1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 70         
 71         /* mathlogreg4.sas */
 72         
 73         %include '/home/brunner0/441s20/readmath2b.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
       user cpu time       0.00 seconds
       system cpu time     0.00 seconds
       memory              244.81k
       OS Memory           32420.00k
       Timestamp           02/10/2020 12:55:47 AM
       Step Count                        146  Switch Count  0
       Page Faults                       0
       Page Reclaims                     27
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           32
       
 
 180        title2 'Use missing values for prediction';
 181        
 182        /* Make missing data indicators */
 
 NOTE: The infile '/home/brunner0/441s20/exploremath.data.txt' is:
       Filename=/home/brunner0/441s20/exploremath.data.txt,
       Owner Name=brunner0,Group Name=oda,
       Access Permission=-rw-r--r--,
       Last Modified=26Jan2020:18:49:34,
       File Size (bytes)=44583
 
 NOTE: 579 records were read from the infile '/home/brunner0/441s20/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 96:24    99 at 135:13   
 NOTE: The data set WORK.MATHEX has 579 observations and 35 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.00 seconds
       user cpu time       0.01 seconds
       system cpu time     0.00 seconds
       memory              963.50k
       OS Memory           32936.00k
       Timestamp           02/10/2020 12:55:47 AM
       Step Count                        147  Switch Count  3
       Page Faults                       0
       Page Reclaims                     124
       Page Swaps                        0
       Voluntary Context Switches        27
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 183        data mathex2;
 184             set mathex;
 185             if hsgpa+hscalc+precalc = . then missused = 1 ;
 186                else missused = 0;
 187             format missused ynfmt.;
 188             label missused   = 'Any of hsgpa hscalc precalc missing';
 189        
 
 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).
       142 at 185:14   204 at 185:21   
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: The data set WORK.MATHEX2 has 579 observations and 36 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.00 seconds
       user cpu time       0.00 seconds
       system cpu time     0.01 seconds
       memory              1306.68k
       OS Memory           33196.00k
       Timestamp           02/10/2020 12:55:47 AM
       Step Count                        148  Switch Count  2
       Page Faults                       0
       Page Reclaims                     114
       Page Swaps                        0
       Voluntary Context Switches        14
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 190        proc freq data=mathex2;
 191             title2 'Percent passed for the record';
 192             tables passed;
 193        run;
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX2.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.02 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              2874.53k
       OS Memory           33452.00k
       Timestamp           02/10/2020 12:55:47 AM
       Step Count                        149  Switch Count  3
       Page Faults                       0
       Page Reclaims                     237
       Page Swaps                        0
       Voluntary Context Switches        16
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           272
       
 
 194        
 195        proc freq data=mathex2;
 196             title2 'Missingness on variables used, as a predictor of passing';
 197             tables missused * passed / nocol nopercent chisq;
 198        run;
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX2.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.04 seconds
       user cpu time       0.04 seconds
       system cpu time     0.00 seconds
       memory              1820.15k
       OS Memory           33968.00k
       Timestamp           02/10/2020 12:55:47 AM
       Step Count                        150  Switch Count  5
       Page Faults                       0
       Page Reclaims                     247
       Page Swaps                        0
       Voluntary Context Switches        40
       Involuntary Context Switches      1
       Block Input Operations            0
       Block Output Operations           528
       
 
 199        
 200        /* If missing on hsgpa, hscalc or precalc, give them an estimated
 201           probabilty of passing of 0.348. If not missing, use the model with
 202           hsgpa, hscalc and precalc to calculate the estimated probabilities. */
 203        
 204        proc logistic data = mathex2 noprint;
 205             title3 'Look at estimated probabilities';
 206             model passed (event='Yes') = hsgpa hscalc precalc;
 207             output out=mathex3 prob=pihat;
 208        /* The data set mathex3 has everything in mathex2, and also pihat */
 209        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: The data set WORK.MATHEX3 has 579 observations and 38 variables.
 NOTE: PROCEDURE LOGISTIC used (Total process time):
       real time           0.00 seconds
       user cpu time       0.00 seconds
       system cpu time     0.01 seconds
       memory              2342.03k
       OS Memory           35004.00k
       Timestamp           02/10/2020 12:55:47 AM
       Step Count                        151  Switch Count  3
       Page Faults                       0
       Page Reclaims                     229
       Page Swaps                        0
       Voluntary Context Switches        22
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           552
       
