don't see the original post to which this is a reply.
>     >>
>     >> Art Kendall
>     >> Social Research Consultants
>     >>
>     >> On 2/19/2013 4:55 AM, John F Hall wrote:
>     >>
>     >>  Brian****
>     >>
>     >> ** **
>     >>
>     >> Just had a quick look through your paper.  Very
>     thought-provoking.  I
>     >> particularly like your approach aimed at future employment
>     prospects for
>     >> students.  This mirrors my reasoning in setting up the Social
>     Research
>     >> Option of the BA Applied Social Studies at the then Polytechnic
>     of North
>     >> London in 1976.  In those days, given its universal adoption by
>     academia
>     >> and the public sector, plus the availability of the manual in
>     any decent
>     >> bookshop, the only sensible software option was SPSS.****
>     >>
>     >> ** **
>     >>
>     >> I take your point about the constraints on course design: the final
>     >> 1991-92 version of my SPSS-syntax-based undergraduate course
>     was taken in
>     >> semester 2 of their second year.  It  consisted of 13 weeks x 3
>     hour
>     >> sessions, comprising one hour of formal teaching followed by a
>     practical
>     >> computer lab session (in two shifts of half a class each)
>     closing with a
>     >> short discussion of students’ output.  Week 14 was for
>     assessment.  ****
>     >>
>     >> ** **
>     >>
>     >> On using syntax (my unashamed preference over point-and-click)
>     see the
>     >> syllabus and specimen assessment for the original course on my
>     site.
>     >> ****
>     >>
>     >> The examples are from 1992, but the same syllabus and
>     assessment format
>     >> was used for 10 years or so before then.  I can’t give a direct
>     URL for
>     >> them, but you can access them in pdf format from the links on:****
>     >>
>     >> ** **
>     >>
>     >>
>     http://surveyresearch.weebly.com/background-to-current-project.html****
>     >>
>     >> ** **
>     >>
>     >> *Survey Analysis Workshop – Syllabus*
>     >>
>     >> *            ***
>     >>
>     >> Syllabus for postgraduate course Survey Analysis Workshop
>     (using SPSS)
>     >> taught at Polytechnic of North London as at March 1992. Forms
>     basis for
>     >> updated course materials on this website****
>     >>
>     >> ** **
>     >>
>     >> *Survey Analysis Workshop: specimen assessment*
>     >>
>     >> * *
>     >>
>     >> Specimen assessment for course, as distributed to students.
>     Gives an idea
>     >> of the sort of things you should understand and have learned to
>     do by the
>     >> end of the course.****
>     >>
>     >> ** **
>     >>
>     >> Students were then able to go to their professional placements
>     in their 3
>     >> rd year with a fair degree of technical competence, but always
>     had free
>     >> access to the Polytechnic–services (data-prep, printing,
>     computing) and
>     >> to
>     >> myself for professional advice and assistance.  Our students
>     were always
>     >> in great demand and some very impressive research was done for
>     their
>     >> placement agencies, some resulting in professional publications
>     with the
>     >> student as first author.  Many of our students were offered
>     jobs in these
>     >> agencies before they even came back for their 4th year in
>     college.****
>     >>
>     >> ** **
>     >>
>     >> The undergraduate course was originally in the 4th year, and
>     therefore
>     >> not first taught until 1980, but was brought forward into year 2 in
>     >> around
>     >> 1982.  It was effectively the same as the highly acclaimed and much
>     >> sought-after *Survey Analysis Workshop*, a postgraduate course
>     >> (practice-oriented, hands-on, part-time, evening) I started in
>     1976.
>     >> Great
>     >> students, great fun.  Materials from the latter have now been
>     converted,
>     >> updated and greatly expanded as a Teach-Yourself course using
>     SPSS (19)
>     >> for
>     >> Windows.  The full course is now available on:
>     >>
>     http://surveyresearch.weebly.com/1-survey-analysis-workshop.html but I
>     >> still have a lot more tutorials and exercises to write, check,
>     >> upload.****
>     >>
>     >> ** **
>     >>
>     >> On looking at your table comparing the capabilities of R, SAS,
>     Stata and
>     >> SPSS, I’m not sure you’re right about SPSS and large files.  I’ve
>     >> recently been using SPSS19 on files with 35,600  (European
>     Social Survey)
>     >> and 163,200 respondents (National Well-Being Survey).  Your
>     table also
>     >> shows SPSS having limitations for simple recode/syntax
>     procedures.  I
>     >> disagree: this is where SPSS reigns supreme (at least if it’s
>     used in
>     >> syntax mode).  Lower down the table you indicate limitations in
>     SPSS for
>     >> handling different data formats and for export to Excel etc.
>      Colleagues
>     >> on the SPSS-X list-server are better able to comment on that.****
>     >>
>     >> ** **
>     >>
>     >> What is the copyright position for wider distribution of your
>     article?
>     >> Is
>     >> it yours or does it reside with Sage?  I think you/they should
>     consider
>     >> circulating it to the SPSS-X listerver and the Quantitative methods
>     >> teaching group and also to user-groups for SAS, R and Stata.
