1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 72         
 73         /* mathlogreg3.sas */
 74         
 75         /* Goal: Develop a prediction model that uses all the data and makes a
 76            prediction for every case. */
 77         
 78         %include '/home/u1407221/441s24/SAS08/ReadLabelMath2.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: Format NCFMT is already on the library WORK.FORMATS.
 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     0.00 seconds
       memory              247.34k
       OS Memory           28836.00k
       Timestamp           03/10/2024 07:57:59 PM
       Step Count                        109  Switch Count  0
       Page Faults                       0
       Page Reclaims                     65
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           32
       
 
 
 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 124:24   
 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     0.01 seconds
       memory              1172.81k
       OS Memory           29352.00k
       Timestamp           03/10/2024 07:57:59 PM
       Step Count                        110  Switch Count  2
       Page Faults                       0
       Page Reclaims                     123
       Page Swaps                        0
       Voluntary Context Switches        21
       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              1413.65k
       OS Memory           29740.00k
       Timestamp           03/10/2024 07:57:59 PM
       Step Count                        111  Switch Count  2
       Page Faults                       0
       Page Reclaims                     157
       Page Swaps                        0
       Voluntary Context Switches        12
       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              1409.09k
       OS Memory           29740.00k
       Timestamp           03/10/2024 07:57:59 PM
       Step Count                        112  Switch Count  2
       Page Faults                       0
       Page Reclaims                     131
       Page Swaps                        0
       Voluntary Context Switches        14
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 239        title2 'Try using missing values for prediction';
 240        
 241        /* Make missing data indicators */
 242        data mathex2;
 243             set explore;
 244             if gender   = . then sexmiss    = 1; else sexmiss=0; /* Includes mtongue */
 245             if course2  = . then coursemiss = 1; else coursemiss=0;
 246             if hsgpa    = . then hsgpamiss  = 1; else hsgpamiss=0;
 247             if hscalc   = . then hscalcmiss = 1; else hscalcmiss=0;
 248             if hsengl   = . then hsenglmiss = 1; else hsenglmiss=0;
 249             if totscore = . then testmiss   = 1; else testmiss=0;
 250             nmiss = sum(sexmiss--testmiss);
 251             if hsgpa+hscalc+precalc = . then missused = 1 ; else missused = 0;
 252        
 253             format sexmiss -- testmiss missused ynfmt.;
 254             label sexmiss    = 'Gender and mother tongue missing'
 255                   coursemiss = 'Course missing'
 256                   hsgpamiss  = 'HS GPA missing'
 257                   hscalcmiss = 'HS Calculus mark missing'
 258                   hsenglmiss = 'HS English mark missing'
 259                   testmiss   = 'Diagnostic test scores missing'
 260                   missused   = 'Any of hsgpa hscalc precalc missing';
 261        
 262        /* Checks are commented out
 263        proc freq;
 264             tables gender*sexmiss / norow nocol nopercent missing;
 265             tables course*coursemiss / norow nocol nopercent missing;
 266             tables hsgpa*hsgpamiss / norow nocol nopercent missing;
 267             tables hscalc*hscalcmiss / norow nocol nopercent missing;
 268             tables hsengl*hsenglmiss / norow nocol nopercent missing;
 269             tables totscore*testmiss / norow nocol nopercent missing;
 270             tables (hsgpamiss hscalcmiss testmiss)*missused
 271                                      / norow nocol nopercent missing;
 272        */
 273        
 
 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 251:14   204 at 251:21   
 NOTE: There were 579 observations read from the data set WORK.EXPLORE.
 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       0.01 seconds
       system cpu time     0.00 seconds
       memory              1316.68k
       OS Memory           29612.00k
       Timestamp           03/10/2024 07:57:59 PM
       Step Count                        113  Switch Count  2
       Page Faults                       0
       Page Reclaims                     128
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           528
       
 
 274        proc freq data=mathex2;
 275             title2 'Check usefulness of missing data indicators one at a time';
 276             tables (sexmiss -- testmiss nmiss) * passed / nocol nopercent chisq;
 277        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX2.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.22 seconds
       user cpu time       0.22 seconds
       system cpu time     0.00 seconds
       memory              4457.56k
       OS Memory           30896.00k
       Timestamp           03/10/2024 07:57:59 PM
       Step Count                        114  Switch Count  5
       Page Faults                       0
       Page Reclaims                     398
       Page Swaps                        0
       Voluntary Context Switches        31
       Involuntary Context Switches      14
       Block Input Operations            0
       Block Output Operations           632
       
 
 278        proc freq data=mathex2;
 279             title2 'Missingness on variables used, and passing the course';
 280             tables missused * passed / nocol nopercent chisq;
 281        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              1416.78k
       OS Memory           30896.00k
       Timestamp           03/10/2024 07:58:00 PM
       Step Count                        115  Switch Count  5
       Page Faults                       0
       Page Reclaims                     257
       Page Swaps                        0
       Voluntary Context Switches        34
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           544
       
 
 282        
 283        /* Strategy: If missing on hsgpa, hscalc or precalc, predict they will
 284           not pass. If not missing, use the model with hsgpa, hscalc and precalc.
 285           Question: Will missingness on Gender/Mother tongue, Course or HS English
 286           add to the ability of (hsgpa, hscalc or precalc) to predict?
 287        
 288           However, the following table shows that every student who was missing
 289           course was also missing on at least one of the good predictors, so
 290           coursemiss is out.   */
 291        
 292        proc freq data=mathex2;
 293             tables coursemiss*missused / norow nocol nopercent missing;
 294        
 
 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       0.01 seconds
       system cpu time     0.00 seconds
       memory              1303.81k
       OS Memory           31152.00k
       Timestamp           03/10/2024 07:58:00 PM
       Step Count                        116  Switch Count  4
       Page Faults                       0
       Page Reclaims                     191
       Page Swaps                        0
       Voluntary Context Switches        29
       Involuntary Context Switches      1
       Block Input Operations            0
       Block Output Operations           536
       
 
 295        proc logistic data = mathex2;
 296             title3 'HS GPA, HS Calculus and Pre-calculus test';
 297             model passed (event='Yes') = hsgpa hscalc precalc
 298                                          sexmiss hsenglmiss;
 299             MissingVars: test sexmiss=hsenglmiss=0;
 300        
 301        /* If missing on hsgpa, hscalc or precalc, give them an estimated
 302           probabilty of passing = 0.348. If not missing, use the model with
 303           hsgpa, hscalc and precalc to calculate the estimated probabilities. */
 304        
 305        quit;
 
 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           0.08 seconds
       user cpu time       0.08 seconds
       system cpu time     0.00 seconds
       memory              2492.21k
       OS Memory           31928.00k
       Timestamp           03/10/2024 07:58:00 PM
       Step Count                        117  Switch Count  1
       Page Faults                       0
       Page Reclaims                     222
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           56
       
 
 306        
 307        
 308        
 309        
 310        
 311        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 323