SPSS CTABLE syntax
Locked
 
|
Hi,
I need some help in generating a table in the format as I have mentioned below. This should be done using the CTABLES synatx. The variable that is specified in a table is a Nominal variable (i.e. Number of chocolates consumed in a day). At the same time, I do also have some scale variables for which I need to generate a table (similar format) and also provide statistics. However I tried to do some R&D on the Scale variables but to my surprise I could only generate the statistics but not a table (util I convert it to a nominal variable). <http://spssx-discussion.1045642.n5.nabble.com/file/t340698/Table.png> Can any one help with the CTABLE syntax for generating a table in the above manner. Thanks for your help in advance. Regards, Jagadish -- Sent from: http://spssx-discussion.1045642.n5.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 |
|
|
I'm sorry, but as far as I can see, the "statistics" you generate
on that table are not sensible to look at.
Fifteen people used the response category, 1-5; that would be
the modal number of responses. But your Statistic, Mode, is
"4" because there were two categories that had 4 respondents.
Does anyone ever care about that?
Statistics typically reveal something about the respondents, not
about the number and choice of categories on the scale.
Are you sure that that is what you want?
--
Rich Ulrich
From: SPSSX(r) Discussion <[hidden email]> on behalf of jagadishpchary <[hidden email]>
Sent: Saturday, September 28, 2019 7:40 AM To: [hidden email] <[hidden email]> Subject: SPSS CTABLE syntax Hi,
I need some help in generating a table in the format as I have mentioned below. This should be done using the CTABLES synatx. The variable that is specified in a table is a Nominal variable (i.e. Number of chocolates consumed in a day). At the same time, I do also have some scale variables for which I need to generate a table (similar format) and also provide statistics. However I tried to do some R&D on the Scale variables but to my surprise I could only generate the statistics but not a table (util I convert it to a nominal variable). <http://spssx-discussion.1045642.n5.nabble.com/file/t340698/Table.png> Can any one help with the CTABLE syntax for generating a table in the above manner. Thanks for your help in advance. Regards, Jagadish -- Sent from: http://spssx-discussion.1045642.n5.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 |
|
|
In reply to this post by jagadishpchary
That table is unadulturated silliness. Meaningless is too kind. OP needs to formulate a meaningful question.
===================== 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 |
|
|
In reply to this post by Rich Ulrich
Hi Rich,
Thanks for the reply. The values in the table are just for illustration purpose only. Those are not the actual figures. I am only trying to explain that I need the Table in the given format for both Scale and categorical variables. Hope it is clear now. Regards, Jagadish -- Sent from: http://spssx-discussion.1045642.n5.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 |
|
In reply to this post by jagadishpchary
Even if the number of chocolates is coarsened into categories it could still
be at least ordinal. Please cut-and paste the data definition for the variables you are interested into a post. Then post what questions you are trying to answer. Are you really having many people eating that many chocolates in a day!?! ----- Art Kendall Social Research Consultants -- Sent from: http://spssx-discussion.1045642.n5.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
Art Kendall
Social Research Consultants |
|
|
In reply to this post by jagadishpchary
There is nothing wrong with the table you are after (other than the useless total column) assuming that the chocolate variable is really scale, which seems reasonable. It's just a frequency table with some other summary statistics. Those would mostly not be valid if the data are categorical. To get this table using the Analyze > Tables > Custom Tables canvas do this. The variable is named choc. I am assuming that the variable is set to a scale measurement level. - right click on choc and choose ordinal for the measure. (CTABLES does not distinguish between nominal and ordinal). - drag choc to the row area of the canvas - right click again on choc (it's still in the source list) and choose scale - drag it again to the canvas below the categorical choc - click on Summary Statistics and pick all the statistics you want. - on the canvas, set Position in the Summary Statistics group at the bottom to Rows. - click ok The generated syntax would be like this. CTABLES /TABLE choc [C][COUNT] + choc [MEAN, MEDIAN, MODE, STDDEV, MINIMUM, MAXIMUM, SEMEAN] /SLABELS POSITION=ROW. Top box and bottom box is a little trickier, but you can get it by selecting the categorical choc, going to Categories and Totals, and using Add Category. However, to do that, you need to have value labels for choc. Or do this with RECODE INTO On Sat, Sep 28, 2019 at 4:35 PM jagadishpchary <[hidden email]> wrote: Hi, |
|
|
Hi John,
This is what I was looking for the syntax. Thanks. Could you also let me know how the T2B & B2B should be computed in Ctables for a rating Kind of Questions. Regards, Jagadish -- Sent from: http://spssx-discussion.1045642.n5.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 |
|
|
Unfortunately, the solution I had in mind does not work with this table due to its internal structure. To get, say, top box, you would have to run the table and then specify the top two categories in the CTABLES syntax and run it again. You could use the STATS CATEGORY EXTENSION command, which can be installed from the Extensions > Extension Hub menu to define the category order (value labels not necessary), and then run the CTABLES command like this, where the top box categories are 20.0 and 22.0 in my dataset. STATS CATEGORY ORDER ITEMS=choc PREFIX=order OTHER=NO /OPTIONS ORDER=D CATEGORYLABELS=VARLABELS. CTABLES /pcompute &top = expr([20.0]+ [22.0]) /pproperties &top label = "top box" /TABLE choc [C][COUNT] + choc [MEAN, MEDIAN, MODE, STDDEV, MINIMUM, MAXIMUM, SEMEAN] /SLABELS POSITION=ROW /catgories variable= choc [!order_choc &top]. On Sun, Sep 29, 2019 at 10:50 PM jagadishpchary <[hidden email]> wrote: Hi John, |
«
Return to SPSSX Discussion
|
1 view|%1 views
| Free forum by Nabble | Edit this page |