Missing Validation Button

[TheDuck]

CONTENTS DELETED

The author has deleted this message.

[Poes, Matthew Joseph]

There is no validation section, data can't be validated with a simple button click.  It's also worth noting that there is a big difference between validation and reliability.  Reliability can be tested with some simple button clicks, and this does exist under the scale section.  Dimension reduction is a slightly more complex form of reliability analysis, in a way, as it contains factor analysis, which allows you to test the factor structure of the scale, and from this you can infer similar reliability information as you get from Cronbach's alpha.

I'm not sure what text you have, but if it's confusing the concepts of validation and reliability, I would consider that to be problematic.  You may want to reread and be certain you have not missed anything in the lessons.  Validation can take a variety of forms (since true direct validation is typically impossible), and all of the require that you have multiple data sets, multiple related measures and outcomes, and run a series of analysis.  The analysis used for validation depend on the scale, but typically involve some form of General linear model.  Discriminant validity, as an example, refers to the ability of a measure to discriminate between what it should be measuring, and what it should not be measuring.  Using a simple regression, you can try to predict an appropriate outcome, and then look at the model r squared and model coefficients.  From there, you then replace the appropriate outcome with one that you know should theoretically be unrelated.  In this case you !
 hope the model is unable to predict the unrelated outcome.  In this case, there will be no section which is labeled validity because validation is based on a set of theoretical concepts, and it's up to the user to understand how he or she can address these concepts based on a sound basic understanding of statistical principles.

And now for a short rant.  I think it's absolutely crucial that people new to SPSS understand that it is just a tool.  While IBM has been working hard to make the program fairly automated and idiot proof, it does not change the fact that as a user, we must understand the statistics that underlie the procedures.  The worst thing someone could do is focus on learning the software and not know the statistics and related concepts, theories, and philosophies.  This would be like learning how to use Microsoft word and not being literate.  If you can't read or write, then a word processing program is pointless.  I ended up having a lengthy and pointless argument last week with a  PhD professor, who uses statistics every day, over why her PhD candidate student could utilize either of two approaches with identical results (Poisson regression verse logistic regression).  They simply didn't have the fundamental understanding to know that in this scenario, they were nearly identical (th!
 e coefficients of both models were insignificantly different in this case), and in this scenario, it was actually more appropriate to use the logistic regression anyway.  Validity and reliability are hot button topics for me because so many people mix the two up and get it so very wrong.  A measure is not, in my book, considered a good measure just because it shows strong reliability.  Just because it measures the same thing repeatedly doesn't mean that it measures what you think it does.  More than half of the measures I've evaluated in my short tenure have been shown to be nothing more than climate surveys measuring the general happiness of the participants, and not the detailed constructs they intend to measure.

Matthew J Poes
Research Data Specialist
Center for Prevention Research and Development
University of Illinois
510 Devonshire Dr.
Champaign, IL 61820
Phone: [phone]
email: [hidden email]


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of TheDuck
Sent: Sunday, July 01, 2012 8:37 PM
To: [hidden email]
Subject: Missing Validation Button

Ok, so I am a student and am learning SPSS. The lesson I am on now is discussing validating the data. Well I have data put in and went to validate as the book states to. However, under Data there is no Validation section.
Any clue why or where it is?

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Missing-Validation-Button-tp5713937.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

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

[Maguin, Eugene]

Duck,
Tell us what you mean by 'data validation'/Tell us how you'd do 'data validation'?

Gene Maguin


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of TheDuck
Sent: Sunday, July 01, 2012 9:37 PM
To: [hidden email]
Subject: Missing Validation Button

Ok, so I am a student and am learning SPSS. The lesson I am on now is discussing validating the data. Well I have data put in and went to validate as the book states to. However, under Data there is no Validation section.
Any clue why or where it is?

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Missing-Validation-Button-tp5713937.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

=====================
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]

The OP is referring to the Validation menu which IIRC, is part of the Data
Preparation option.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Maguin, Eugene
Sent: Monday, July 02, 2012 8:26 AM
To: [hidden email]
Subject: Re: Missing Validation Button

Duck,
Tell us what you mean by 'data validation'/Tell us how you'd do 'data
validation'?

Gene Maguin


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
TheDuck
Sent: Sunday, July 01, 2012 9:37 PM
To: [hidden email]
Subject: Missing Validation Button

Ok, so I am a student and am learning SPSS. The lesson I am on now is
discussing validating the data. Well I have data put in and went to validate
as the book states to. However, under Data there is no Validation section.
Any clue why or where it is?

