This post was updated on .
Hi everyone,
I'm able to convert/restructure an initial dataset (wide) to a long/stacked format using the SPSS syntax and everything works generally well. However, when there are missing values for one of the variables in the initial dataset, it seems like SPSS does not create any row (displaying a missing value) in the new (i.e., stacked) dataset. The wave is entirely omitted from the stacked dataset, which is problematic for subsequent analyses. I was wondering whether it would be possible for SPSS (using the VARSTOCASE syntax) to create empty/blank cells (i.e., SYSMIS) in the new dataset when there are missing values in the initial dataset ? Here's the syntax that I'm using: VARSTOCASES /MAKE fubpi FROM fubpi_3months fubpi_6months fubpi_9months fubpi_12months /INDEX = WAVE /KEEP = ID. Thanks in advance for your assistance. O. -- Sent from: http://spssx-discussion.1045642.n5.nabble.com/ ===================== To manage your subscription to SPSSX-L, send a message to LISTSERV@LISTSERV.UGA.EDU (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 |
Look at the Null=keep subcommand.
Gene Maguin -----Original Message----- From: SPSSX(r) Discussion <[hidden email]> On Behalf Of Oliver Sent: Wednesday, March 03, 2021 1:29 PM To: [hidden email] Subject: VARSTOCASES (Missing values in the initial dataset) Hi everyone, I'm able to convert/restructure an initial dataset (wide) to a long/stacked format using the SPSS syntax and everything works generally well. However, when there are missing values for one of the variables in the initial dataset, it seems like SPSS does not create any row (displaying a missing value) in the new (i.e., stacked) dataset. The wave is entirely omitted from the stacked dataset, which is problematic for subsequent analyses. I was wondering whether it would be possible for SPSS (using the VARSTOCASE syntax) to create empty/blank cells (i.e., SYSMIS) in the new dataset when there are missing values in the initial dataset ? Here's the syntax that I'm using: VARSTOCASES /MAKE fubpi FROM fubpi_3months fubpi_6months fubpi_9months fubpi_12months /INDEX = WAVE /KEEP = ID. Thanks in advance for your assistance. O. -- 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 ===================== 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 Oliver
untested
try adding /null = keep recode fubpi (symis= -99999) (else=copy). missing values fubpi (-99999). add value labels fubpi -99999 ' some words to explain'. or you could remove the missingness status, missing values fubpi_3months fubpi_6months fubpi_9months fubpi_12months () varstocases ... missing values fubpi ... value labels fubpi ... ----- 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 Maguin, Eugene
Thanks for your suggestion, Eugene. It worked very well. Thanks !
-- 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 Art Kendall
Thanks for your suggestion, Art. I tried a couple of strategies and it worked
very well. -- 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 |
Free forum by Nabble | Edit this page |