>      This should
>     >> result in a cascade of responses from a range of very
>     experienced users
>     >> (and programmers) which you could use in a follow-up article.****
>     >>
>     >> ** **
>     >>
>     >> Meanwhile I’ll dig out a few simple exercises from my tutorials
>     and ask
>     >> colleagues versed in R, Stata (*and SAS?) to replicate them:
>     I’d still
>     >> like to see them side-by-side with notes of how easy/hard they
>     are and
>     >> how
>     >> long they take to do.****
>     >>
>     >> ** **
>     >>
>     >> Best wishes, and thanks again for the sight of your article.****
>     >>
>     >> ** **
>     >>
>     >> John****
>     >>
>     >> ** **
>     >>
>     >> ** **
>     >>
>     >> John F Hall (Mr)****
>     >>
>     >> [retired academic survey researcher]****
>     >>
>     >> ** **
>     >>
>     >> Email:
>
>     > johnfhall@
>
>     >  ****
>     >>
>     >> Website: www.surveyresearch.weebly.com
>     <http://www.surveyresearch.weebly.com>
>     >> <http://surveyresearch.weebly.com/>
>     >> ****
>     >>
>     >> ** **
>     >>
>     >> ** **
>     >>
>     >> ** **
>     >>
>     >> ** **
>     >>
>     >> ** **
>     >>
>     >> *From:* John F Hall [mailto:
>
>     > johnfhall@
>
>     >  <
>
>     > johnfhall@
>
>     > >]
>     >> *Sent:* 19 February 2013 08:37
>     >> *To:* 'Brian Ward'
>     >> *Subject:* RE: What's Better-R, SASR, SPSSR, or StataR?****
>     >>
>     >> ** **
>     >>
>     >> Brian****
>     >>
>     >> ** **
>     >>
>     >> Many thanks for this.  I’ll check it out as soon as I’ve had my
>     breakfast
>     >> and get back to you.  ****
>     >>
>     >> ** **
>     >>
>     >> Your students may find my website useful: everything is freely
>     >> downloadable.****
>     >>
>     >> ** **
>     >>
>     >> John****
>     >>
>     >> ** **
>     >>
>     >> *From:* Brian Ward [mailto:
>
>     > bwward3@
>
>     >  <
>
>     > bwward3@
>
>     > >]
>     >> *Sent:* 19 February 2013 05:25
>     >> *To:* John F Hall
>     >> *Subject:* Re: What's Better-R, SASR, SPSSR, or StataR?****
>     >>
>     >> ** **
>     >>
>     >> John,****
>     >>
>     >>  ****
>     >>
>     >> I would be happy to send you a copy of my manuscript (see
>     attached).
>     >> However, it is a very brief teaching note (truncated by the
>     request of
>     >> the
>     >> journal) that was meant to simply encourage conversation among
>     college
>     >> instructors on what statistical software to use. It is
>     non-technical, and
>     >> based on your conversation below, it may not be precisely what
>     you are
>     >> looking for. Regardless, I hope it may help to some extent.****
>     >>
>     >>  ****
>     >>
>     >> All the best,****
>     >>
>     >> Brian****
>     >>
>     >> On Sun, Feb 17, 2013 at 4:44 AM, John F Hall <
>
>     > johnfhall@
>
>     > > wrote:*
>     >> ***
>     >>
>     >> Dear Brian****
>     >>
>     >>  ****
>     >>
>     >> Your recent JASS paper *What’s Better—R, SAS®, SPSS®, or
>     Stata®? Thoughts
>     >> for Instructors of Statistics and Research Methods
>     >>
>     Courses<http://jax.sagepub.com/content/early/2013/01/21/1936724412450570.abstract?utm_content=Visibility_and_reach_O&utm_medium=social_Twitter&utm_campaign=G_ALL_T_2012&utm_source=open&keytype=ref&siteid=spjax&utm_term=Sociology&ijkey=YyG8yvdawCyw6>
>     >> * was highlighted in a recent
>     >>
>     discussion<http://natcenlearning.ning.com/group/makingresearchreal/forum/topics/spss-sas-stata-or-r-what-s-best-for-teaching>between
>     >> teachers of quantitative methods in the social sciences for which
>     >> significant funding has been allocated by the Nuffield
>     Foundation, the
>     >> Higher Education Academy and the Economic and Social Research
>     Council.
