Simplifying SPSS output when working with Pooled Datasets
Locked
Simplifying SPSS output when working with Pooled Datasets
 
|
Hi
I am working on a multiple imputation dataset in SPSS v25, and have been using the ‘Data>Split File > Compare Groups’ process to analyse my data. I am really only interested in the output relating to the pooled results, but because I created 20 blocks of imputations, I have to scroll through a lot of irrelevant output whenever I analyse my data. While I realise this is not a major issue, it can lead to some confusion when trying to identify the results I am actually interested in, so I am looking for a method of simplifying my output. Does anybody know a method (or syntax) which can be used to only show analysis relating to pooled results, instead of providing details relating to each individual imputation block. Thanks in advance, Michael -- 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 |
|
|
You can use OMS to suppress objects of particular types from the Viewer. If the individual results are in separate tables from the pooled ones (depends on the procedure), find the table types and tell OMS to suppress them before running the pooled analysis. To find the table types, right click on each undesired table and choose Copy OMS table subtype. Paste all these somewhere. Suppose the types are A, B, and C. Run this OMS SELECT TABLES /IF SUBTYPES=["A" "B" "C"] /DESTINATION VIEWER=NO. Then run your analyses. To turn off OMS filtering, run OMSEND. On Mon, Dec 10, 2018 at 10:12 AM MConnolly123 <[hidden email]> wrote: Hi |
Re: Simplifying SPSS output when working with Pooled Datasets
Administrator
|
If the results for each imputed data set and the pooled estimates are in the
SAME table, you could still use OMS to write that table to a new dataset. Then activate the dataset and delete (or filter out) the unwanted rows, and use SUMMARIZE to generate a table if one is needed. HTH. Jon Peck wrote > You can use OMS to suppress objects of particular types from the Viewer. > If the individual results are in separate tables from the pooled ones > (depends on the procedure), find the table types and tell OMS to suppress > them before running the pooled analysis. > > To find the table types, right click on each undesired table and choose > Copy OMS table subtype. Paste all these somewhere. Suppose the types are > A, B, and C. Run this > OMS SELECT TABLES /IF SUBTYPES=["A" "B" "C"] /DESTINATION VIEWER=NO. > Then run your analyses. > To turn off OMS filtering, run > OMSEND. > > On Mon, Dec 10, 2018 at 10:12 AM MConnolly123 < > m.g.connolly1@ > > > wrote: > >> Hi >> >> I am working on a multiple imputation dataset in SPSS v25, and have been >> using the ‘Data>Split File > Compare Groups’ process to analyse my data. >> I >> am really only interested in the output relating to the pooled results, >> but >> because I created 20 blocks of imputations, I have to scroll through a >> lot >> of irrelevant output whenever I analyse my data. While I realise this is >> not >> a major issue, it can lead to some confusion when trying to identify the >> results I am actually interested in, so I am looking for a method of >> simplifying my output. >> >> Does anybody know a method (or syntax) which can be used to only show >> analysis relating to pooled results, instead of providing details >> relating >> to each individual imputation block. >> >> Thanks in advance, >> >> Michael >> >> >> >> >> -- >> Sent from: http://spssx-discussion.1045642.n5.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 >> > > > -- > Jon K Peck > jkpeck@ > > ===================== > 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. -- 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
--
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/). |
Re: Simplifying SPSS output when working with Pooled Datasets
|
|
Hi Jon,
Thank you very much taking the time to respond and for your helpful response. As you suggested in your second post, the results are all reported as one table, therefore I think I will need to take the second approach you have recommended. I am unfamiliar with the process of writing a table to a new dataset, could you point me in the direction of any guidance that would help me do this? I have searched myself for this, and haven't been able to find anything on this matter, or much at all on OMS in general. Thanks again. -- 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 |
|
|
For tables where the pooled results are in the table along with the results from each imputed dataset, you can use the SPSSINC MODIFY TABLES extension command to hide all but the pooled rows. You specify the table subtype and use one of the custom functions installed with this command. For example, for Descriptives, you could write SPSSINC MODIFY TABLES subtype="'Descriptive Statistics'" SELECT="<<ALL>>" DIMENSION= ROWS LEVEL = -1 PROCESS = PRECEDING /STYLES APPLYTO=LABELS CUSTOMFUNCTION="customstylefunctions.hideNonfinalRows". For regression, it would be SPSSINC MODIFY TABLES subtype="Coefficients" SELECT="<<ALL>>" DIMENSION= ROWS LEVEL = -1 PROCESS = PRECEDING /STYLES APPLYTO=LABELS CUSTOMFUNCTION="customstylefunctions.hideNonfinalRows". Find the table type as described in an earlier message. The command would be the same for any table except for the subtype specification. If this command is not already installed, you can install it from the Extensions > Extension Hub menu. On Tue, Dec 11, 2018 at 4:36 AM MConnolly123 <[hidden email]> wrote: Hi Jon, |
|
|
p.s. If you have a bunch of outputs, you can apply MODIFY TABLES to all of them by specifying PROCESS=ALL instead of PROCESS=PRECEDING. On Tue, Dec 11, 2018 at 7:42 AM Jon Peck <[hidden email]> wrote:
|
«
Return to SPSSX Discussion
|
1 view|%1 views
| Free forum by Nabble | Edit this page |