 
 210        
 211        proc print data=mathex3 (obs=13);
 212                             /* List only the first 13 observations */
 213             var hsgpa hscalc precalc pihat;
 214        run;
 
 NOTE: There were 13 observations read from the data set WORK.MATHEX3.
 NOTE: PROCEDURE PRINT used (Total process time):
       real time           0.02 seconds
       user cpu time       0.03 seconds
       system cpu time     0.00 seconds
       memory              934.43k
       OS Memory           33704.00k
       Timestamp           02/10/2020 12:55:47 AM
       Step Count                        152  Switch Count  0
       Page Faults                       0
       Page Reclaims                     62
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           24
       
 
 215        
 216        /* Based on invariance and the Law of Total Probability (double expectation),
 217           I predict that the mean pihat will be around 0.624, the proportion of
 218           students with non-missing data who passed. */
 219        
 220        proc univariate normal plot data=mathex3;
 221             title2 'Explore the distribution of estimated probabilities';
 222             where missused = 0; /* Should have n=375 */
 223             var pihat;
 224        run;
 
 NOTE: PROCEDURE UNIVARIATE used (Total process time):
       real time           0.38 seconds
       user cpu time       0.17 seconds
       system cpu time     0.01 seconds
       memory              15070.68k
       OS Memory           46508.00k
       Timestamp           02/10/2020 12:55:47 AM
       Step Count                        153  Switch Count  4
       Page Faults                       0
       Page Reclaims                     3677
       Page Swaps                        0
       Voluntary Context Switches        306
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           1008
       
 
 225        
 226        /* Where should we draw the line, and predict that the student will pass?
 227           In the exploratory sample, 52.68% passed overall, so find the
 228           pihat that cuts of the bottom 52.68%, and use that as a cutoff.*/
 229        
 230        data mathex4;
 231             set mathex3;
 232             if pihat = . then pihat = 0.348;
 233             /* Proportion with missing data who passed  */
 234        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX3.
 NOTE: The data set WORK.MATHEX4 has 579 observations and 38 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              1289.59k
       OS Memory           46508.00k
       Timestamp           02/10/2020 12:55:47 AM
       Step Count                        154  Switch Count  2
       Page Faults                       0
       Page Reclaims                     101
       Page Swaps                        0
       Voluntary Context Switches        13
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 235        proc freq data = mathex4;
 236             title2 'Seek the 52.68 percentile';
 237             tables pihat;
 238        run;
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX4.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.37 seconds
       user cpu time       0.37 seconds
       system cpu time     0.00 seconds
       memory              1617.93k
       OS Memory           47276.00k
       Timestamp           02/10/2020 12:55:48 AM
       Step Count                        155  Switch Count  3
       Page Faults                       0
       Page Reclaims                     267
       Page Swaps                        0
       Voluntary Context Switches        22
       Involuntary Context Switches      1
       Block Input Operations            0
       Block Output Operations           528
       
 
 239        
 240        /* There was a pihat right at the 52.68th percentile: 0.4063743825.
 241           If pihat > 0.406, predict the student will pass. For the record and
 242           before peeking, I predict 75% correct. */
 243        
 244        /* Read and transform the replication data -- same code as mathread1.sas
 245           except no keep statement.  Creates the data set mathrep. */
 246        %include '/home/brunner0/441s20/readreplic.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
       user cpu time       0.00 seconds
       system cpu time     0.00 seconds
       memory              351.71k
       OS Memory           46756.00k
       Timestamp           02/10/2020 12:55:48 AM
       Step Count                        156  Switch Count  0
       Page Faults                       0
       Page Reclaims                     14
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           0
       