>     >> **
>     >> **
>     >>
>     >>  ****
>     >>
>     >> There are currently several discussions on the SPSS-X
>     listserver, the QM
>     >> teachers forum and the above Natcen hosted site.  The first
>     theme centres
>     >> on the use of syntax vs GUI in SPSS; the second has champions
>     of R, Stata
>     >> etc. over SPSS (for survey analysis); the third reveals significant
>     >> differences between disciplines in what should be taught, and how
>     >> (including trawls for recommended introductory teaching
>     materials).****
>     >>
>     >>  ****
>     >>
>     >> http://www.quantitativemethods.ac.uk****
>     >>
>     >>  ****
>     >>
>     >>
>     *********************************************************************
>     >>
>     >> QM Teachers' Mailing list****
>     >>
>     >> subscribe at
>
>     > quantitative_methods_teaching-join@.ac
>
>     > ****
>     >>
>     >>
>     *********************************************************************
>     >>
>     >> QM teaching blog: http://qmteaching.wordpress.com/****
>     >>
>     >>  ****
>     >>
>     >>
>     *********************************************************************
>     >>
>     >> Resources for teaching QM available at:****
>     >>
>     >>
>     >>
>     http://www.esrc.ac.uk/funding-and-guidance/tools-and-resources/undergraduate-QM/index.aspx
>     >> ****
>     >>
>     >>
>     **********************************************************************
>     >>
>     >>  ****
>     >>
>     >> Here is my initial message to the new Natcen-hosted group:****
>     >>
>     >>  ****
>     >>
>     >> I've just joined this group, so feeling my way tentatively
>     around.****
>     >>
>     >> Members may like to look at my website, Journeys in Survey
>     >>
>     Research,<http://surveyresearch.weebly.com/index.html>based on
>     >> almost 50 years working in survey research and teaching research
>     >> methods. ****
>     >>
>     >> The site has three main components:
>     >>
>     >> *1:*
>     >>
>     <http://natcenlearning.ning.com/1-survey-analysis-workshop.html>*Survey
>     >> Analysis Workshop
>     >>
>     (SPSS)*<http://natcenlearning.ning.com/1-survey-analysis-workshop.html>
>     >> *2: **Survey Research
>     >>
>     Practice*<http://natcenlearning.ning.com/2-survey-research-practice.html>
>     >> *3: **Subjective Social Indicators (Quality of
>     >>
>     Life)*<http://natcenlearning.ning.com/3-subjective-social-indicators-quality-of-life.html>
>     >> ****
>     >>
>     >> The first derives from the SPSS-based courses in data
>     management and
>     >> analysis I designed and taught at SSRC Summer Schools from 1972
>     to 1976
>     >> and
>     >> to postgrads and undergrads at the then Polytechnic of North
>     London from
>     >> 1976 to 1992, when I took early retirement. Learning materials
>     from these
>     >> courses have now been converted, updated and greatly revised
>     for use with
>     >> SPSS for Windows. So far there are 450+ pages of teach-youself
>     tutorias
>     >> with not an equation yet in sight. They are syntax-based (but many
>     >> examples
>     >> and exercises are repeated using the GUI menus. They are aimed
>     at total
>     >> newbies, and assume no previous experience, but even experienced
>     >> researchers and teachers may learn a thing or two from them.****
>     >>
>     >> The second contains links to useful on-line resources for
>     survey research
>     >> plus a wealth of (not easily available, if at all) materials
>     from my time
>     >> at the then SSRC Survey Unit and my own Survey research Unit at the
>     >> Polytechnic of North London.****
>     >>
>     >> The third is a new section created when the contents grew too
>     large for
>     >> the second. It covers all the Quality of Life in Britain
>     surveys I did
>     >> with
>     >> Mark Abrams from 1971 to 1975 and links to other previous and
>     ccurrent
>     >> subjective social indicator work in UK, Europe and the USA.****
>     >>
>     >> Whilst not explicitly oriented to the teaching of quantitative
>     methods,
>     >> my
>     >> own students found they learned more statistics from my courses
>     than they
>     >> did from the offical stats course. ****
>     >>
>     >> Indeed the new degree I was appointed to design and head up at
>     PNL in
>     >> 1976
>     >> (BA Applied Social Studies, Social Research Option) was openly
>     intended
>     >> to
>     >> remedy the pathetic state of QM teaching to social science
>     students in UK
>     >> universities, the bulk of which could be attributed to the poor
>     quality
>     >> of
>     >> supervisors, anti-pathy to empiricism, but most of all to a lack of
>     >> numeracy in undergraduates.****
>     >>
>     >> Feedback on the site from colleagues and students has been very
>     positive:
>     >> hopefully members will feel the same.****
>     >>
>     >> I’m particularly interested in comparisons of SPSS with other
>     software to
>     >> perform the same tasks as those in the SPSS syntax-based
>     tutorials on my
>     >> website, particularly the very early ones.  I have been in
>     correspondence
>     >> with Laurie Moseley (Emeritus Pofessor, Health Services Research,
>     >> Glamorgan) about R, which I downloaded two days ago to check it
>     out.
