1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 NOTE: ODS statements in the SAS Studio environment may disable some output features.
 71         
 72         /* mathlogreg2.sas */
 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              244.34k
       OS Memory           30372.00k
       Timestamp           02/10/2020 12:09:23 AM
       Step Count                        64  Switch Count  0
       Page Faults                       0
       Page Reclaims                     24
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           32
       
 
 180        /* %include '/home/brunner0/441s20/readexplor.sas'; */
 181        title2 'Predict Passing the course (Y-N) with Logistic Regression';
 182        
 183        /* We know course is useful:
 184            c1 = 'Catch-up' c2 = 'Mainstream' c3 = 'Elite' */
 185        
 
 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       0.00 seconds
       system cpu time     0.00 seconds
       memory              891.56k
       OS Memory           30888.00k
       Timestamp           02/10/2020 12:09:23 AM
       Step Count                        65  Switch Count  3
       Page Faults                       0
       Page Reclaims                     106
       Page Swaps                        0
       Voluntary Context Switches        24
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 186        proc logistic data = mathex;
 187             title3 'Course and HS variables';
 188             model passed (event='Yes') = c1 c3 hsgpa hscalc hsengl;
 189             course: test c1=c3=0;
 190        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           0.10 seconds
       user cpu time       0.10 seconds
       system cpu time     0.00 seconds
       memory              4573.59k
       OS Memory           32952.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        66  Switch Count  1
       Page Faults                       0
       Page Reclaims                     435
       Page Swaps                        0
       Voluntary Context Switches        6
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           56
       
 
 191        
 192        
 193        /* Decision: Drop course */
 194        
 195        
 196        ods select ParameterEstimates; /* Limit the output */
 197        proc logistic data = mathex;
 198             title3 'Just HS variables';
 199             model passed (event='Yes') = hsgpa hscalc hsengl;
 200        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           0.02 seconds
       user cpu time       0.03 seconds
       system cpu time     0.00 seconds
       memory              2339.25k
       OS Memory           32952.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        67  Switch Count  1
       Page Faults                       0
       Page Reclaims                     192
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           40
       
 
 201        
 202        
 203        /* Decision: Drop HS English.
 204           Does the diagnostic test add anything? */
 205        
 206        
 207        ods select ParameterEstimates;
 208        proc logistic data = mathex;
 209             title3 'HS GPA, HS Calculus and Diagnostic Test';
 210             model passed (event='Yes') = hsgpa hscalc calc precalc;
 211        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           0.02 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              2306.09k
       OS Memory           32952.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        68  Switch Count  1
       Page Faults                       0
       Page Reclaims                     202
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           40
       
 
 212        
 213        
 214        /* Decision: Drop the calc subscale, but which is better,
 215           precalc or total score? */
 216        
 217        
 218        ods select ParameterEstimates TestStmts; /* I ran a trace to find out the name */
 219        proc logistic data = mathex;
 220             title3 'HS GPA, HS Calculus and Diagnostic Test';
 221             model passed (event='Yes') = hsgpa hscalc precalc totscore;
 222             precalc_n_totscore: test precalc = totscore = 0;
 223        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
       user cpu time       0.03 seconds
       system cpu time     0.01 seconds
       memory              2331.43k
       OS Memory           32952.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        69  Switch Count  1
       Page Faults                       0
       Page Reclaims                     201
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           48
       
 
 224        
 225        
 226        /* Decision: Keep precalc rather than totscore. Confirm */
 227        
 228        
 229        ods select ParameterEstimates;
 230        proc logistic data = mathex;
 231             title3 'HS GPA, HS Calculus and Pre-calculus test';
 232             model passed (event='Yes') = hsgpa hscalc precalc;
 233        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           0.02 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              2282.78k
       OS Memory           32952.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        70  Switch Count  1
       Page Faults                       0
       Page Reclaims                     188
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           40
       
 
 234        
 235        proc logistic data = mathex;
 236             title3 'Try gender, ethnic and mother tongue controlling for good stuff';
 237             class ethnic (param=ref ref='East Indian');
 238                  /* Specifying a reference category that's not the last value */
 239             model passed (event='Yes') = hsgpa hscalc precalc ethnic gender mtongue;
 240             contrast 'Demographics'      ethnic  1 0 0 0 0,
 241                                          ethnic  0 1 0 0 0,
 242                                          ethnic  0 0 1 0 0,
 243                                          ethnic  0 0 0 1 0,
 244                                          ethnic  0 0 0 0 1,
 245                                          gender  1,
 246                                          mtongue 1 / e;
 247                                                     /* Display the effect matrix */
 248        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           0.14 seconds
       user cpu time       0.15 seconds
       system cpu time     0.00 seconds
       memory              2586.50k
       OS Memory           33208.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        71  Switch Count  1
       Page Faults                       0
       Page Reclaims                     253
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      1
       Block Input Operations            0
       Block Output Operations           104
       
