Log: mathlogreg2.sas

 
 1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 NOTE: ODS statements in the SAS Studio environment may disable some output features.
 62         
 63         /* mathlogreg2.sas */
 64         %include '/folders/myfolders/441s18/Lecture/mathread1.sas';
 NOTE: Format YNFMT is already on the library WORK.FORMATS.
 NOTE: Format YNFMT has been output.
 NOTE: Format CRSFMT is already on the library WORK.FORMATS.
 NOTE: Format CRSFMT has been output.
 NOTE: Format NFMT is already on the library WORK.FORMATS.
 NOTE: Format NFMT has been output.
 
 NOTE: PROCEDURE FORMAT used (Total process time):
       real time           0.00 seconds
       cpu time            0.00 seconds
       
 
 178        title2 'Predict Passing the course (Y-N) with Logistic Regression';
 179        
 180        /* We know course is useful:
 181            c1 = 'Catch-up' c2 = 'Mainstream' c3 = 'Elite' */
 182        
 
 NOTE: The infile '/folders/myfolders/441s18/Lecture/exploremath.data.txt' is:
       Filename=/folders/myfolders/441s18/Lecture/exploremath.data.txt,
       Owner Name=root,Group Name=vboxsf,
       Access Permission=-rwxrwx---,
       Last Modified=18Jan2016:17:34:49,
       File Size (bytes)=44583
 
 NOTE: 579 records were read from the infile '/folders/myfolders/441s18/Lecture/exploremath.data.txt'.
       The minimum record length was 75.
       The maximum record length was 75.
 NOTE: Missing values were generated as a result of performing an operation on missing values.
       Each place is given by: (Number of times) at (Line):(Column).
       99 at 101:24   99 at 102:18   
 NOTE: The data set WORK.MATHEX has 579 observations and 25 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.01 seconds
       cpu time            0.00 seconds
       
 183        proc logistic data = mathex;
 
 184             title3 'Course and HS variables';
 185             model passed (event='Yes') = c1 c3 hsgpa hscalc hsengl;
 186             course: test c1=c3=0;
 187        run;
 
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied.
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.12 seconds
       cpu time            0.12 seconds
       
 
 188        
 189        
 190        /* Decision: Drop course */
 191        
 192        
 193        ods select ParameterEstimates; /* Limit the output */
 194        proc logistic data = mathex;
 195             title3 'Just HS variables';
 196             model passed (event='Yes') = hsgpa hscalc hsengl;
 197        run;
 
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied.
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.03 seconds
       cpu time            0.04 seconds
       
 
 198        
 199        
 200        /* Decision: Drop HS English.
 201           Does the diagnostic test add anything? */
 202        
 203        
 204        ods select ParameterEstimates;
 205        proc logistic data = mathex;
 206             title3 'HS GPA, HS Calculus and Diagnostic Test';
 207             model passed (event='Yes') = hsgpa hscalc calc precalc;
 208        run;
 
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied.
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.04 seconds
       cpu time            0.03 seconds
       
 
 209        
 210        
 211        /* Decision: Drop the calc subscale, but which is better,
 212           precalc or total score? */
 213        
 214        
 215        ods select ParameterEstimates TestStmts; /* I ran a trace to find out the name */
 216        proc logistic data = mathex;
 217             title3 'HS GPA, HS Calculus and Diagnostic Test';
 218             model passed (event='Yes') = hsgpa hscalc precalc totscore;
 219             precalc_n_totscore: test precalc = totscore = 0;
 220        run;
 
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied.
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.04 seconds
       cpu time            0.03 seconds
       
 
 221        
 222        
 223        /* Decision: Keep precalc rather than totscore. Confirm */
 224        
 225        
 226        ods select ParameterEstimates;
 227        proc logistic data = mathex;
 228             title3 'HS GPA, HS Calculus and Pre-calculus test';
 229             model passed (event='Yes') = hsgpa hscalc precalc;
 230        run;
 
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied.
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.04 seconds
       cpu time            0.03 seconds
       
 
 231        
 232        proc logistic data = mathex;
 233             title3 'Try gender, ethnic and mother tongue controlling for good stuff';
 234             class ethnic (param=ref ref='East Indian');
 235                  /* Specifying a reference category that's not the last value */
 236             model passed (event='Yes') = hsgpa hscalc precalc ethnic gender mtongue;
 237             contrast 'Demographics'      ethnic  1 0 0 0 0,
 238                                          ethnic  0 1 0 0 0,
 239                                          ethnic  0 0 1 0 0,
 240                                          ethnic  0 0 0 1 0,
 241                                          ethnic  0 0 0 0 1,
 242                                          gender  1,
 243                                          mtongue 1 / e;
 244                                                     /* Display the effect matrix */
 245        run;
 