>     >> Here’s an extract from what I said to him:****
>     >>  ------------------------------
>     >>
>     >> *There are three main issues for me: first that some people (mainly
>     >> statisticians, psychologists and econometricians) don’t seem to
>     be able
>     >> to
>     >> think outside their disciplinary box; second, that they
>     misunderstand my
>     >> approach using SPSS syntax as a route to understanding the
>     language and
>     >> logic of (survey) data analysis and to acquiring marketable
>     technical and
>     >> quantitative skills; third that they seem to define survey
>     analysis as
>     >> dealing with complex sample designs, imputed data, survey error
>     etc (look
>     >> at the course outlines) and miss the original point of the research
>     >> question.  As John Tukey once said, “All the statistics in the
>     world
>     >> won’t
>     >> save you if you asked the wrong question in the first place!”*****
>     >>
>     >> * *****
>     >>
>     >> *Some listers recommend R over SPSS: I just downloaded it and
>     barely got
>     >> past page 1 of the manual.  For my kind of students it’s complete
>     >> gobble-de-gook.  Others recommend Stata (mainly because of the
>     price
>     >> differential) but I’ve never seen side-by-side examples of
>     Stata and SPSS
>     >> syntax for the same exercise, but I have neither time nor
>     inclination to
>     >> learn yet another software application.*****
>     >>
>     >> * *****
>     >>
>     >> *I’m sticking with SPSS (and with the substantive content of
>     the surveys
>     >> I’m working with).  My pedagogic approach was always learning
>     by doing,
>     >> with a view to eventual employment as social researchers.  I
>     always used
>     >> actual data from real surveys and peppered my classes with
>     anecdotes from
>     >> years of field experience: I doubt if many current tutors have
>     much of
>     >> the
>     >> latter, if any.  My course was, and still is, unique, and
>     probably more
>     >> fun.  Aged 72, I just want to get the rest of it finished
>     before I pop my
>     >> clogs.*****
>     >>  ------------------------------
>     >>
>     >>  ****
>     >>
>     >> I checked the link to your paper, but only got the abstract.
>      As an early
>     >> retired academic on a fractional pension, I can’t afford to
>     subscribe to
>     >> journals: is there any chance you could let me have a copy of
>     the paper
>     >> so
>     >> that I can see the side-by-side examples?  ****
>     >>
>     >>  ****
>     >>
>     >> I’m more than happy to collaborate using the exercises on my
>     site.****
>     >>
>     >>  ****
>     >>
>     >> Thanks in advance****
>     >>
>     >>  ****
>     >>
>     >> John Hall****
>     >>
>     >>  ****
>     >>
>     >> John F Hall (Mr)****
>     >>
>     >> [retired academic survey researcher]****
>     >>
>     >>  ****
>     >>
>     >> Email:
>
>     > johnfhall@
>
>     >  ****
>     >>
>     >> Website: www.surveyresearch.weebly.com
>     <http://www.surveyresearch.weebly.com>
>     >> <http://surveyresearch.weebly.com/>
>     >> ****
>     >>
>     >>  ****
>     >>
>     >>  ****
>     >>
>     >>  ****
>     >>
>     >>  ****
>     >>
>     >>  ****
>     >>
>     >> ** **
>     >>
>     >>
>     >>  ===================== To manage your subscription to SPSSX-L,
>     send a
>     >> message to
>
>     > LISTSERV@.UGA
>
>     >  (not to SPSSX-L), with no body text
>     >> except the command. To leave the list, send the command SIGNOFF
>     SPSSX-L
>     >> For
>     >> a list of commands to manage subscriptions, send the command
>     INFO REFCARD
>
>
>
>
>
>     -----
>     Please reply to the list and not to my personal email.
>     Those desiring my consulting or training services please feel free
>     to email me.
>     --
>     View this message in context:
>     http://spssx-discussion.1045642.n5.nabble.com/Re-What-s-Better-R-SASR-SPSSR-or-StataR-tp5718122p5718129.html
>     Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
>     =====================
>     To manage your subscription to SPSSX-L, send a message to
>     [hidden email] <mailto:[hidden email]> (not
>     to SPSSX-L), with no body text except the
>     command. To leave the list, send the command
>     SIGNOFF SPSSX-L
>     For a list of commands to manage subscriptions, send the command
>     INFO REFCARD
>
>

[David Marso]

Wow, No Looping or Macros or User Programs?
BOSH!  WTH have I been doing for the past 20+ years?
I suspect Ward has minimal experience with "advanced?" SPSS features ;-)
---

Bruce Weaver wrote

I also do not agree with all of the pluses and minuses in Table 1.  E.g., SPSS is given a minus for "Simple recode syntax/procedures".  The RECODE syntax could not be much simpler, IMO.  Perhaps Ward is referring more to the GUI dialog for RECODE.  ;-)

It's not clear to me from the article how much actual experience Ward has with each of these packages.  The review by Mitchell (from UCLA Statistical Computing) that appeared a few years ago is now dated -- e.g., I think SPSS did not even have GENLIN when he wrote it.  But the think I liked about it was that Mitchell clearly had lots of hands-on experience with all the packages he discussed.  IIRC, they included SPSS, SAS, Stata and maybe R.

Cheers,
Bruce

Marta García-Granero-2 wrote

I got it (using the University library resources).

I don't agree with some "-" or "-/+" SPSS gets in table 1.

Regards,
Marta

El 19/02/2013 18:51, J. R. Carroll escribió:
> meh, I probably should have said "to solicit interest from the
> listserv to pester Brian to give it to us"
>
> And by "pester", I jest.
