Obtaining AIC and BIC for model selection- logistic regression

SIMMII — Sun, 03 Dec 2023 15:36:52 GMT

Hi,

I used this code to obtain the table with all possible models and their respective AIC/BIC:

proc logistic data=pred3_num;
class x5 x7 x8;
model I_y(ref='0') = x1 x2 x21 x22 x23 x24 x25 x26 x27 x28 x29 xx2 x3 x31 x4 x41 x42 x5-x8 x9 x91 x10 x11 x111 x112 x113 x114 x115 x116 x117 x118 x119 xx11 x12-x14 
x15 x151 x152 /
selection=score best=1;
run;
%MACRO logistic_aic_sbc_score(yvariable=I_y,xvariables=x1 x2 x21 x22 x23 x24 x25 x26 x27 x28 x29 xx2 x3 x31 x4 x41 x42 x5-x8 x9 x91 x10 x11 x111 x112 x113 x114 x115 x116 x117 x118 x119 xx11 x12-x14 
x15 x151 x152,dataset=pred3_num,minvar=1,maxvar=42);

But the log message here is giving me a few errors:

 OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 2          TITLE;
 NOTE: The quoted string currently being processed has become more than 262 bytes long.  You might have unbalanced quotation marks.
 3          FOOTNOTE;
 4          OPTIONS LOCALE=en_US DFLANG=LOCALE;
 5          DATA _NULL_;
 6          RUN;
 7          OPTIONS VALIDVARNAME=ANY;
 8          OPTIONS VALIDMEMNAME=EXTEND;
 74         &GRAPHTERM; ;*';*";*/;RUN;QUIT;
                          _________________
                          49
 NOTE 49-169: The meaning of an identifier after a quoted string might change in a future SAS release.  Inserting white space 
              between a quoted string and the succeeding identifier is recommended.
 
 9          FILENAME _HTMLOUT TEMP;
 10         FILENAME _GSFNAME TEMP;
 11         FILENAME _DATAOUT TEMP;
 12         %LET SYSCC=0;
 13         %LET _CLIENTAPP='SAS Studio';
 14         %LET _CLIENTAPPABREV=Studio;
 15         %LET _CLIENTAPPVERSION=3.81;
 16         %LET _CLIENTVERSION=3.81;
 NOTE: The quoted string currently being processed has become more than 262 bytes long.  You might have unbalanced quotation marks.
 17         %LET _CLIENTMODE=wip;
 18         %LET _SASSERVERNAME=%BQUOTE(SASApp);
 19         %LET _SASHOSTNAME=%BQUOTE(odaws02-usw2-2);
 20         %LET _SASPROGRAMFILEHOST=%BQUOTE(odaws02-usw2-2);
 21         %LET _CLIENTUSERID=%BQUOTE(u63584079);
 22         %LET _CLIENTUSERNAME=%BQUOTE(u63584079);
 23         %LET CLIENTMACHINE=%BQUOTE(MODEMCABLE061.63-179-173.MC.VIDEOTRON.CA);
 24         %LET _CLIENTMACHINE=%BQUOTE(MODEMCABLE061.63-179-173.MC.VIDEOTRON.CA);
 25         %let SASWORKLOCATION="%sysfunc(getoption(work))/";
 26         FILENAME _CWD '.'
                            _
                            49
 26       ! ;
 NOTE 49-169: The meaning of an identifier after a quoted string might change in a future SAS release.  Inserting white space 
              between a quoted string and the succeeding identifier is recommended.
 27         DATA _NULL_;
 28         CALL SYMPUT('_SASWORKINGDIR',PATHNAME('_CWD'));
                                       ____________
                                       49
 NOTE 49-169: The meaning of an identifier after a quoted string might change in a future SAS release.  Inserting white space 
              between a quoted string and the succeeding identifier is recommended.
 29         RUN;
 30         FILENAME _CWD;
 31         
 32         %LET _SASPROGRAMFILE = %NRQUOTE(%NRSTR(/home/u63584079/sasuser.v94/Ps2_draft.sas));
 NOTE: The quoted string currently being processed has become more than 262 bytes long.  You might have unbalanced quotation marks.
 33         %LET _BASEURL = %BQUOTE(https://odamid-usw2-2.oda.sas.com/SASStudio/);
 28         CALL SYMPUT('_SASWORKINGDIR',PATHNAME('_CWD'));
                                                       ____
                                                       49
 NOTE 49-169: The meaning of an identifier after a quoted string might change in a future SAS release.  Inserting white space 
              between a quoted string and the succeeding identifier is recommended.
 
