advice on a custom table
Locked
 
|
Dear List,
I recently learned (from this list) that CTABLES does not produce a cumulative percent column. Which is an issue because that _was_ my best bet for producing a large number (~200) frequency tables. Perhaps the collective wisdom of this list can help.
Here is an example of what I need:
Count Perc of total Cum perc of total
SA 4 40% 40%
A 3 30% 70%
D 2 20% 90%
DA 1 10% 100%
Total 10 100%
Any assistance is greatly appreciated!
Thank you!
John
|
|
|
Do you want FREQUENCIES output minus the Valid Percent column? From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of J P Dear List, I recently learned (from this list) that CTABLES does not produce a cumulative percent column. Which is an issue because that _was_ my best bet for producing a large number (~200) frequency tables. Perhaps the collective wisdom of this list can help. Here is an example of what I need: Count Perc of total Cum perc of total SA 4 40% 40% A 3 30% 70% D 2 20% 90% DA 1 10% 100% Total 10 100% Any assistance is greatly appreciated! Thank you! John |
|
|
Yes, plus the cumulative percent reversed.
From: ViAnn Beadle <[hidden email]> To: [hidden email] Sent: Thu, December 17, 2009 4:22:22 PM Subject: Re: advice on a custom table Do you want FREQUENCIES output minus the Valid Percent column?
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of J P
Dear List,
I recently learned (from this list) that CTABLES does not produce a cumulative percent column. Which is an issue because that _was_ my best bet for producing a large number (~200) frequency tables. Perhaps the collective wisdom of this list can help.
Here is an example of what I need:
Count Perc of total Cum perc of total SA 4 40% 40% A 3 30% 70% D 2 20% 90% DA 1 10% 100% Total 10 100%
Any assistance is greatly appreciated!
Thank you!
John
|
|
|
1. What keeps you from using FREQUENCIES? 2. If you do need to use CTABLES, a tiny custom function used with the SPSSINC MODIFY TABLES extension command could easily convert a column into a cumulative percent column. Jon Peck SPSS, an IBM Company [hidden email] 312-651-3435
Yes, plus the cumulative percent reversed. From: ViAnn Beadle <[hidden email]> To: [hidden email] Sent: Thu, December 17, 2009 4:22:22 PM Subject: Re: advice on a custom table Do you want FREQUENCIES output minus the Valid Percent column?
|
|
|
Jon,
Please read between the lines when I say it's not my decision regarding frequencies.
Can you tell me more about the modify tables extension?
Thank you,
John
From: Jon K Peck <[hidden email]> To: [hidden email] Sent: Thu, December 17, 2009 4:43:14 PM Subject: Re: advice on a custom table 1. What keeps you from using FREQUENCIES? 2. If you do need to use CTABLES, a tiny custom function used with the SPSSINC MODIFY TABLES extension command could easily convert a column into a cumulative percent column. Jon Peck SPSS, an IBM Company [hidden email] 312-651-3435
Yes, plus the cumulative percent reversed. From: ViAnn Beadle <[hidden email]> To: [hidden email] Sent: Thu, December 17, 2009 4:22:22 PM Subject: Re: advice on a custom table Do you want FREQUENCIES output minus the Valid Percent column?
|
|
|
What release of SPSS Statistics are you
running? It might be possible to produce your desired table with Release
18. Custom Tables has a couple of enhancements, including the capability
to include expressions involving cell statistics.
Cumulative percents would be computed by computing rolling sums of
the column percents. From: SPSSX(r)
Discussion [mailto:[hidden email]] On
Behalf Of J P Jon, Please read between the lines when I say it's not my decision
regarding frequencies. Can you tell me more about the modify tables extension? Thank you, John
No virus found in this incoming message. |
|
|
The post-compute feature in CTABLES V18 is very useful, but to get the cumulative sums at each value you would have to insert a post compute for every cell, and you would have to know all the categories in advance. That is, the syntax would have to specify a computation for each category value. That would mean a PCOMPUTE subcommand and a PPROPERTIES subcommand for each category and listing all those PCOMPUTEs in the CATEGORIES subcommand. Could be done, but you would probably want a program to generate the syntax, perhaps from the variable value labels or by discovering the values on a data pass. Jon Peck SPSS, an IBM Company [hidden email] 312-651-3435
What release of SPSS Statistics are you running? It might be possible to produce your desired table with Release 18. Custom Tables has a couple of enhancements, including the capability to include expressions involving cell statistics. Cumulative percents would be computed by computing rolling sums of the column percents. Tony Babinec From: SPSSX(r) Discussion [[hidden email]] On Behalf Of J P Sent: Friday, December 18, 2009 7:22 AM To: [hidden email] Subject: Re: advice on a custom table Jon, Please read between the lines when I say it's not my decision regarding frequencies. Can you tell me more about the modify tables extension? Thank you, John No virus found in this incoming message.
|
| Free forum by Nabble | Edit this page |