>
> But, I agree - the paper should be sent next round.  I always enjoy
> free scholarly papers :P
>
>
> -J
>
>
> ----
>
>
> J. R. Carroll
> Independent Researcher through Hurtz Labs
> Research Methods, Test Development, and Statistics
> www.jrcresearch.net <http://www.jrcresearch.net/>
> www.ontvp.com <http://www.ontvp.com>
> Cell:  [phone]
> Email: [hidden email] <mailto:[hidden email]>
> [hidden email] <mailto:[hidden email]>
> [hidden email] <mailto:[hidden email]>
> <https://www.facebook.com/J.R.Car><https://twitter.com/jNammer><http://www.linkedin.com/in/jrcarroll>
>
>
>
> On Tue, Feb 19, 2013 at 12:47 PM, David Marso <[hidden email]
> <mailto:[hidden email]>> wrote:
>
>     Hard to read a paper when there is only an abstract ;-(
>     --
>
>     J. R. Carroll-3 wrote
>     > I don't think there is one.  I think John took an off-list
>     conversation to
>     > the list as a way to solicit responses for Brian's paper.
>     >
>     > My apologies if I assumed too much, John.
>     >
>     > -j
>     >
>     >
>     > ----
>     >
>     >
>     > J. R. Carroll
>     > Independent Researcher through Hurtz Labs
>     > Research Methods, Test Development, and Statistics
>     > www.jrcresearch.net <http://www.jrcresearch.net>
>     > www.ontvp.com <http://www.ontvp.com>
>     > Cell: [phone] <tel:%28650%29%20776-6613>
>     > Email:
>
>     > jrcarroll@
>
>     >
>
>     > jrcarroll@
>
>     >
>
>     > jrc.csus@
>
>     > <https://www.facebook.com/J.R.Car>
>     >
>     <https://twitter.com/jNammer><http://www.linkedin.com/in/jrcarroll>
>     >
>     >
>     >
>     > On Tue, Feb 19, 2013 at 9:55 AM, Art Kendall <
>
>     > Art@
>
>     > > wrote:
>     >
>     >>  I don't see the original post to which this is a reply.
>     >>
>     >> Art Kendall
>     >> Social Research Consultants
>     >>
>     >> On 2/19/2013 4:55 AM, John F Hall wrote:
>     >>
>     >>  Brian****
>     >>
>     >> ** **
>     >>
>     >> Just had a quick look through your paper.  Very
>     thought-provoking.  I
>     >> particularly like your approach aimed at future employment
>     prospects for
>     >> students.  This mirrors my reasoning in setting up the Social
>     Research
>     >> Option of the BA Applied Social Studies at the then Polytechnic
>     of North
>     >> London in 1976.  In those days, given its universal adoption by
>     academia
>     >> and the public sector, plus the availability of the manual in
>     any decent
>     >> bookshop, the only sensible software option was SPSS.****
>     >>
>     >> ** **
>     >>
>     >> I take your point about the constraints on course design: the final
>     >> 1991-92 version of my SPSS-syntax-based undergraduate course
>     was taken in
>     >> semester 2 of their second year.  It  consisted of 13 weeks x 3
>     hour
>     >> sessions, comprising one hour of formal teaching followed by a
>     practical
>     >> computer lab session (in two shifts of half a class each)
>     closing with a
>     >> short discussion of students’ output.  Week 14 was for
>     assessment.  ****
>     >>
>     >> ** **
>     >>
>     >> On using syntax (my unashamed preference over point-and-click)
>     see the
>     >> syllabus and specimen assessment for the original course on my
>     site.
>     >> ****
>     >>
>     >> The examples are from 1992, but the same syllabus and
>     assessment format
>     >> was used for 10 years or so before then.  I can’t give a direct
>     URL for
>     >> them, but you can access them in pdf format from the links on:****
>     >>
>     >> ** **
>     >>
>     >>
>     http://surveyresearch.weebly.com/background-to-current-project.html****
>     >>
>     >> ** **
>     >>
>     >> *Survey Analysis Workshop – Syllabus*
>     >>
>     >> *            ***
>     >>
>     >> Syllabus for postgraduate course Survey Analysis Workshop
>     (using SPSS)
>     >> taught at Polytechnic of North London as at March 1992. Forms
>     basis for
>     >> updated course materials on this website****
>     >>
>     >> ** **
>     >>
>     >> *Survey Analysis Workshop: specimen assessment*
>     >>
>     >> * *
>     >>
>     >> Specimen assessment for course, as distributed to students.
>     Gives an idea
>     >> of the sort of things you should understand and have learned to
>     do by the
>     >> end of the course.****
>     >>
>     >> ** **
>     >>
>     >> Students were then able to go to their professional placements
>     in their 3
>     >> rd year with a fair degree of technical competence, but always
>     had free
>     >> access to the Polytechnic–services (data-prep, printing,
>     computing) and
>     >> to
>     >> myself for professional advice and assistance.  Our students
>     were always
>     >> in great demand and some very impressive research was done for
>     their
>     >> placement agencies, some resulting in professional publications
>     with the
>     >> student as first author.  Many of our students were offered
>     jobs in these
>     >> agencies before they even came back for their 4th year in
>     college.****
>     >>
>     >> ** **
>     >>
>     >> The undergraduate course was originally in the 4th year, and
>     therefore
>     >> not first taught until 1980, but was brought forward into year 2 in
>     >> around
>     >> 1982.  It was effectively the same as the highly acclaimed and much
>     >> sought-after *Survey Analysis Workshop*, a postgraduate course
>     >> (practice-oriented, hands-on, part-time, evening) I started in
>     1976.