 
 359        /* The data step continues ... */
 360        
 361        b0 = -14.7970; b1 = 0.1173; b2 = 0.0638; b3 = 0.2989; /* Exploratory sample values */
 362        L = b0 + b1*hsgpa + b2*hscalc + b3*precalc;
 363        pihat = exp(L)/(1+exp(L)); /* Some will be missing. */
 364        if pihat = . then pihat = 0.348; /* Sample proportion passed in the exploratory sample */
 365        if pihat > 0.406 then Prediction = 'Pass    '; else Prediction = 'Not Pass';
 366        
 367        /* Commented out
 368        proc freq data = replic;
 369             title2 'Checking Prediction';
 370             tables pihat * Prediction / norow nocol nopercent missing;
 371        run;
 372        */
 373        
 
 NOTE: The infile '/home/brunner0/441s20/replicmath.data.txt' is:
       Filename=/home/brunner0/441s20/replicmath.data.txt,
       Owner Name=brunner0,Group Name=oda,
       Access Permission=-rw-r--r--,
       Last Modified=26Jan2020:18:49:13,
       File Size (bytes)=38214
 
 NOTE: 579 records were read from the infile '/home/brunner0/441s20/replicmath.data.txt'.
       The minimum record length was 64.
       The maximum record length was 64.
 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).
       81 at 274:24    81 at 310:18    97 at 362:12    30 at 362:23    59 at 362:35    186 at 363:9    186 at 363:18
       186 at 363:19   
 NOTE: The data set WORK.REPLIC has 579 observations and 42 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.00 seconds
       user cpu time       0.00 seconds
       system cpu time     0.01 seconds
       memory              909.65k
       OS Memory           47016.00k
       Timestamp           02/10/2020 12:55:48 AM
       Step Count                        157  Switch Count  2
       Page Faults                       0
       Page Reclaims                     69
       Page Swaps                        0
       Voluntary Context Switches        19
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 374        proc freq data = replic;
 375             title2 'How good is the prediction?';
 376             tables Prediction*passed / nocol;
 377        
 
 NOTE: There were 579 observations read from the data set WORK.REPLIC.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.02 seconds
       user cpu time       0.03 seconds
       system cpu time     0.00 seconds
       memory              1170.93k
       OS Memory           47536.00k
       Timestamp           02/10/2020 12:55:48 AM
       Step Count                        158  Switch Count  5
       Page Faults                       0
       Page Reclaims                     191
       Page Swaps                        0
       Voluntary Context Switches        38
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           536
       
 
 378        proc iml;
 NOTE: IML Ready
 379             PercentCorrect = 35.75 + 34.54;
 380             print PercentCorrect;
 381        run;
 NOTE: Module MAIN is undefined in IML; cannot be RUN.
 382        
 383        /* Prediction may be better at the extremes. */
 384        
 NOTE: Exiting IML.
 NOTE: PROCEDURE IML used (Total process time):
       real time           0.00 seconds
       user cpu time       0.01 seconds
       system cpu time     0.00 seconds
       memory              540.28k
       OS Memory           46756.00k
       Timestamp           02/10/2020 12:55:48 AM
       Step Count                        159  Switch Count  0
       Page Faults                       0
       Page Reclaims                     136
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           8
       
 
 385        proc freq data = replic;
 386             tables pihat*passed / norow nocol nopercent;
 387        run;
 
 NOTE: There were 579 observations read from the data set WORK.REPLIC.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.89 seconds
       user cpu time       0.90 seconds
       system cpu time     0.00 seconds
       memory              1312.62k
       OS Memory           47536.00k
       Timestamp           02/10/2020 12:55:49 AM
       Step Count                        160  Switch Count  4
       Page Faults                       0
       Page Reclaims                     192
       Page Swaps                        0
       Voluntary Context Switches        29
       Involuntary Context Switches      2
       Block Input Operations            0
       Block Output Operations           864
       
 
 388        
 389        
 390        
 391        
 392        
 393        
 394        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 405