SPSSX Discussion

Re: [APA] query about online texts

Classic

List

Threaded

7 messages Options

Art Kendall

Re: [APA] query about online texts

Long time no see!

I do not know about specific online texts to recommend if you are using
them to teach.
If you are teaching, SPSS comes with tutorials, "coaches" to help
interpret output etc.
You might check the archives at
http://www.listserv.uga.edu/archives/spssx-l.html
I know this topic has come up. If you don't find what you want in the
archives, you can join the list there and post your question. I would
suggest that you be more specific about what kind of stat you are
interested in and who would be using the "textbook" .

If you have specific stat/methods questions , feel free to ask me.

Art Kendall
Social Research Consultants
Art@Dr Kendall.org
301-864-5570

Wittig, Michele wrote:
> I'm away from most of my books for 6 months and am wondering if members of this list can recommend some good, free, online statistical "textbooks." I searched and found a couple. For example, one is:
>
> http://www/statsoft.com/textbook
>
> Although that is a good source, it didn't have the answer to my question, so maybe there are more comprehensive sources or ones than can be searched with more keywords. thanks! MWittig
>
>

=====================
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

Art Kendall
Social Research Consultants

Bruce Weaver

Re: [APA] query about online texts

Administrator

Art Kendall wrote

Long time no see!

I do not know about specific online texts to recommend if you are using
them to teach.
If you are teaching, SPSS comes with tutorials, "coaches" to help
interpret output etc.
You might check the archives at
http://www.listserv.uga.edu/archives/spssx-l.html
I know this topic has come up. If you don't find what you want in the
archives, you can join the list there and post your question. I would
suggest that you be more specific about what kind of stat you are
interested in and who would be using the "textbook" .

If you have specific stat/methods questions , feel free to ask me.

Art Kendall
Social Research Consultants
Art@Dr Kendall.org
301-864-5570

Hi Art. Without knowing a bit more (e.g., topics, level), it's hard to make suggestions. But here are some sites I think are good. Perhaps they'll be useful to your friend.

http://davidmlane.com/hyperstat/index.html
http://onlinestatbook.com/
http://faculty.chass.ncsu.edu/garson/PA765/statnote.htm

The first two are suitable for an introductory to intermediate level course in psychology, for example. The 3rd is more advanced and comprehensive.

Cheers,
Bruce

--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

PLEASE NOTE THE FOLLOWING:
1. My Hotmail account is not monitored regularly. To send me an e-mail, please use the address shown above.
2. The SPSSX Discussion forum on Nabble is no longer linked to the SPSSX-L listserv administered by UGA (https://listserv.uga.edu/).

Steve Simon, P.Mean Consulting

Re: [APA] query about online texts

In reply to this post by Art Kendall

Wittig, Michele wrote:

> I'm away from most of my books for 6 months and am wondering if
> members of this list can recommend some good, free, online statistical
> "textbooks."

I'm looking forward to the day when I can carry all of my statistics
books on my Kindle, but that won't happen anytime soon. For what it's
worth, the Kindle is very nice, but most of the books for it are not free.

With a free textbook, you get what you pay for, of course. A notable
exception is the Engineering Statistics Handbook. It is free because it
was developed by government employees.
www.itl.nist.gov/div898/handbook/index.htm

Some authors have also negotiated an agreement with their publisher to
make a textbook freely available once it has been out of print for a
while. An example of this is "Applications, Basics, and Computing of
Exploratory Data Analysis" by Velleman and Hoaglin.

http://hdl.handle.net/1813/78

There was also an effort to develop a statistics textbook for the
typical introductory college class using a collaborative effort and an
open source license, but I can't find the details of this project.
--
Steve Simon, Standard Disclaimer
"The first three steps in a descriptive
data analysis, with examples in PASW/SPSS"
Thursday, January 21, 2010, 11am-noon, CST.
Details at www.pmean.com/webinars

=====================
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

ViAnn Beadle

Re: [APA] query about online texts

Good serious statistical textbooks are very expensive--they have high
production costs and limited distribution. Amazon occasionally provides some
of them on Kindle but not at a significant discount. I'm fortunate to live
close to a land-grant university which provides slightly limited borrowing
privileges for all citizens of the state.

Another possibility is to look for statistical tutorials online from major
universities.

Also, I think it's really unfortunate that many companies do not provide a
decent library or book purchase budget for their knowledge workers.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Steve Simon, P.Mean Consulting
Sent: Thursday, January 07, 2010 1:38 PM
To: [hidden email]
Subject: Re: [APA] query about online texts

Wittig, Michele wrote:

> I'm away from most of my books for 6 months and am wondering if
> members of this list can recommend some good, free, online statistical
> "textbooks."

I'm looking forward to the day when I can carry all of my statistics books
on my Kindle, but that won't happen anytime soon. For what it's worth, the
Kindle is very nice, but most of the books for it are not free.