>     >> Great
>     >> students, great fun.  Materials from the latter have now been
>     converted,
>     >> updated and greatly expanded as a Teach-Yourself course using
>     SPSS (19)
>     >> for
>     >> Windows.  The full course is now available on:
>     >>
>     http://surveyresearch.weebly.com/1-survey-analysis-workshop.html but I
>     >> still have a lot more tutorials and exercises to write, check,
>     >> upload.****
>     >>
>     >> ** **
>     >>
>     >> On looking at your table comparing the capabilities of R, SAS,
>     Stata and
>     >> SPSS, I’m not sure you’re right about SPSS and large files.  I’ve
>     >> recently been using SPSS19 on files with 35,600  (European
>     Social Survey)
>     >> and 163,200 respondents (National Well-Being Survey).  Your
>     table also
>     >> shows SPSS having limitations for simple recode/syntax
>     procedures.  I
>     >> disagree: this is where SPSS reigns supreme (at least if it’s
>     used in
>     >> syntax mode).  Lower down the table you indicate limitations in
>     SPSS for
>     >> handling different data formats and for export to Excel etc.
>      Colleagues
>     >> on the SPSS-X list-server are better able to comment on that.****
>     >>
>     >> ** **
>     >>
>     >> What is the copyright position for wider distribution of your
>     article?
>     >> Is
>     >> it yours or does it reside with Sage?  I think you/they should
>     consider
>     >> circulating it to the SPSS-X listerver and the Quantitative methods
>     >> teaching group and also to user-groups for SAS, R and Stata.
>      This should
>     >> result in a cascade of responses from a range of very
>     experienced users
>     >> (and programmers) which you could use in a follow-up article.****
>     >>
>     >> ** **
>     >>
>     >> Meanwhile I’ll dig out a few simple exercises from my tutorials
>     and ask
>     >> colleagues versed in R, Stata (*and SAS?) to replicate them:
>     I’d still
>     >> like to see them side-by-side with notes of how easy/hard they
>     are and
>     >> how
>     >> long they take to do.****
>     >>
>     >> ** **
>     >>
>     >> Best wishes, and thanks again for the sight of your article.****
>     >>
>     >> ** **
>     >>
>     >> John****
>     >>
>     >> ** **
>     >>
>     >> ** **
>     >>
>     >> John F Hall (Mr)****
>     >>
>     >> [retired academic survey researcher]****
>     >>
>     >> ** **
>     >>
>     >> Email:
>
>     > johnfhall@
>
>     >  ****
>     >>
>     >> Website: www.surveyresearch.weebly.com
>     <http://www.surveyresearch.weebly.com>
>     >> <http://surveyresearch.weebly.com/>
>     >> ****
>     >>
>     >> ** **
>     >>
>     >> ** **
>     >>
>     >> ** **
>     >>
>     >> ** **
>     >>
>     >> ** **
>     >>
>     >> *From:* John F Hall [mailto:
>
>     > johnfhall@
>
>     >  <
>
>     > johnfhall@
>
>     > >]
>     >> *Sent:* 19 February 2013 08:37
>     >> *To:* 'Brian Ward'
>     >> *Subject:* RE: What's Better-R, SASR, SPSSR, or StataR?****
>     >>
>     >> ** **
>     >>
>     >> Brian****
>     >>
>     >> ** **
>     >>
>     >> Many thanks for this.  I’ll check it out as soon as I’ve had my
>     breakfast
>     >> and get back to you.  ****
>     >>
>     >> ** **
>     >>
>     >> Your students may find my website useful: everything is freely
>     >> downloadable.****
>     >>
>     >> ** **
>     >>
>     >> John****
>     >>
>     >> ** **
>     >>
>     >> *From:* Brian Ward [mailto:
>
>     > bwward3@
>
>     >  <
>
>     > bwward3@
>
>     > >]
>     >> *Sent:* 19 February 2013 05:25
>     >> *To:* John F Hall
>     >> *Subject:* Re: What's Better-R, SASR, SPSSR, or StataR?****
>     >>
>     >> ** **
>     >>
>     >> John,****
>     >>
>     >>  ****
>     >>
>     >> I would be happy to send you a copy of my manuscript (see
>     attached).
