1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 NOTE: ODS statements in the SAS Studio environment may disable some output features.
 73         
 74         /* mathlogreg2.sas */
 75         %include '/home/u1407221/441s24/SAS08/ReadLabelMath2.sas';
 NOTE: Format YNFMT has been output.
 NOTE: Format CRSFMT has been output.
 NOTE: Format NFMT has been output.
 NOTE: Format NCFMT has been output.
 
 NOTE: PROCEDURE FORMAT used (Total process time):
       real time           0.00 seconds
       user cpu time       0.00 seconds
       system cpu time     0.01 seconds
       memory              302.78k
       OS Memory           25252.00k
       Timestamp           03/10/2024 06:14:57 PM
       Step Count                        24  Switch Count  2
       Page Faults                       0
       Page Reclaims                     89
       Page Swaps                        0
       Voluntary Context Switches        12
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           56
       
 
 
 NOTE: The infile '/home/u1407221/441s24/data/math.data.txt' is:
       Filename=/home/u1407221/441s24/data/math.data.txt,
       Owner Name=u1407221,Group Name=oda,
       Access Permission=-rw-r--r--,
       Last Modified=10Feb2024:17:04:10,
       File Size (bytes)=90324
 
 NOTE: 1158 records were read from the infile '/home/u1407221/441s24/data/math.data.txt'.
       The minimum record length was 76.
       The maximum record length was 76.
 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).
       180 at 121:24   
 NOTE: The data set WORK.MATH has 1158 observations and 37 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.02 seconds
       user cpu time       0.01 seconds
       system cpu time     0.00 seconds
       memory              1176.21k
       OS Memory           26536.00k
       Timestamp           03/10/2024 06:14:57 PM
       Step Count                        25  Switch Count  3
       Page Faults                       0
       Page Reclaims                     283
       Page Swaps                        0
       Voluntary Context Switches        23
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           776
       
 
 
 NOTE: There were 1158 observations read from the data set WORK.MATH.
 NOTE: The data set WORK.REPLIC has 579 observations and 37 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.00 seconds
       user cpu time       0.00 seconds
       system cpu time     0.00 seconds
       memory              1412.81k
       OS Memory           26924.00k
       Timestamp           03/10/2024 06:14:57 PM
       Step Count                        26  Switch Count  2
       Page Faults                       0
       Page Reclaims                     152
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 
 NOTE: There were 1158 observations read from the data set WORK.MATH.
 NOTE: The data set WORK.EXPLORE has 579 observations and 28 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.00 seconds
       user cpu time       0.00 seconds
       system cpu time     0.00 seconds
       memory              1408.28k
       OS Memory           26924.00k
       Timestamp           03/10/2024 06:14:57 PM
       Step Count                        27  Switch Count  2
       Page Faults                       0
       Page Reclaims                     132
       Page Swaps                        0
       Voluntary Context Switches        12
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 236        
 237        title2 'Predict Passing the course (Y-N) with Logistic Regression';
 238        
 239        /* We know course is useful:
 240            c1 = 'Catch-up' c2 = 'Mainstream' c3 = 'Elite' */
 241        
 242        proc logistic data = explore;
 243             title3 'Course and HS variables';
 244             model passed (event='Yes') = c1 c3 hsgpa hscalc hsengl;
 245             course: test c1=c3=0;
 246             HSvars: test hsgpa=hscalc=hsengl=0;
 247        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.EXPLORE.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.09 seconds
       user cpu time       0.09 seconds
       system cpu time     0.00 seconds
       memory              5277.37k
       OS Memory           30648.00k
       Timestamp           03/10/2024 06:14:57 PM
       Step Count                        28  Switch Count  1
       Page Faults                       0
       Page Reclaims                     1896
       Page Swaps                        0
       Voluntary Context Switches        6
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           56
       
 
 248        
 249        /* Decision: Drop course */
 250        
 251        ods select ParameterEstimates; /* Limit the output */
 252        proc logistic data = explore;
 253             title3 'Just HS variables';
 254             model passed (event='Yes') = hsgpa hscalc hsengl;
 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.EXPLORE.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.02 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              2338.65k
       OS Memory           30904.00k
       Timestamp           03/10/2024 06:14:57 PM
       Step Count                        29  Switch Count  1
       Page Faults                       0
       Page Reclaims                     257
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           48
       
 
 256        
 257        /* Decision: Drop HS English.
 258           Does the diagnostic test add anything? */
 259        
 260        ods select ParameterEstimates;
 261        proc logistic data = explore;
 262             title3 'HS GPA, HS Calculus and Diagnostic Test';
 263             model passed (event='Yes') = hsgpa hscalc calc precalc;
 264        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.EXPLORE.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.02 seconds
       user cpu time       0.02 seconds
       system cpu time     0.01 seconds
       memory              2301.65k
       OS Memory           30904.00k
       Timestamp           03/10/2024 06:14:57 PM
       Step Count                        30  Switch Count  1
       Page Faults                       0
       Page Reclaims                     199
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           40
       
