Data recoding for multiple binary variables
Locked
 
|
Hi
I have list of 200 variables Q1 to Q200 where data is in binary format. if answer is chosen its coded 1 if no than it is 0. I would like to convert chosen code (which is 1) in respective code (Variable name). how we can do it easily. Can we do it through vector or loop function? pls help. data is like q1 q2 q3 q4 q5 q6 1 1 1 1 1 1 and need to convert like q1 q2 q3 q4 q5 q6 1 2 3 4 5 6 Regards Sat -- 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 |
Re: Data recoding for multiple binary variables
|
|
VECTOR q=q1 TO q200.
LOOP #=1 TO 200. COMPUTE q(#)=#*q(#). END LOOP. ===================== 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 |
Re: Data recoding for multiple binary variables
Administrator
|
In reply to this post by Satish
David has posted a nice solution. But I am wondering why you want to do
this. What is it you are ultimately trying to achieve? There may be another way. Thanks for clarifying. Satish wrote > Hi > > I have list of 200 variables Q1 to Q200 where data is in binary format. if > answer is chosen its coded 1 if no than it is 0. > > I would like to convert chosen code (which is 1) in respective code > (Variable name). how we can do it easily. Can we do it through vector or > loop function? pls help. > > data is like > > q1 q2 q3 q4 q5 q6 > 1 1 1 1 1 1 > > > and need to convert like > > q1 q2 q3 q4 q5 q6 > 1 2 3 4 5 6 > > Regards > Sat > > > > > > -- > 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 ----- -- 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/). |
|
|
In reply to this post by Satish
I am wondering whether you actually have a multiple response set coded as a set of dichotomies. If so, you might, instead, define this set using the MRSETS command and analyze with CTABLES. On Sat, Jul 6, 2019 at 3:35 PM Satish <[hidden email]> wrote: Hi |
Re: Data recoding for multiple binary variables
|
|
Pushing Jon's question one step further... I am curious
about what sort of question or analysis /wants/ to have
the "1" responses in form of the question number.
When I see a string of answers that are "multiple responses"
that run, say, {1,2, 5, 9, ... 198} for the questions that were Yes,
I would either run mult-response or CTABLES. For other sorts
of analyses or presentations, I think I would have to /convert/
them to the string of 0/1 numbers that you already have.
For curiousity's sake - What presentation or analysis is helped
by what you want to do?
--
Rich Ulrich
From: SPSSX(r) Discussion <[hidden email]> on behalf of Jon Peck <[hidden email]>
Sent: Saturday, July 6, 2019 5:58 PM To: [hidden email] Subject: Re: Data recoding for multiple binary variables I am wondering whether you actually have a multiple response set coded as a set of dichotomies. If so, you might, instead, define this set using the MRSETS command and analyze with CTABLES.
On Sat, Jul 6, 2019 at 3:35 PM Satish <[hidden email]> wrote:
Hi |
|
|
In reply to this post by David Marso-2
Hi David
Thanks helping me. its working fine. Satish -- 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 |
|
|
This post was updated on .
In reply to this post by Rich Ulrich
Hi Rich Ulrich,
Yes, I am using CTABLES for running tables for these set of answer. Here is the main reason to recode all binary data in to unique code. I have a (Top of mind) question which is single response automobiles car name where we have list of 200 cars starting from 1 to 200. There is one more (spont awareness) question which is in binary (0,1) format and there are 200 separate variable for each brand. For getting consolidated data for TOM and SPONT i need to merge data of both question but it was not possible run tables without re coding binary data into UNIQUE CODE same as TOM. here is the the syntax for generating consolidate tables for TOM+SPONT >> TOM : Single Response question. CTABLES /VLABELS VARIABLES=Overall DISPLAY= DEFAULT /TABLE Q7[C] [COLPCT.COUNT "Column %"F40.0,TOTALS[COUNT"Wtd Base" F40.0,UCOUNT"Unwtd Base" F40.0 ]] BY Overall[C]+zone[C] /SLABELS POSITION=ROW /CATEGORIES VARIABLES=Q7 EMPTY=INCLUDE TOTAL=YES LABEL= "" POSITION= BEFORE /CATEGORIES VARIABLES=Overall EMPTY=INCLUDE TOTAL=No LABEL= "Overall" POSITION= BEFORE /TITLES TITLE="Top of mind (TOM)" >> SPONT : Multiple question. MRSETS /MDGROUP NAME =$Q7a LABEL ="" VARIABLES =Q7a_1 to Q7a_200 VALUE =1. CTABLES /VLABELS VARIABLES=Overall DISPLAY= DEFAULT /TABLE $Q7a[C] [COLPCT.COUNT "Column %"F40.0,TOTALS[COUNT"Wtd Base" F40.0,UCOUNT"Unwtd Base" F40.0 ]] BY Overall[C]+zone[C] /SLABELS POSITION=ROW /CATEGORIES VARIABLES=$Q7a EMPTY=INCLUDE TOTAL=YES LABEL= "" POSITION= BEFORE /CATEGORIES VARIABLES=Overall EMPTY=INCLUDE TOTAL=No LABEL= "Overall" POSITION= BEFORE /TITLES TITLE=" SPONT" > TOM+SPONT AFTER RE CODIG BINARY VARIABLES OF SPONT IN TO UNIQUE CODE. MRSETS /MCGROUP NAME =$Q7a LABEL ="" VARIABLES =Q7 Q7a_1 to Q7a_200 VALUE =1. CTABLES /VLABELS VARIABLES=Overall DISPLAY= DEFAULT /TABLE $Q7a[C] [COLPCT.COUNT "Column %"F40.0,TOTALS[COUNT"Wtd Base" F40.0,UCOUNT"Unwtd Base" F40.0 ]] BY Overall[C]+zone[C] /SLABELS POSITION=ROW /CATEGORIES VARIABLES=$Q7a EMPTY=INCLUDE TOTAL=YES LABEL= "" POSITION= BEFORE /CATEGORIES VARIABLES=Overall EMPTY=INCLUDE TOTAL=No LABEL= "Overall" POSITION= BEFORE /TITLES TITLE="TOM+SPONT" Please let me know if there is any shortcut method to generate consolidated tables for single response question and multiple response question in binary format. Satish -- 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 |
|
|
I guess your current problem is solved, but for future similar work, you might want to consider using a multiple category set instead of a multiple dichotomy set. Then, if you do need the multiple dichotomy form, you can use the STATS MCSET CONVERT extension command, available via Extensions > Extension Hub, to convert the MC set to an MD set. On Tue, Jul 9, 2019 at 12:02 PM Satish <[hidden email]> wrote: Hi Rich Ulrich, |
Re: Data recoding for multiple binary variables
|
Converting multiple dichotomous set (MRD) to multiple categorical
set (MRC) or back are also done by good old macros !MRDMRC and
!MRCMRD found in collection "Categorical-Binary recodings" on my
page
http://www.spsstools.net/en/KO-spssmacros 09.07.2019 22:04, Jon Peck пишет:
===================== 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 think it would be nice if these macros came with dialog box interfaces. The dialog could even include the macro definition so that that did not have to be loaded separately. On Tue, Jul 9, 2019 at 1:51 PM Kirill Orlov <[hidden email]> wrote:
|
«
Return to SPSSX Discussion
|
1 view|%1 views
| Free forum by Nabble | Edit this page |