>     >> However, it is a very brief teaching note (truncated by the
>     request of
>     >> the
>     >> journal) that was meant to simply encourage conversation among
>     college
>     >> instructors on what statistical software to use. It is
>     non-technical, and
>     >> based on your conversation below, it may not be precisely what
>     you are
>     >> looking for. Regardless, I hope it may help to some extent.****
>     >>
>     >>  ****
>     >>
>     >> All the best,****
>     >>
>     >> Brian****
>     >>
>     >> On Sun, Feb 17, 2013 at 4:44 AM, John F Hall <
>
>     > johnfhall@
>
>     > > wrote:*
>     >> ***
>     >>
>     >> Dear Brian****
>     >>
>     >>  ****
>     >>
>     >> Your recent JASS paper *What’s Better—R, SAS®, SPSS®, or
>     Stata®? Thoughts
>     >> for Instructors of Statistics and Research Methods
>     >>
>     Courses<http://jax.sagepub.com/content/early/2013/01/21/1936724412450570.abstract?utm_content=Visibility_and_reach_O&utm_medium=social_Twitter&utm_campaign=G_ALL_T_2012&utm_source=open&keytype=ref&siteid=spjax&utm_term=Sociology&ijkey=YyG8yvdawCyw6>
>     >> * was highlighted in a recent
>     >>
>     discussion<http://natcenlearning.ning.com/group/makingresearchreal/forum/topics/spss-sas-stata-or-r-what-s-best-for-teaching>between
>     >> teachers of quantitative methods in the social sciences for which
>     >> significant funding has been allocated by the Nuffield
>     Foundation, the
>     >> Higher Education Academy and the Economic and Social Research
>     Council.
>     >> **
>     >> **
>     >>
>     >>  ****
>     >>
>     >> There are currently several discussions on the SPSS-X
>     listserver, the QM
>     >> teachers forum and the above Natcen hosted site.  The first
>     theme centres
>     >> on the use of syntax vs GUI in SPSS; the second has champions
>     of R, Stata
>     >> etc. over SPSS (for survey analysis); the third reveals significant
>     >> differences between disciplines in what should be taught, and how
>     >> (including trawls for recommended introductory teaching
>     materials).****
>     >>
>     >>  ****
>     >>
>     >> http://www.quantitativemethods.ac.uk****
>     >>
>     >>  ****
>     >>
>     >>
>     *********************************************************************
>     >>
>     >> QM Teachers' Mailing list****
>     >>
>     >> subscribe at
>
>     > quantitative_methods_teaching-join@.ac
>
>     > ****
>     >>
>     >>
>     *********************************************************************
>     >>
>     >> QM teaching blog: http://qmteaching.wordpress.com/****
>     >>
>     >>  ****
>     >>
>     >>
>     *********************************************************************
>     >>
>     >> Resources for teaching QM available at:****
>     >>
>     >>
>     >>
>     http://www.esrc.ac.uk/funding-and-guidance/tools-and-resources/undergraduate-QM/index.aspx
>     >> ****
>     >>
>     >>
>     **********************************************************************
>     >>
>     >>  ****
>     >>
>     >> Here is my initial message to the new Natcen-hosted group:****
>     >>
>     >>  ****
>     >>
>     >> I've just joined this group, so feeling my way tentatively
>     around.****
>     >>
>     >> Members may like to look at my website, Journeys in Survey
>     >>
>     Research,<http://surveyresearch.weebly.com/index.html>based on
>     >> almost 50 years working in survey research and teaching research
>     >> methods. ****
>     >>
>     >> The site has three main components:
>     >>
>     >> *1:*
>     >>
>     <http://natcenlearning.ning.com/1-survey-analysis-workshop.html>*Survey
>     >> Analysis Workshop
>     >>
>     (SPSS)*<http://natcenlearning.ning.com/1-survey-analysis-workshop.html>
>     >> *2: **Survey Research
>     >>
>     Practice*<http://natcenlearning.ning.com/2-survey-research-practice.html>
>     >> *3: **Subjective Social Indicators (Quality of
>     >>
>     Life)*<http://natcenlearning.ning.com/3-subjective-social-indicators-quality-of-life.html>
>     >> ****
>     >>
>     >> The first derives from the SPSS-based courses in data
>     management and
>     >> analysis I designed and taught at SSRC Summer Schools from 1972
>     to 1976
>     >> and
>     >> to postgrads and undergrads at the then Polytechnic of North
>     London from
>     >> 1976 to 1992, when I took early retirement. Learning materials
>     from these
>     >> courses have now been converted, updated and greatly revised
>     for use with
>     >> SPSS for Windows. So far there are 450+ pages of teach-youself
>     tutorias
>     >> with not an equation yet in sight. They are syntax-based (but many
>     >> examples
>     >> and exercises are repeated using the GUI menus. They are aimed
>     at total
>     >> newbies, and assume no previous experience, but even experienced
>     >> researchers and teachers may learn a thing or two from them.****
>     >>
>     >> The second contains links to useful on-line resources for
>     survey research
>     >> plus a wealth of (not easily available, if at all) materials
>     from my time
>     >> at the then SSRC Survey Unit and my own Survey research Unit at the
>     >> Polytechnic of North London.****
>     >>
>     >> The third is a new section created when the contents grew too
>     large for
>     >> the second. It covers all the Quality of Life in Britain
>     surveys I did
>     >> with
>     >> Mark Abrams from 1971 to 1975 and links to other previous and
>     ccurrent
>     >> subjective social indicator work in UK, Europe and the USA.****
>     >>
>     >> Whilst not explicitly oriented to the teaching of quantitative
>     methods,
>     >> my
>     >> own students found they learned more statistics from my courses
>     than they
>     >> did from the offical stats course. ****
>     >>
>     >> Indeed the new degree I was appointed to design and head up at
>     PNL in
>     >> 1976
>     >> (BA Applied Social Studies, Social Research Option) was openly
>     intended
>     >> to
>     >> remedy the pathetic state of QM teaching to social science
>     students in UK
>     >> universities, the bulk of which could be attributed to the poor
>     quality
>     >> of
>     >> supervisors, anti-pathy to empiricism, but most of all to a lack of
>     >> numeracy in undergraduates.****
>     >>
>     >> Feedback on the site from colleagues and students has been very
>     positive:
>     >> hopefully members will feel the same.****
>     >>
>     >> I’m particularly interested in comparisons of SPSS with other
>     software to
>     >> perform the same tasks as those in the SPSS syntax-based
>     tutorials on my
>     >> website, particularly the very early ones.  I have been in
>     correspondence
>     >> with Laurie Moseley (Emeritus Pofessor, Health Services Research,
>     >> Glamorgan) about R, which I downloaded two days ago to check it
>     out.
