1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 70         
 71         /* MathReg1.sas  */
 72         %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           29348.00k
       Timestamp           02/03/2020 05:33:48 PM
       Step Count                        38  Switch Count  0
       Page Faults                       0
       Page Reclaims                     28
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           32
       
 
 176        /* readmath2b has dummy variable definitions
 177                e1-e4,e6 for ethnic (Reference category is East Indian)
 178                gender=1 for Female
 179                mtongue=1 for English
 180                c1-c3: c1 = 'Catch-up' c2 = 'Mainstream' c3 = 'Elite'   */
 181        
 182        title2 'Variable Selection for Predicting Grade';
 183        
 
 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 95:24    99 at 134:13   
 NOTE: The data set WORK.MATHEX has 579 observations and 34 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.06 seconds
       user cpu time       0.00 seconds
       system cpu time     0.00 seconds
       memory              873.15k
       OS Memory           29864.00k
       Timestamp           02/03/2020 05:33:48 PM
       Step Count                        39  Switch Count  3
       Page Faults                       0
       Page Reclaims                     139
       Page Swaps                        0
       Voluntary Context Switches        27
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 184        proc freq;
 185             title3 'Check dummy variables';
 186             tables sex*gender / norow nocol nopercent missing;
 187             tables tongue*mtongue / norow nocol nopercent missing;
 188             tables (e1-e4 e6) * ethnic / norow nocol nopercent missing;
 189             tables (c1-c3) * course / norow nocol nopercent missing;
 190        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.22 seconds
       user cpu time       0.22 seconds
       system cpu time     0.01 seconds
       memory              4035.93k
       OS Memory           31920.00k
       Timestamp           02/03/2020 05:33:48 PM
       Step Count                        40  Switch Count  5
       Page Faults                       0
       Page Reclaims                     552
       Page Swaps                        0
       Voluntary Context Switches        28
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           616
       
 
 191        proc reg plots = none; /* Suppress diagnostic plots for now*/
 192             title3 'Model A: Predict University Calculus Grade from HS Information';
 193             model grade = hsgpa hscalc hsengl;
 194        
 195        /* It is very interesting to know what proportion of the remaining
 196           variation is explained by each variable, controlling for the other two.
 197           F = t-squared, and
 198                               a = sF/(n-p + sF)
 199        */
 200        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.04 seconds
       user cpu time       0.05 seconds
       system cpu time     0.00 seconds
       memory              2751.59k
       OS Memory           33728.00k
       Timestamp           02/03/2020 05:33:48 PM
       Step Count                        41  Switch Count  2
       Page Faults                       0
       Page Reclaims                     393
       Page Swaps                        0
       Voluntary Context Switches        24
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           48
       
 
 201        proc iml;
 NOTE: IML Ready
 202             title3 'Proportion of remaining variation for HS information';
 203             n = 323;
 203      !               p = 4;
 203      !                      s = 1;
 204             print "hsgpa controlling for hscalc and hsengl";
 205             t = 8.00;
 205      !                F = t**2;
 205      !                           a = s*F/(n-p + s*F);
 206             print a;
 207        
 208             print "hscalc controlling for hsgpa and hsengl";
 209             t = 3.14;
 209      !                F = t**2;
 209      !                           a = s*F/(n-p + s*F);
 210             print a;
 211        
 212             print "hsengl controlling for hsgpa and hscalc";
 213             t = -3.26;
 213      !                 F = t**2;
 213      !                            a = s*F/(n-p + s*F);
 214             print a;
 215        
 NOTE: Exiting IML.
 NOTE: PROCEDURE IML used (Total process time):
       real time           0.02 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              629.25k
       OS Memory           32164.00k
       Timestamp           02/03/2020 05:33:48 PM
       Step Count                        42  Switch Count  1
       Page Faults                       0
       Page Reclaims                     290
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           24
       
 
 216        proc reg plots = none;
 217             title3 'Model B: Predict University Calculus Grade from Diagnostic Test';
 218             model grade = precalc calc;
 219        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.04 seconds
       user cpu time       0.04 seconds
       system cpu time     0.00 seconds
       memory              2543.12k
       OS Memory           34240.00k
       Timestamp           02/03/2020 05:33:48 PM
       Step Count                        43  Switch Count  2
       Page Faults                       0
       Page Reclaims                     303
       Page Swaps                        0
       Voluntary Context Switches        22
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           48
       
 
 220        proc reg plots = none;
 221             title3 'Model C: Do the diagnostic test and HS info both contribute?';
 222             model grade = hsgpa hscalc hsengl precalc calc;
 223             Diagnostic_Test:  test  precalc=calc=0;
 224             HS_Information:   test  hsgpa=hscalc=hsengl=0;
 225        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.07 seconds
       user cpu time       0.08 seconds
       system cpu time     0.00 seconds
       memory              2548.78k
       OS Memory           34240.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        44  Switch Count  2
       Page Faults                       0
       Page Reclaims                     266
       Page Swaps                        0
       Voluntary Context Switches        18
       Involuntary Context Switches      2
       Block Input Operations            0
       Block Output Operations           96
       