 
 249        
 250        
 251        /* Decision: Forget about ethnicity. */
 252        
 253        
 254        ods select ParameterEstimates;
 255        proc logistic data = mathex;
 256             title3 'HS GPA, HS Calculus, Pre-calculus test, Gender and Mother tongue';
 257             model passed (event='Yes') = hsgpa hscalc precalc gender mtongue;
 258        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           0.02 seconds
       user cpu time       0.03 seconds
       system cpu time     0.00 seconds
       memory              2303.68k
       OS Memory           33208.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        72  Switch Count  1
       Page Faults                       0
       Page Reclaims                     198
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           40
       
 
 259        
 260        
 261        /* Decision: Drop Gender and Mother tongue too.
 262           My model now has just HS GPA, HS Calculus and Pre-calculus test. */
 263        
 264        
 265        proc logistic data = mathex;
 266             title3 'Try automatic (stepwise) selection';
 267             model passed (event='Yes') =
 268                           gender mtongue e1-e6
 269                           hsgpa hscalc hsengl
 270                           c1-c3  precalc calc totscore
 271                           / selection = stepwise slentry = 0.05 slstay = 0.05 ;
 272                           /* Default slentry = slstay = 0.15 */
 273        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           0.16 seconds
       user cpu time       0.17 seconds
       system cpu time     0.00 seconds
       memory              2577.09k
       OS Memory           33208.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        73  Switch Count  1
       Page Faults                       0
       Page Reclaims                     211
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           104
       
 
 274        
 275        
 276        /* Note 211 observations lost to missingness for stepwise, compared to 204
 277           for the earlier model with hsgpa, hscalc and precalc. */
 278        
 279        /* Perhaps missingness on the variables we dropped could be useful.  */
 280        
 281        proc freq;
 282             title2 'Explore missingness on omitted variables';
 283             tables gender mtongue ethnic;
 284             tables gender*mtongue / norow nocol nopercent missing;
 285             tables gender*course / norow nocol nopercent missing;
 286        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
       user cpu time       0.08 seconds
       system cpu time     0.00 seconds
       memory              1629.90k
       OS Memory           32944.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        74  Switch Count  5
       Page Faults                       0
       Page Reclaims                     232
       Page Swaps                        0
       Voluntary Context Switches        33
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           544
       
 
 287        
 288        
 289        data mathex2;
 290             set mathex;
 291             if gender = . then sexmiss = 1; else sexmiss=0; /* Includes mtongue */
 292             if course = . then coursemiss = 1; else coursemiss=0;
 293             format sexmiss coursemiss ynfmt.;
 294             label sexmiss    = 'Gender and mother tongue missing'
 295                   coursemiss = 'Course missing';
 296        
 297        /* Checks are commented out
 298        proc freq;
 299             tables gender*sexmiss / norow nocol nopercent missing;
 300             tables course*coursemiss / norow nocol nopercent missing;
 301             tables sexmiss*coursemiss / norow nocol nopercent missing chisq;
 302        */
 303        
 304        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: The data set WORK.MATHEX2 has 579 observations and 37 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              1291.53k
       OS Memory           32684.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        75  Switch Count  2
       Page Faults                       0
       Page Reclaims                     95
       Page Swaps                        0
       Voluntary Context Switches        12
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 305        proc logistic data = mathex2;
 306             title3 'Try adding missingness on gender/mtongue and course';
 307             model passed (event='Yes') = hsgpa hscalc precalc sexmiss coursemiss;
 308        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           0.08 seconds
       user cpu time       0.08 seconds
       system cpu time     0.00 seconds
       memory              2429.46k
       OS Memory           33720.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        76  Switch Count  1
       Page Faults                       0
       Page Reclaims                     211
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      8
       Block Input Operations            0
       Block Output Operations           64
       
 
 309        
 310        
 311        /* All the cases with course missing were deleted because of
 312        missingness on other variables. */
 313        
 314        proc logistic data = mathex2;
 315             title3 'Try adding missingness on gender/mtongue and course';
 316             model passed (event='Yes') = hsgpa hscalc precalc sexmiss;
 317        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           0.08 seconds
       user cpu time       0.07 seconds
       system cpu time     0.00 seconds
       memory              2333.09k
       OS Memory           33720.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        77  Switch Count  1
       Page Faults                       0
       Page Reclaims                     205
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           80
       
 
 318        
 319        /* Here's the current model. */
 320        
 321        proc logistic data = mathex;
 322             title3 'HS GPA, HS Calculus and Pre-calculus test';
 323             model passed (event='Yes') = hsgpa hscalc precalc;
 324        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           0.07 seconds
       user cpu time       0.07 seconds
       system cpu time     0.00 seconds
       memory              2308.87k
       OS Memory           33720.00k
       Timestamp           02/10/2020 12:09:24 AM
       Step Count                        78  Switch Count  1
       Page Faults                       0
       Page Reclaims                     201
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      1
       Block Input Operations            0
       Block Output Operations           64
       
 
 325        
 326        
 327        /* Goal: Develop a prediction model that uses all the data and makes a
 328           prediction for every case.  */
 329        
 330        
 331        
 332        
 333        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 344