>     >> Here’s an extract from what I said to him:****
>     >>  ------------------------------
>     >>
>     >> *There are three main issues for me: first that some people (mainly
>     >> statisticians, psychologists and econometricians) don’t seem to
>     be able
>     >> to
>     >> think outside their disciplinary box; second, that they
>     misunderstand my
>     >> approach using SPSS syntax as a route to understanding the
>     language and
>     >> logic of (survey) data analysis and to acquiring marketable
>     technical and
>     >> quantitative skills; third that they seem to define survey
>     analysis as
>     >> dealing with complex sample designs, imputed data, survey error
>     etc (look
>     >> at the course outlines) and miss the original point of the research
>     >> question.  As John Tukey once said, “All the statistics in the
>     world
>     >> won’t
>     >> save you if you asked the wrong question in the first place!”*****
>     >>
>     >> * *****
>     >>
>     >> *Some listers recommend R over SPSS: I just downloaded it and
>     barely got
>     >> past page 1 of the manual.  For my kind of students it’s complete
>     >> gobble-de-gook.  Others recommend Stata (mainly because of the
>     price
>     >> differential) but I’ve never seen side-by-side examples of
>     Stata and SPSS
>     >> syntax for the same exercise, but I have neither time nor
>     inclination to
>     >> learn yet another software application.*****
>     >>
>     >> * *****
>     >>
>     >> *I’m sticking with SPSS (and with the substantive content of
>     the surveys
>     >> I’m working with).  My pedagogic approach was always learning
>     by doing,
>     >> with a view to eventual employment as social researchers.  I
>     always used
>     >> actual data from real surveys and peppered my classes with
>     anecdotes from
>     >> years of field experience: I doubt if many current tutors have
>     much of
>     >> the
>     >> latter, if any.  My course was, and still is, unique, and
>     probably more
>     >> fun.  Aged 72, I just want to get the rest of it finished
>     before I pop my
>     >> clogs.*****
>     >>  ------------------------------
>     >>
>     >>  ****
>     >>
>     >> I checked the link to your paper, but only got the abstract.
>      As an early
>     >> retired academic on a fractional pension, I can’t afford to
>     subscribe to
>     >> journals: is there any chance you could let me have a copy of
>     the paper
>     >> so
>     >> that I can see the side-by-side examples?  ****
>     >>
>     >>  ****
>     >>
>     >> I’m more than happy to collaborate using the exercises on my
>     site.****
>     >>
>     >>  ****
>     >>
>     >> Thanks in advance****
>     >>
>     >>  ****
>     >>
>     >> John Hall****
>     >>
>     >>  ****
>     >>
>     >> John F Hall (Mr)****
>     >>
>     >> [retired academic survey researcher]****
>     >>
>     >>  ****
>     >>
>     >> Email:
>
>     > johnfhall@
>
>     >  ****
>     >>
>     >> Website: www.surveyresearch.weebly.com
>     <http://www.surveyresearch.weebly.com>
>     >> <http://surveyresearch.weebly.com/>
>     >> ****
>     >>
>     >>  ****
>     >>
>     >>  ****
>     >>
>     >>  ****
>     >>
>     >>  ****
>     >>
>     >>  ****
>     >>
>     >> ** **
>     >>
>     >>
>     >>  ===================== To manage your subscription to SPSSX-L,
>     send a
>     >> message to
>
>     > LISTSERV@.UGA
>
>     >  (not to SPSSX-L), with no body text
>     >> except the command. To leave the list, send the command SIGNOFF
>     SPSSX-L
>     >> For
>     >> a list of commands to manage subscriptions, send the command
>     INFO REFCARD
>
>
>
>
>
>     -----
>     Please reply to the list and not to my personal email.
>     Those desiring my consulting or training services please feel free
>     to email me.
>     --
>     View this message in context:
>     http://spssx-discussion.1045642.n5.nabble.com/Re-What-s-Better-R-SASR-SPSSR-or-StataR-tp5718122p5718129.html
>     Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
>     =====================
>     To manage your subscription to SPSSX-L, send a message to
>     [hidden email] <mailto:[hidden email]> (not
>     to SPSSX-L), with no body text except the
>     command. To leave the list, send the command
>     SIGNOFF SPSSX-L
>     For a list of commands to manage subscriptions, send the command
>     INFO REFCARD
>
>