 34         %LET _EXECENV=SASStudio;
 35         DATA _NULL_;
 36         CALL SYMPUT("GRAPHINIT","");
 37         CALL SYMPUT("GRAPHTERM","");
 38         RC=TSLVL('SASXGOPT','N');
 39         _ERROR_=0;
 40         IF (RC^=' ') THEN DO;
 41         CALL SYMPUT("GRAPHINIT","GOPTIONS RESET=ALL GSFNAME=_GSFNAME;");
 42         CALL SYMPUT("GRAPHTERM","GOPTIONS NOACCESSIBLE;");
 43         END;
 44         RUN;
 45         DATA _NULL_;
 46         RC=SYSPROD("PRODNUM002");
 47         IF (RC^=1) THEN DO;
 NOTE: The quoted string currently being processed has become more than 262 bytes long.  You might have unbalanced quotation marks.
 48         CALL SYMPUT("GRAPHINIT","");
 49         CALL SYMPUT("GRAPHTERM","");
 50         END;
 51         RUN;
 52         %LET _DATAOUT_MIME_TYPE=;
 53         %LET _DATAOUT_NAME=;
 54         %LET _DATAOUT_TABLE=;
 55         %LET _DATAOUT_URL=;
 56         %SYMDEL _DATAOUT_MIME_TYPE _DATAOUT_NAME _DATAOUT_URL _DATAOUT_TABLE;
 57         %LET _SASWS_ = %BQUOTE(/home/u63584079);
 40         IF (RC^=' ') THEN DO;
                      ___________
                      49
 NOTE 49-169: The meaning of an identifier after a quoted string might change in a future SAS release.  Inserting white space 
              between a quoted string and the succeeding identifier is recommended.
 
 58         %LET _SASWSTEMP_=%BQUOTE(/home/u63584079/.sasstudio/.images/6857b072-c60b-4db4-9863-5f24234a4f61);
 59         ODS LISTING CLOSE;
 60         ODS AUTONAVIGATE OFF;
 61         ODS GRAPHICS ON;
 62         ODS HTML5 (ID=WEB) DEVICE=PNG GPATH="&_SASWSTEMP_" ENCODING=utf8  FILE=_HTMLOUT (TITLE='Results:
 62       ! Ps2_draft.sas') STYLE=Htmlblue OPTIONS(BITMAP_MODE='INLINE' OUTLINE='ON' SVG_MODE='INLINE'
                         _______________________________________      ___________  ____________
                         49                                           49           49
 62       ! CSS_PREFIX='.ods_6857b072-c60b-4db4-9863-5f24234a4f61' BODY_ID='div_6857b072-c60b-4db4-9863-5f24234a4f61' );
 NOTE 49-169: The meaning of an identifier after a quoted string might change in a future SAS release.  Inserting white space 
              between a quoted string and the succeeding identifier is recommended.
 63         &GRAPHINIT;
 64         OPTIONS FIRSTOBS=1;
 65         OPTIONS OBS=MAX;
 66         OPTIONS DTRESET DATE NUMBER NOTES;
 67         OPTIONS NOTES STIMER SOURCE NOSYNTAXCHECK;
 68         
 69         proc logistic data=pred3_num;
 70         class x5 x7 x8;
 71         model I_y(ref='0') = x1 x2 x21 x22 x23 x24 x25 x26 x27 x28 x29 xx2 x3 x31 x4 x41 x42 x5-x8 x9 x91 x10 x11 x111 x112 x113
 71       ! x114 x115 x116 x117 x118 x119 xx11 x12-x14
 49: LINE and COLUMN cannot be determined.
 NOTE: NOSPOOL is on. Rerunning with OPTION SPOOL might allow recovery of the LINE and COLUMN where the error has occurred.
 NOTE 49-169: The meaning of an identifier after a quoted string might change in a future SAS release.  Inserting white space 
              between a quoted string and the succeeding identifier is recommended.
 NOTE: The quoted string currently being processed has become more than 262 bytes long.  You might have unbalanced quotation marks.
 72         x15 x151 x152 /
 73         selection=score best=1;
 74         run;
 75         %MACRO logistic_aic_sbc_score(yvariable=I_y,xvariables=x1 x2 x21 x22 x23 x24 x25 x26 x27 x28 x29 xx2 x3 x31 x4 x41 x42
 75       ! x5-x8 x9 x91 x10 x11 x111 x112 x113 x114 x115 x116 x117 x118 x119 xx11 x12-x14
 76         x15 x151 x152,dataset=pred3_num,minvar=1,maxvar=42);
 77         
 78         OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 79         ODS HTML CLOSE;
 80         &GRAPHTERM; ;*';*";*/;RUN;QUIT;
 81         QUIT;RUN;
 82         ODS HTML5 (ID=WEB) CLOSE;
 83         
 84         FILENAME _GSFNAME;
 85         DATA _NULL_;
 86         RUN;
 87         OPTIONS NOTES STIMER SOURCE SYNTAXCHECK;
 88         
 User: u63584079

And the output was only giving me a table with chi-squares as metrics of selection

How can I fix this?

Re: Obtaining AIC and BIC for model selection- logistic regression

SteveDenham — Thu, 07 Dec 2023 18:54:19 GMT

Save your code and data. then restart SAS, or disconnect and reconnect SAS Studio. At some point, it looks like you have an unmatched single or double quote.

From what you posted, it also looks to me like you called a macro named logistic_aic_sbc_score. The unbalanced quote may be in that macro..

SteveDenham

topic Obtaining AIC and BIC for model selection- logistic regression in Statistical Procedures

Obtaining AIC and BIC for model selection- logistic regression

Re: Obtaining AIC and BIC for model selection- logistic regression