With a free textbook, you get what you pay for, of course. A notable
exception is the Engineering Statistics Handbook. It is free because it was
developed by government employees.
www.itl.nist.gov/div898/handbook/index.htm

Some authors have also negotiated an agreement with their publisher to make
a textbook freely available once it has been out of print for a while. An
example of this is "Applications, Basics, and Computing of Exploratory Data
Analysis" by Velleman and Hoaglin.

http://hdl.handle.net/1813/78

There was also an effort to develop a statistics textbook for the typical
introductory college class using a collaborative effort and an open source
license, but I can't find the details of this project.
--
Steve Simon, Standard Disclaimer
"The first three steps in a descriptive
data analysis, with examples in PASW/SPSS"
Thursday, January 21, 2010, 11am-noon, CST.
Details at www.pmean.com/webinars

=====================
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

=====================
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

parisec

code for block randomization

In reply to this post by Art Kendall

Hi all,

Someone was kind enough to share this code a few years back and I have used a few times for randomization of subjects to conditions in studies. I now am working on a study where I need to have patients randomized in smaller chunks so that within a group of 4 patients, 2 get assigned to group 1 and 2 get assigned to group 2. There are 50 patients to so I would have 12 blocks of 4 patients and one block of 2 patients. Within each block, I want a 1:1 randomization.

Any assistance is appreciated.

Thanks
Carol

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

*Step 1 - create the file with 50 IDs.

INPUT PROGRAM.
LOOP id=1 TO 200 .
- END CASE.
END LOOP .
END FILE.
END INPUT PROGRAM.

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

After step 1 is where I need code to do the following:

1) assign the following "block" for IDs:
1-4=1
5-8=2
9-12=3
13-16=4
17-20=5
21-24=6
25-28=7
29-32=8
33-36=9
37-40=10
41-44=11
45-48=12
49-50=13
2) Apply the remaining code below to each block.
******************************

*Step 2 - create the 1s and 0s for group.

USE ALL.
do if $casenum = 1.
compute #s_$_1=100.
compute #s_$_2=200.
end if.
do if #s_$_2 > 0.
compute group= uniform(1)* #s_$_2 < #s_$_1.
compute #s_$_1 = #s_$_1 - group.
compute #s_$_2 = #s_$_2 - 1.
else.
compute group= 0.
end if.
VARIABLE LABEL group '100 from the first 200 cases (SAMPLE)'.
FORMAT group (f1.0).
EXECUTE .

*label the values of 0 and 1.
value label group 0 'Block' 1 'No Block'.

=====================
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

Ruben Geert van den Berg

Re: code for block randomization

Dear Carol,

If I get you right, the code below should work.

Best,

Ruben

*Testdata.

input program.

loop id=1 to 50.

end case.

end loop.

end file.

end input program.

compute group=tru((id-1)/4)+1.

*Generating experimental condition.

set seed 1.

compute t1=rv.uni(0,1).

rank t1 by group

/nti(2).

delete variables t1.

value labels nt1 1'Condition A'2'Condition B'.

rename variables nt1=Experimental_condition.

> Date: Fri, 29 Oct 2010 13:41:21 -0700
> From: [hidden email]
> Subject: code for block randomization
> To: [hidden email]
>
> Hi all,
>
> Someone was kind enough to share this code a few years back and I have used a few times for randomization of subjects to conditions in studies. I now am working on a study where I need to have patients randomized in smaller chunks so that within a group of 4 patients, 2 get assigned to group 1 and 2 get assigned to group 2. There are 50 patients to so I would have 12 blocks of 4 patients and one block of 2 patients. Within each block, I want a 1:1 randomization.
>
>
> Any assistance is appreciated.
>
> Thanks
> Carol
>
>
> ***********************
>
> *Step 1 - create the file with 50 IDs.
>
> INPUT PROGRAM.
> LOOP id=1 TO 200 .
> - END CASE.
> END LOOP .
> END FILE.
> END INPUT PROGRAM.
>
> ***************************
>
> After step 1 is where I need code to do the following:
>
> 1) assign the following "block" for IDs:
> 1-4=1
> 5-8=2
> 9-12=3
> 13-16=4
> 17-20=5
> 21-24=6
> 25-28=7
> 29-32=8
> 33-36=9
> 37-40=10
> 41-44=11
> 45-48=12
> 49-50=13
> 2) Apply the remaining code below to each block.
> ******************************
>
> *Step 2 - create the 1s and 0s for group.
>
>
> USE ALL.
> do if $casenum = 1.
> compute #s_$_1=100.
> compute #s_$_2=200.
> end if.
> do if #s_$_2 > 0.
> compute group= uniform(1)* #s_$_2 < #s_$_1.
> compute #s_$_1 = #s_$_1 - group.
> compute #s_$_2 = #s_$_2 - 1.
> else.
> compute group= 0.
> end if.
> VARIABLE LABEL group '100 from the first 200 cases (SAMPLE)'.
> FORMAT group (f1.0).
> EXECUTE .
>
> *label the values of 0 and 1.
> value label group 0 'Block' 1 'No Block'.
>
> =====================
> 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

parisec

Re: code for block randomization

Dear Ruben,

This worked perfectly.

Thank you very much for your help.

Carol

From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Ruben van den Berg
Sent: Sunday, October 31, 2010 1:06 PM
To: [hidden email]
Subject: Re: code for block randomization

Dear Carol,

If I get you right, the code below should work.

Best,

Ruben

*Testdata.

input program.

loop id=1 to 50.

end case.

end loop.

end file.

end input program.

compute group=tru((id-1)/4)+1.

*Generating experimental condition.

set seed 1.

compute t1=rv.uni(0,1).

rank t1 by group

/nti(2).

delete variables t1.

value labels nt1 1'Condition A'2'Condition B'.

rename variables nt1=Experimental_condition.