--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/Missing-Validation-Button-tp57
13937.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

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

[Bruce Weaver]

I suspect TheDuck is referring to VALIDATEDATA, which is available in the Data Preparation option.  If it's not available via the GUI, the most likely explanation is that the Data Preparation option is not licensed.

HTH.

Maguin, Eugene wrote

Duck,
Tell us what you mean by 'data validation'/Tell us how you'd do 'data validation'?

Gene Maguin


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of TheDuck
Sent: Sunday, July 01, 2012 9:37 PM
To: [hidden email]
Subject: Missing Validation Button

Ok, so I am a student and am learning SPSS. The lesson I am on now is discussing validating the data. Well I have data put in and went to validate as the book states to. However, under Data there is no Validation section.
Any clue why or where it is?

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Missing-Validation-Button-tp5713937.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

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

[Melissa Ives]

VALIDATEDATA is not a free option.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Bruce Weaver
Sent: Monday, July 02, 2012 9:56 AM
To: [hidden email]
Subject: Re: [SPSSX-L] Missing Validation Button

I suspect TheDuck is referring to VALIDATEDATA, which is available in the Data Preparation option.  If it's not available via the GUI, the most likely explanation is that the Data Preparation option is not licensed.

HTH.




Maguin, Eugene wrote

>
> Duck,
> Tell us what you mean by 'data validation'/Tell us how you'd do 'data
> validation'?
>
> Gene Maguin
>
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of TheDuck
> Sent: Sunday, July 01, 2012 9:37 PM
> To: SPSSX-L@.UGA
> Subject: Missing Validation Button
>
> Ok, so I am a student and am learning SPSS. The lesson I am on now is
> discussing validating the data. Well I have data put in and went to
> validate as the book states to. However, under Data there is no
> Validation section.
> Any clue why or where it is?
>
> --
> View this message in context:
> http://spssx-discussion.1045642.n5.nabble.com/Missing-Validation-Butto
> n-tp5713937.html Sent from the SPSSX Discussion mailing list archive
> at Nabble.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
>
> =====================
> 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
>

-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Missing-Validation-Button-tp5713937p5713947.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

PRIVILEGED AND CONFIDENTIAL INFORMATION
This transmittal and any attachments may contain PRIVILEGED AND
CONFIDENTIAL information and is intended only for the use of the
addressee. If you are not the designated recipient, or an employee
or agent authorized to deliver such transmittals to the designated
recipient, you are hereby notified that any dissemination,
copying or publication of this transmittal is strictly prohibited. If
you have received this transmittal in error, please notify us
immediately by replying to the sender and delete this copy from your
system. You may also call us at [phone] for assistance.

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

[Poes, Matthew Joseph]

I didn't realize such a thing existed, but this now brings up a different issue.  Different meanings of the word validation, I'm glad you guys picked that up, I was confused on the issue and responded to the topic starter with a rant on measurement validation.  Data validation in this module is for ensuring that the data meets certain validation rules, that it was entered correctly, correct?  Something that I traditionally rely on either SPSS validation code that I write, or handling the whole thing in SQL instead.

Matthew J Poes
Research Data Specialist
Center for Prevention Research and Development
University of Illinois
510 Devonshire Dr.
Champaign, IL 61820
Phone: [phone]
email: [hidden email]



-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Melissa Ives
Sent: Monday, July 02, 2012 10:07 AM
To: [hidden email]
Subject: Re: Missing Validation Button

VALIDATEDATA is not a free option.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Bruce Weaver
Sent: Monday, July 02, 2012 9:56 AM
To: [hidden email]
Subject: Re: [SPSSX-L] Missing Validation Button

I suspect TheDuck is referring to VALIDATEDATA, which is available in the Data Preparation option.  If it's not available via the GUI, the most likely explanation is that the Data Preparation option is not licensed.

HTH.




Maguin, Eugene wrote

>
> Duck,
> Tell us what you mean by 'data validation'/Tell us how you'd do 'data
> validation'?
>
> Gene Maguin
>
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of TheDuck
> Sent: Sunday, July 01, 2012 9:37 PM
> To: SPSSX-L@.UGA
> Subject: Missing Validation Button
>
> Ok, so I am a student and am learning SPSS. The lesson I am on now is
> discussing validating the data. Well I have data put in and went to
> validate as the book states to. However, under Data there is no
> Validation section.
> Any clue why or where it is?
>
> --
> View this message in context:
> http://spssx-discussion.1045642.n5.nabble.com/Missing-Validation-Butto
> n-tp5713937.html Sent from the SPSSX Discussion mailing list archive
> at Nabble.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
>
> =====================
> 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
>

-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Missing-Validation-Button-tp5713937p5713947.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

PRIVILEGED AND CONFIDENTIAL INFORMATION
This transmittal and any attachments may contain PRIVILEGED AND CONFIDENTIAL information and is intended only for the use of the addressee. If you are not the designated recipient, or an employee or agent authorized to deliver such transmittals to the designated recipient, you are hereby notified that any dissemination, copying or publication of this transmittal is strictly prohibited. If you have received this transmittal in error, please notify us immediately by replying to the sender and delete this copy from your system. You may also call us at [phone] for assistance.

