pspp-users
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: PSPP Help


From: Alan Mead
Subject: Re: PSPP Help
Date: Mon, 11 Jan 2016 12:03:57 -0600
User-agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:38.0) Gecko/20100101 Thunderbird/38.5.0

Ed,

I think the crosstabs issue came up previously and I don't think it's possible.  I would suggest that you log a bug for each of these with a clear description of what you expect and what doesn't work. Including your syntax and a tiny sample dataset would also help.

http://savannah.gnu.org/bugs/?func=additem&group=pspp

About compute and dummy coding, that's also not available through the PSPP GUI but I have never found the SPSS GUI particularly easy... Wouldn't it be easier to just write a snippet of code to do this? BTW, I use recode statements:

recode d5_sex (1=1) (SYSMIS=COPY) (ELSE=0) into d5_sex_males.
execute.

If you had multiple values, recode is a lot easier:

* assume segment is 1-5 and 1 is the "baseline" group.
recode d6_segment (2=1) (SYSMIS=COPY) (ELSE=0) into d6_segment_2.
recode d6_segment (3=1) (SYSMIS=COPY) (ELSE=0) into d6_segment_3.
recode d6_segment (4=1) (SYSMIS=COPY) (ELSE=0) into d6_segment_4.
recode d6_segment (5=1) (SYSMIS=COPY) (ELSE=0) into d6_segment_5.
execute.

And finally, I don't know anything about the last question. PSPP had syntax before it had a GUI, so if it's not supported by syntax, I doubt it's supported by the GUI.  I think a couple SPSS routines (e.g., FREQ) have some (syntax) options about how to list variables, and those are likely to work similarly in PSPP.  SPSS also buries similar features in a context menu in the output window but PSPP wouldn't have anything like that at this time.

-Alan

On 1/10/2016 8:49 PM, Ed Nelson wrote:

I'm a new user of PSPP.  I have used SPSS for a long time but just started using PSPP a couple of months ago and I have several questions and would appreciate someone's help.
  • Crosstabs -- I don't see how to run a three-variable crosstab from the graphical interface.  It appears that it only runs two-variable tables.  However, when I use my SPSS syntax file it will read the file and create a three-variable table. 
    Here's an example of the SPSS syntax.
    CROSSTABS
      /TABLES=g2_owngun BY d5_sex BY d11_class
      /FORMAT=AVALUE TABLES
      /CELLS=COUNT COLUMN.
    Is there a way to do this from the interface?
  • Select cases -- I want to create a dummy variable for use with regression.  In SPSS I would use the Compute command to set a variable equal to 0.  Then I would use the select cases command to change that variable to 1 if the person was male.  I would click on select cases and then then on the If button and then tell SPSS to change the value to 1 if the person was male.  Here's an example of the SPSS syntax.
    COMPUTE d5_sex_males=0.
    IF  (d5_sex = 1) d5_sex_males=1.
    That would give me the dummy variable.  But I can't see how to do this from the interface in PSPP.  lt will however run the SPSS syntax file and do it correctly.  I'm writing exercises for my students and don't want to have to show them syntax.  I want to be able to do it from the interface.  Is that possible?

  • In SPSS you can click on Edit and then on Options and tell SPSS to show the variable names alphabetically.  In PSPP it shows the variable labels instead of the variable names.  Is there any way to get it to show the variable names in the interface?
Thank you for all help you might be able to give me.

  Ed

--
Ed Nelson
Professor Emeritus of Sociology
CSU Fresno
559-978-9391
address@hidden


_______________________________________________
Pspp-users mailing list
address@hidden
https://lists.gnu.org/mailman/listinfo/pspp-users

-- 

Alan D. Mead, Ph.D.
President, Talent Algorithms Inc.

science + technology = better workers

+815.588.3846 (Office)
+267.334.4143 (Mobile)

http://www.alanmead.org

Announcing the Journal of Computerized Adaptive Testing (JCAT), a
peer-reviewed electronic journal designed to advance the science and
practice of computerized adaptive testing: http://www.iacat.org/jcat

reply via email to

[Prev in Thread] Current Thread [Next in Thread]