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied.
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.17 seconds
       cpu time            0.15 seconds
       
 
 246        
 247        
 248        /* Decision: Forget about ethnicity. */
 249        
 250        
 251        ods select ParameterEstimates;
 252        proc logistic data = mathex;
 253             title3 'HS GPA, HS Calculus, Pre-calculus test, Gender and Mother tongue';
 254             model passed (event='Yes') = hsgpa hscalc precalc gender mtongue;
 255        run;
 
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied.
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.04 seconds
       cpu time            0.02 seconds
       
 
 256        
 257        
 258        /* Decision: Drop Gender and Mother tongue too.
 259           My model now has just HS GPA, HS Calculus and Pre-calculus test. */
 260        
 261        
 262        proc logistic data = mathex;
 263             title3 'Try automatic (stepwise) selection';
 264             model passed (event='Yes') =
 265                           gender mtongue e1-e6
 266                           hsgpa hscalc hsengl
 267                           c1-c3  precalc calc totscore
 268                           / selection = stepwise slentry = 0.05 slstay = 0.05 ;
 269                           /* Default slentry = slstay = 0.15 */
 270        run;
 
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied in Step 0.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied in Step 1.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied in Step 2.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied in Step 3.
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.18 seconds
       cpu time            0.17 seconds
       
 
 271        
 272        
 273        /* Note 211 observations lost to missingness for stepwise, compared to 204
 274           for the earlier model with hsgpa, hscalc and precalc. */
 275        
 276        /* Perhaps missingness on the variables we dropped could be useful.  */
 277        
 278        proc freq;
 279             title2 'Explore missingness on omitted variables';
 280             tables gender mtongue ethnic;
 281             tables gender*mtongue / norow nocol nopercent missing;
 282             tables gender*course / norow nocol nopercent missing;
 283        run;
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.08 seconds
       cpu time            0.09 seconds
       
 
 284        
 285        
 286        data mathex2;
 287             set mathex;
 288             if gender = . then sexmiss = 1; else sexmiss=0; /* Includes mtongue */
 289             if course = . then coursemiss = 1; else coursemiss=0;
 290             format sexmiss coursemiss ynfmt.;
 291             label sexmiss    = 'Gender and mother tongue missing'
 292                   coursemiss = 'Course missing';
 293        
 294        /* Checks are commented out
 295        proc freq;
 296             tables gender*sexmiss / norow nocol nopercent missing;
 297             tables course*coursemiss / norow nocol nopercent missing;
 298             tables sexmiss*coursemiss / norow nocol nopercent missing chisq;
 299        */
 300        
 301        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: The data set WORK.MATHEX2 has 579 observations and 27 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.00 seconds
       cpu time            0.00 seconds
       
 302        proc logistic data = mathex2;
 
 303             title3 'Try adding missingness on gender/mtongue and course';
 304             model passed (event='Yes') = hsgpa hscalc precalc sexmiss coursemiss;
 305        run;
 
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied.
 NOTE: There were 579 observations read from the data set WORK.MATHEX2.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.09 seconds
       cpu time            0.08 seconds
       
 
 306        
 307        
 308        /* All the cases with course missing were deleted because of
 309        missingness on other variables. */
 310        
 311        proc logistic data = mathex2;
 312             title3 'Try adding missingness on gender/mtongue and course';
 313             model passed (event='Yes') = hsgpa hscalc precalc sexmiss;
 314        run;
 
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied.
 NOTE: There were 579 observations read from the data set WORK.MATHEX2.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.09 seconds
       cpu time            0.08 seconds
       
 
 315        
 316        /* Here's the current model. */
 317        
 318        proc logistic data = mathex;
 319             title3 'HS GPA, HS Calculus and Pre-calculus test';
 320             model passed (event='Yes') = hsgpa hscalc precalc;
 321        run;
 
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied.
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.08 seconds
       cpu time            0.08 seconds
       
 
 322        
 323        
 324        /* Goal: Develop a prediction model that uses all the data and makes a
 325           prediction for every case.  */
 326        
 327        
 328        
 329        
 330        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 343