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

[Bibel, Daniel (POL)]

Appreciate any help:

I had a trial version of SPSS 20 installed; in addition I installed Python 2.7

The trial has expired, and I have fallen back to SPSS 18; which has Python 2.6 installed.

I am trying to run syntax with V18 and get the following:

SPSSINC SPLIT DATASET SPLITVAR=Agency
/OUTPUT DIRECTORY= "r:\ucrr\temp" DELETECONTENTS=YES
/OPTIONS NAMES=VALUES PRINTLIST=YES
FILELIST="results".

>Error # 6887.  Command name: BEGIN PROGRAM
>External program failed during initialization.
>Execution of this command stops.
Additional error message: spss.pth points to wrong plug-in version.

Will I need to uninstall Py 2.7 to get this to work? Or - how do I get SPSS to point to the 'right' plug-in?

Thanks in advance

Dan Bibel
Massachusetts State Police

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

[Jon K Peck]

V18 and V20 should not interfere with each other (unless you installed these in the same directory :-)).

I have both and can run programmability with either.

For V18, look at the files
spss.pth and SpssClient.pth that are located in c:\python26\lib\site-packages (or wherever you installed Python).
They should have as the first line
spss180

Check also the file spssdxcfg.ini in the directory where V18 is installed.  It should have a section looking like this.
[Python]
HOME=C:/Python26
EXECUTE_X=Execute_Python
STOP_EMBEDDED_X=End_Embedded_Python
SET_POST_SPSS_OUTPUT=PyPostSpssOutput
PRE_ACTION=from spss import preaction\tnpreaction.start()
POST_ACTION=from spss import postaction\tnpostaction.end()
LIB_NAME=statisticspython
INIT_EMBEDDED_X=Init_Embedded_Python

It should not matter, but if Python27 is on your DOS Path, remove it.

Run a basic test.
begin program.
import spss
print 'ok'
end program.

to get confirmation that programmability is installed correctly before worrying about SPLIT DATASET.

HTH,

Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
new phone: [phone]




From:        "Bibel, Daniel (POL)" <[hidden email]>
To:        [hidden email]
Date:        07/02/2012 10:16 AM
Subject:        [SPSSX-L]
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Appreciate any help:

I had a trial version of SPSS 20 installed; in addition I installed Python 2.7

The trial has expired, and I have fallen back to SPSS 18; which has Python 2.6 installed.

I am trying to run syntax with V18 and get the following:

SPSSINC SPLIT DATASET SPLITVAR=Agency
/OUTPUT DIRECTORY= "r:\ucrr\temp" DELETECONTENTS=YES
/OPTIONS NAMES=VALUES PRINTLIST=YES
FILELIST="results".

>Error # 6887.  Command name: BEGIN PROGRAM
>External program failed during initialization.
>Execution of this command stops.
Additional error message: spss.pth points to wrong plug-in version.

Will I need to uninstall Py 2.7 to get this to work? Or - how do I get SPSS to point to the 'right' plug-in?

Thanks in advance

Dan Bibel
Massachusetts State Police

=====================
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]

There are some differing meanings to the term "validating the data". 1&2 apply to all analyses.
1) validating the data entry process.
First assure that all of the metadata in the variables view is complete.
If you are dealing with raw data on paper, etc then either enter the data a second time and compare the entries or proofread all of the data.
Do things to assure that all variables only have legitimate values via  frequencies, descriptives, explore, etc.
Then look at bivariate oddities via crosstabs, MEANS, explore with breakdown factors, scatter plots, etc.
Use the GUI under "identify duplicate cases" and "identify unusual cases, paste that syntax then run it.

2)Validating your syntax for transformations. Review with your partners any transformations of the raw data are done correctly, recoding, scoring, etc.
Be sure that you can always go back and do the process over correctly.
Do the same kinds of checks on the transformed data as you did on the raw data.

3)After you have done that ask your instructor if the purpose of the exercise to evaluate the validity of  summative scales.
On 7/1/2012 9:36 PM, TheDuck wrote:

Ok, so I am a student and am learning SPSS. The lesson I am on now is
discussing validating the data. Well I have data put in and went to validate
as the book states to. However, under Data there is no Validation section.
Any clue why or where it is?

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Missing-Validation-Button-tp5713937.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

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