RE.: Bad GPL on SPSS v23 x64
Locked
 
|
Hi folks, RE.: Bad GPL on SPSS v23 x64 Please check following Case Studies example and see why resulting chart created by Chart Builder is different than one built by Legacy Scatter Plot: GET FILE='..\Statistics\SPSS\SPSS 23\Samples\English\recidivism.sav'. DATASET NAME DataSet4 WINDOW=FRONT. COXREG time /STATUS=arrest2(1) /METHOD=ENTER age /SAVE=PRESID /CRITERIA=PIN(.05) POUT(.10) ITERATE(20). Bad Chart: * Chart Builder. GGRAPH /GRAPHDATASET NAME="graphdataset" VARIABLES=time PR1_1 MISSING=LISTWISE REPORTMISSING=NO /GRAPHSPEC SOURCE=INLINE. BEGIN GPL SOURCE: s=userSource(id("graphdataset")) DATA: time=col(source(s), name("time")) DATA: PR1_1=col(source(s), name("PR1_1"), unit.category()) GUIDE: axis(dim(1), label("Time to second arrest")) GUIDE: axis(dim(2), label("Partial residual for Age in years")) ELEMENT: point(position(time*PR1_1)) END GPL. Good Chart: GRAPH /SCATTERPLOT(BIVAR)=time WITH PR1_1 /MISSING=LISTWISE. Max. |
|
|
PR1_1 has a categorical measurement level,
so the Chart Builder adds a unit.category() call to the GPL. If
you remove the unit.category() call for PR_1 or change the measurement
level before using the Chart Builder, you get the same chart.
Jon Peck (no "h") aka Kim Senior Software Engineer, IBM [hidden email] phone: 720-342-5621 From: MaxJasper <[hidden email]> To: [hidden email] Date: 07/04/2015 02:46 PM Subject: [SPSSX-L] RE.: Bad GPL on SPSS v23 x64 Sent by: "SPSSX(r) Discussion" <[hidden email]> Hi folks, RE.: Bad GPL on SPSS v23 x64 Please check following Case Studies example and see why resulting chart created by Chart Builder is different than one built by Legacy Scatter Plot: GET FILE='..\Statistics\SPSS\SPSS 23\Samples\English\recidivism.sav'. DATASET NAME DataSet4 WINDOW=FRONT. COXREG time /STATUS=arrest2(1) /METHOD=ENTER age /SAVE=PRESID /CRITERIA=PIN(.05) POUT(.10) ITERATE(20). Bad Chart: * Chart Builder. GGRAPH /GRAPHDATASET NAME="graphdataset" VARIABLES=time PR1_1 MISSING=LISTWISE REPORTMISSING=NO /GRAPHSPEC SOURCE=INLINE. BEGIN GPL SOURCE: s=userSource(id("graphdataset")) DATA: time=col(source(s), name("time")) DATA: PR1_1=col(source(s), name("PR1_1"), unit.category()) GUIDE: axis(dim(1), label("Time to second arrest")) GUIDE: axis(dim(2), label("Partial residual for Age in years")) ELEMENT: point(position(time*PR1_1)) END GPL. Good Chart: GRAPH /SCATTERPLOT(BIVAR)=time WITH PR1_1 /MISSING=LISTWISE. Max. ===================== To manage your subscription to SPSSX-L, send a message to LISTSERV@... (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 |
|
Hi Jon, Based on your info, if we follow this Case Study example as indicated step by step in SPSS v23 package we do not get the resulting chart included in that example simply because it has no explanation of removing unit.category() from Chart Builder. Max. From: Jon K Peck [via SPSSX Discussion] [mailto:[hidden email]] PR1_1 has a categorical measurement level, so the Chart Builder adds a unit.category() call to the GPL. If you remove the unit.category() call for PR_1 or change the measurement level before using the Chart Builder, you get the same chart.
===================== 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 If you reply to this email, your message will be added to the discussion below: http://spssx-discussion.1045642.n5.nabble.com/RE-Bad-GPL-on-SPSS-v23-x64-tp5730051p5730052.html To start a new topic under SPSSX Discussion, email [hidden email] |
|
In reply to this post by Jon K Peck
Why does the COXREG procedure save output variables (format F8.5) as categorical (with NOMINAL and not SCALE level)?
BTW, I run COXREG and happened to misspell PRESID as RESID and did get the Residuals saved. An option not available in the dialog, nor stated in the Command Syntax Reference, other than that COXREG creates these 8 temporary variables. COXREG time /STATUS=arrest2(1) /METHOD=ENTER age /SAVE=SURVIVAL SE HAZARD RESID LML DFBETA PRESID XBETA /PRINT=CI(95) /CRITERIA=PIN(.05) POUT(.10) ITERATE(20). Maybe more interesting than useful... /PRogman
|
Administrator
|
@PRogman:
Consider opening a new thread. Your question has nothing to do with 'Bad GPL on SPSS v23 x64'
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me. --- "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis." Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?" |
|
|
In reply to this post by PRogman
I see that all the SAVE variables get a
nominal measurement level assigned, which does not make sense. I'll
file a bug on that. As for residuals, the CSR says
HAZARD. Cumulative hazard function evaluated at the current case. Alias RESID. Jon Peck (no "h") aka Kim Senior Software Engineer, IBM [hidden email] phone: 720-342-5621 From: PRogman <[hidden email]> To: [hidden email] Date: 07/05/2015 08:50 AM Subject: Re: [SPSSX-L] RE.: Bad GPL on SPSS v23 x64 Sent by: "SPSSX(r) Discussion" <[hidden email]> Why does the COXREG procedure save output variables (format F8.5) as categorical (with NOMINAL and not SCALE level)? BTW, I run COXREG and happened to misspell PRESID as RESID and did get the Residuals saved. An option not available in the dialog, nor stated in the Command Syntax Reference, other than that COXREG creates these 8 temporary variables. COXREG time /STATUS=arrest2(1) /METHOD=ENTER age /SAVE=SURVIVAL SE HAZARD RESID LML DFBETA PRESID XBETA /PRINT=CI(95) /CRITERIA=PIN(.05) POUT(.10) ITERATE(20). Maybe more interesting than useful... /PRogman Jon K Peck wrote > PR1_1 has a categorical measurement level, so the Chart Builder adds a > unit.category() call to the GPL. If you remove the unit.category() call > for PR_1 or change the measurement level before using the Chart Builder, > you get the same chart. > > > Jon Peck (no "h") aka Kim > Senior Software Engineer, IBM > peck@.ibm > phone: 720-342-5621 > > ... -- View this message in context: http://spssx-discussion.1045642.n5.nabble.com/RE-Bad-GPL-on-SPSS-v23-x64-tp5730051p5730059.html Sent from the SPSSX Discussion mailing list archive at 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 |
| Free forum by Nabble | Edit this page |