1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 70         
 71         /* mathlogreg3.sas */
 72         
 73         /* Goal: Develop a prediction model that uses all the data and makes a
 74            prediction for every case. */
 75         
 76         %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              244.75k
       OS Memory           29860.00k
       Timestamp           02/10/2020 12:43:38 AM
       Step Count                        95  Switch Count  0
       Page Faults                       0
       Page Reclaims                     25
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           32
       
 
 183        title2 'Use missing values for prediction';
 184        
 185        /* 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 99:24    99 at 138:13   
 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              901.87k
       OS Memory           30376.00k
       Timestamp           02/10/2020 12:43:38 AM
       Step Count                        96  Switch Count  3
       Page Faults                       0
       Page Reclaims                     130
       Page Swaps                        0
       Voluntary Context Switches        25
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 186        data mathex2;
 187             set mathex;
 188             if gender   = . then sexmiss    = 1; else sexmiss=0; /* Includes mtongue */
 189             if course   = . then coursemiss = 1; else coursemiss=0;
 190             if hsgpa    = . then hsgpamiss  = 1; else hsgpamiss=0;
 191             if hscalc   = . then hscalcmiss = 1; else hscalcmiss=0;
 192             if hsengl   = . then hsenglmiss = 1; else hsenglmiss=0;
 193             if totscore = . then testmiss   = 1; else testmiss=0;
 194             if hsgpa+hscalc+precalc = . then missused = 1 ; else missused = 0;
 195             nmiss = sum(sexmiss--testmiss);
 196        
 197        
 198             format sexmiss -- missused ynfmt.;
 199             label sexmiss    = 'Gender and mother tongue missing'
 200                   coursemiss = 'Course missing'
 201                   hsgpamiss  = 'HS GPA missing'
 202                   hscalcmiss = 'HS Calculus mark missing'
 203                   hsenglmiss = 'HS English mark missing'
 204                   testmiss   = 'Diagnostic test scores missing'
 205                   missused   = 'Any of hsgpa hscalc precalc missing';
 206        
 207        /* Checks are commented out
 208        proc freq;
 209             tables gender*sexmiss / norow nocol nopercent missing;
 210             tables course*coursemiss / norow nocol nopercent missing;
 211             tables hsgpa*hsgpamiss / norow nocol nopercent missing;
 212             tables hscalc*hscalcmiss / norow nocol nopercent missing;
 213             tables hsengl*hsenglmiss / norow nocol nopercent missing;
 214             tables totscore*testmiss / norow nocol nopercent missing;
 215             tables (hsgpamiss hscalcmiss testmiss)*missused
 216                                      / norow nocol nopercent missing;
 217        */
 218        
 
 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 194:14   204 at 194:21   
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: The data set WORK.MATHEX2 has 579 observations and 43 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              1343.84k
       OS Memory           30636.00k
       Timestamp           02/10/2020 12:43:38 AM
       Step Count                        97  Switch Count  2
       Page Faults                       0
       Page Reclaims                     130
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 219        proc freq;
 220             title2 'Check usefulness of missing data indicators one at a time';
 221             tables (sexmiss -- missused nmiss) * passed / nocol nopercent chisq;
 222        run;
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX2.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.27 seconds
       user cpu time       0.27 seconds
       system cpu time     0.01 seconds
       memory              4144.25k
       OS Memory           32176.00k
       Timestamp           02/10/2020 12:43:38 AM
       Step Count                        98  Switch Count  5
       Page Faults                       0
       Page Reclaims                     546
       Page Swaps                        0
       Voluntary Context Switches        32
       Involuntary Context Switches      5
       Block Input Operations            0
       Block Output Operations           656
       
 
 223        
 224        proc freq;
 225             title2 'Missingness on variables used, and passing the course';
 226             tables missused * passed / nocol nopercent chisq;
 227        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              1328.03k
       OS Memory           32688.00k
       Timestamp           02/10/2020 12:43:38 AM
       Step Count                        99  Switch Count  5
       Page Faults                       0
       Page Reclaims                     200
       Page Swaps                        0
       Voluntary Context Switches        32
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           528
       
 
 228        
 229        proc freq;
 230             title2 'Just those with missing on variables used';
 231             where missused = 1;
 232             tables (sexmiss coursemiss) * passed / nocol nopercent chisq;
 233        run;
 
 NOTE: There were 204 observations read from the data set WORK.MATHEX2.
       WHERE missused=1;
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.07 seconds
       user cpu time       0.08 seconds
       system cpu time     0.00 seconds
       memory              1495.15k
       OS Memory           32688.00k
       Timestamp           02/10/2020 12:43:39 AM
       Step Count                        100  Switch Count  7
       Page Faults                       0
       Page Reclaims                     205
       Page Swaps                        0
       Voluntary Context Switches        38
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           576
       
 
 234        
 235        /* Decision: If missing on hsgpa, hscalc or precalc, predict they will
 236           not pass. If not missing, use the model with hsgpa, hscalc and precalc. */
 237        
 238        
 239        
 240        
 241        
 242        
 243        
 244        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 255