 
 265        
 266        /* Decision: Drop the calc subscale, but which is better,
 267           precalc or total score? */
 268        
 269        ods select ParameterEstimates TestStmts; /* I ran a trace to find out the name */
 270        proc logistic data = explore;
 271             title3 'HS GPA, HS Calculus and Diagnostic Test';
 272             model passed (event='Yes') = hsgpa hscalc precalc totscore;
 273             precalc_n_totscore: test precalc = totscore = 0;
 274        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.EXPLORE.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.02 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              2339.25k
       OS Memory           30904.00k
       Timestamp           03/10/2024 06:14:57 PM
       Step Count                        31  Switch Count  1
       Page Faults                       0
       Page Reclaims                     209
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           48
       
 
 275        
 276        /* Decision: Keep precalc rather than totscore. Confirm */
 277        
 278        ods select ParameterEstimates;
 279        proc logistic data = explore;
 280             title3 'HS GPA, HS Calculus and Pre-calculus test';
 281             model passed (event='Yes') = hsgpa hscalc precalc;
 282        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.EXPLORE.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.02 seconds
       user cpu time       0.01 seconds
       system cpu time     0.00 seconds
       memory              2302.59k
       OS Memory           30904.00k
       Timestamp           03/10/2024 06:14:57 PM
       Step Count                        32  Switch Count  1
       Page Faults                       0
       Page Reclaims                     198
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           40
       
 
 283        
 284        proc logistic data = explore;
 285             title3 'Try gender, ethnic and mother tongue controlling for good stuff';
 286             class ethnic (param=ref ref='East Indian');
 287                  /* Specifying a reference category that's not the last value */
 288             model passed (event='Yes') = hsgpa hscalc precalc ethnic gender mtongue;
 289             contrast 'Demographics'      ethnic  1 0 0 0 0,
 290                                          ethnic  0 1 0 0 0,
 291                                          ethnic  0 0 1 0 0,
 292                                          ethnic  0 0 0 1 0,
 293                                          ethnic  0 0 0 0 1,
 294                                          gender  1,
 295                                          mtongue 1 / e;
 296                                                     /* Display the effect matrix */
 297        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.EXPLORE.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.11 seconds
       user cpu time       0.11 seconds
       system cpu time     0.01 seconds
       memory              2690.68k
       OS Memory           31416.00k
       Timestamp           03/10/2024 06:14:57 PM
       Step Count                        33  Switch Count  1
       Page Faults                       0
       Page Reclaims                     311
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           104
       
 
 298        
 299        /* Decision: Forget about ethnicity. */
 300        
 301        ods select ParameterEstimates;
 302        proc logistic data = explore;
 303             title3 'HS GPA, HS Calculus, Pre-calculus test, Gender and Mother tongue';
 304             model passed (event='Yes') = hsgpa hscalc precalc gender mtongue;
 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.EXPLORE.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.02 seconds
       user cpu time       0.01 seconds
       system cpu time     0.00 seconds
       memory              2325.37k
       OS Memory           31416.00k
       Timestamp           03/10/2024 06:14:57 PM
       Step Count                        34  Switch Count  1
       Page Faults                       0
       Page Reclaims                     193
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           40
       
 
 306        
 307        /* Decision: Drop Gender and Mother tongue too.
 308           My model now has just HS GPA, HS Calculus and Pre-calculus test. */
 309        
 310        proc logistic data = explore;
 311             title3 'Try automatic (stepwise) selection';
 312             model passed (event='Yes') =
 313                           gender mtongue e1-e6
 314                           hsgpa hscalc hsengl
 315                           c1-c3  precalc calc totscore
 316                           / selection = stepwise slentry = 0.05 slstay = 0.05 ;
 317                           /* Default slentry = slstay = 0.15 */
 318        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.EXPLORE.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.13 seconds
       user cpu time       0.13 seconds
       system cpu time     0.00 seconds
       memory              2602.12k
       OS Memory           31416.00k
       Timestamp           03/10/2024 06:14:58 PM
       Step Count                        35  Switch Count  1
       Page Faults                       0
       Page Reclaims                     246
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      2
       Block Input Operations            0
       Block Output Operations           176
       
 
 319        
 320        
 321        /* Note 211 observations lost to missingness for stepwise, compared to 204
 322           for the earlier model with hsgpa, hscalc and precalc. */
 323        
 324        /* Perhaps missingness on the variables we dropped could be useful.  */
 325        
 326        proc freq;
 327             title2 'Explore missingness on omitted variables';
 328             tables gender mtongue ethnic;
 329             tables gender*mtongue / norow nocol nopercent missing;
 330             tables gender*course2 / norow nocol nopercent missing;
 331        run;
 
 NOTE: There were 579 observations read from the data set WORK.EXPLORE.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.05 seconds
       user cpu time       0.06 seconds
       system cpu time     0.01 seconds
       memory              1762.21k
       OS Memory           31152.00k
       Timestamp           03/10/2024 06:14:58 PM
       Step Count                        36  Switch Count  5
       Page Faults                       0
       Page Reclaims                     452
       Page Swaps                        0
       Voluntary Context Switches        37
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           544
       
 
 332        
 333        
 334        data explore2;
 335             set explore;
 336             if gender = . then sexmiss = 1; else sexmiss=0; /* Includes mtongue */
 337             if course = . then coursemiss = 1; else coursemiss=0;
 338             format sexmiss coursemiss ynfmt.;
 339             label sexmiss    = 'Gender and mother tongue missing'
 340                   coursemiss = 'Course missing';
 341        
 342        /* Checks are commented out
 343        proc freq;
 344             tables gender*sexmiss / norow nocol nopercent missing;
 345             tables course*coursemiss / norow nocol nopercent missing;
 346             tables sexmiss*coursemiss / norow nocol nopercent missing chisq;
 347        */
 348        
 349        
 
 NOTE: Variable course is uninitialized.
 NOTE: There were 579 observations read from the data set WORK.EXPLORE.
 NOTE: The data set WORK.EXPLORE2 has 579 observations and 31 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.00 seconds
       user cpu time       0.00 seconds
       system cpu time     0.00 seconds
       memory              1266.25k
       OS Memory           31148.00k
       Timestamp           03/10/2024 06:14:58 PM
       Step Count                        37  Switch Count  2
       Page Faults                       0
       Page Reclaims                     162
       Page Swaps                        0
       Voluntary Context Switches        13
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 350        proc logistic data = explore2;
 351             title3 'Try adding missingness on gender/mtongue and course';
 352             model passed (event='Yes') = hsgpa hscalc precalc sexmiss coursemiss;
 353        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.EXPLORE2.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.06 seconds
       user cpu time       0.07 seconds
       system cpu time     0.00 seconds
       memory              2414.34k
       OS Memory           32184.00k
       Timestamp           03/10/2024 06:14:58 PM
       Step Count                        38  Switch Count  1
       Page Faults                       0
       Page Reclaims                     243
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           72
       
 
 354        
 355        
 356        /* All the cases with course missing were deleted because of
 357        missingness on other variables. */
 358        
 359        proc logistic data = explore2;
 360             title3 'Try adding missingness on gender/mtongue and course';
 361             model passed (event='Yes') = hsgpa hscalc precalc sexmiss;
 362        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.EXPLORE2.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.06 seconds
       user cpu time       0.06 seconds
       system cpu time     0.00 seconds
       memory              2342.46k
       OS Memory           32184.00k
       Timestamp           03/10/2024 06:14:58 PM
       Step Count                        39  Switch Count  1
       Page Faults                       0
       Page Reclaims                     208
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           80
       
 
 363        
 364        /* Here's the current model. */
 365        
 366        proc logistic data = explore;
 367             title3 'HS GPA, HS Calculus and Pre-calculus test';
 368             model passed (event='Yes') = hsgpa hscalc precalc;
 369             output out=explore3 prob=pihat;
 370        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.EXPLORE.
 NOTE: The data set WORK.EXPLORE3 has 579 observations and 30 variables.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.06 seconds
       user cpu time       0.06 seconds
       system cpu time     0.00 seconds
       memory              2841.50k
       OS Memory           32444.00k
       Timestamp           03/10/2024 06:14:58 PM
       Step Count                        40  Switch Count  3
       Page Faults                       0
       Page Reclaims                     265
       Page Swaps                        0
       Voluntary Context Switches        26
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           584
       
 
 371        
 372        
 373        proc print data=explore3 (obs=13);
 374                             /* List only the first 13 observations */
 375             var hsgpa hscalc precalc pihat passed;
 376        run;
 
 NOTE: There were 13 observations read from the data set WORK.EXPLORE3.
 NOTE: PROCEDURE PRINT used (Total process time):
       real time           0.02 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              821.53k
       OS Memory           31144.00k
       Timestamp           03/10/2024 06:14:58 PM
       Step Count                        41  Switch Count  0
       Page Faults                       0
       Page Reclaims                     147
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           0
       
 
 377        
 378        
 379        /* Based on invariance and the Law of Total Probability (double expectation),
 380           I predict that the mean pihat will be 234/375 = 0.624, the proportion of
 381           students with non-missing data who passed. */
 382        
 383        proc univariate normal plot data=explore3;
 384             title2 'Explore the distribution of estimated probabilities';
 385             where pihat ne .;
 386             var pihat; /* Should have n=375 non-missing. */
 387        run;
 
 NOTE: PROCEDURE UNIVARIATE used (Total process time):
       real time           2.43 seconds
       user cpu time       0.17 seconds
       system cpu time     0.03 seconds
       memory              22269.43k
       OS Memory           52396.00k
       Timestamp           03/10/2024 06:15:00 PM
       Step Count                        42  Switch Count  4
       Page Faults                       0
       Page Reclaims                     7226
       Page Swaps                        0
       Voluntary Context Switches        523
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           1632
       
 
 388        
 389        
 390        /* Goal: Develop a prediction model that uses all the data and makes a
 391           prediction for every case.  Base on estimated probabilities. */
 392        
 393        
 394        
 395        
 396        
 397        
 398        
 399        
 400        
 401        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 413