 
 226        proc iml;
 NOTE: IML Ready
 227             title3 'Proportion of remaining variation explained by diagnostic test';
 228             print "Precalc and calc controlling for hsgpa hscalc hsengl";
 229             n = 289;
 229      !               p = 6;
 229      !                      s = 2;
 229      !                             F = 8.28;
 230             a = s*F/(n-p + s*F);
 230      !                           print a;
 231        
 NOTE: Exiting IML.
 NOTE: PROCEDURE IML used (Total process time):
       real time           0.01 seconds
       user cpu time       0.01 seconds
       system cpu time     0.00 seconds
       memory              481.00k
       OS Memory           32420.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        45  Switch Count  1
       Page Faults                       0
       Page Reclaims                     133
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           8
       
 
 232        proc iml;
 NOTE: IML Ready
 233             title3 'Proportion of remaining variation explained by HS info';
 234             print "Hsgpa hscalc hsengl controlling for precalc and calc";
 235             n = 289;
 235      !               p = 6;
 235      !                      s = 3;
 235      !                             F = 46.97;
 236             a = s*F/(n-p + s*F);
 236      !                           print a;
 237        
 NOTE: Exiting IML.
 NOTE: PROCEDURE IML used (Total process time):
       real time           0.01 seconds
       user cpu time       0.01 seconds
       system cpu time     0.00 seconds
       memory              483.78k
       OS Memory           32420.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        46  Switch Count  1
       Page Faults                       0
       Page Reclaims                     133
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           0
       
 
 238        proc reg plots = none;
 239             title3 'Model D: See if Course makes a contribution';
 240             model grade = hsgpa hscalc hsengl precalc calc c1 c3;
 241             Course: test c1=c3=0;
 242             Diagnostic_Test:  test  precalc=calc=0;
 243        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.07 seconds
       user cpu time       0.08 seconds
       system cpu time     0.00 seconds
       memory              2550.53k
       OS Memory           34240.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        47  Switch Count  2
       Page Faults                       0
       Page Reclaims                     257
       Page Swaps                        0
       Voluntary Context Switches        23
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           80
       
 
 244        proc glm;
 245             title3 'Model D again with proc glm';
 246             class course;
 247             model grade =  hsgpa hscalc hsengl precalc calc course;
 248             contrast 'Replicate Test of Course' course 1 -1  0,
 249                                                 course 0  1 -1;
 250             contrast 'Diagnostic Test F = 9.06' precalc 1, calc 1;
 251        
 
 NOTE: PROCEDURE GLM used (Total process time):
       real time           0.06 seconds
       user cpu time       0.07 seconds
       system cpu time     0.00 seconds
       memory              1959.84k
       OS Memory           33720.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        48  Switch Count  3
       Page Faults                       0
       Page Reclaims                     346
       Page Swaps                        0
       Voluntary Context Switches        22
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           304
       
 
 252        proc reg plots = none;
 253             title3 'Model E: Include Language, Sex and Ethnic Background';
 254             model grade = hsgpa hscalc hsengl precalc calc
 255                           mtongue gender e1-e4 e6;
 256             TroubleVars: test mtongue=gender=e1=e2=e3=e4=e6=0;
 257             Nationality: test e1=e2=e3=e4=e6=0;
 258        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.08 seconds
       user cpu time       0.08 seconds
       system cpu time     0.01 seconds
       memory              2651.00k
       OS Memory           34496.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        49  Switch Count  2
       Page Faults                       0
       Page Reclaims                     320
       Page Swaps                        0
       Voluntary Context Switches        25
       Involuntary Context Switches      10
       Block Input Operations            0
       Block Output Operations           104
       
 
 259        proc reg plots = none;
 260             title3 'Model F: Discarding Gender and Nationality';
 261             model grade = hsgpa hscalc hsengl precalc calc mtongue;
 262             EnglishTongue: test hsengl=mtongue=0;
 263        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.06 seconds
       user cpu time       0.06 seconds
       system cpu time     0.00 seconds
       memory              2562.12k
       OS Memory           34496.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        50  Switch Count  2
       Page Faults                       0
       Page Reclaims                     264
       Page Swaps                        0
       Voluntary Context Switches        21
       Involuntary Context Switches      3
       Block Input Operations            0
       Block Output Operations           72
       
 
 264        proc iml;
 NOTE: IML Ready
 265             title3 'Proportion of remaining variation explained by mother tongue';
 266             print "Mtongue controlling for hsgpa hscalc hsengl precalc calc";
 267             n = 287;
 267      !               p = 7;
 267      !                      s = 1;
 267      !                             t = -2.23 ;
 267      !                                         F = t**2;
 268             a = s*F/(n-p + s*F);
 268      !                           print a;
 269        
 NOTE: Exiting IML.
 NOTE: PROCEDURE IML used (Total process time):
       real time           0.01 seconds
       user cpu time       0.01 seconds
       system cpu time     0.00 seconds
       memory              483.28k
       OS Memory           32676.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        51  Switch Count  1
       Page Faults                       0
       Page Reclaims                     133
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           0
       
 
 270        proc reg plots = none;
 271             title3 'Model G:  Drop mtongue and calc';
 272             title4 'Compare  R-Square = 0.4556, Adj R-Sq = 0.4460 From Model 3';
 273             model grade = hsgpa hscalc hsengl precalc;
 274        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.04 seconds
       user cpu time       0.04 seconds
       system cpu time     0.00 seconds
       memory              2546.62k
       OS Memory           34752.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        52  Switch Count  3
       Page Faults                       0
       Page Reclaims                     293
       Page Swaps                        0
       Voluntary Context Switches        34
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           56
       
 
 275        proc iml;
 NOTE: IML Ready
 276             title3 'Proportion of remaining variation explained by Pre-calculus';
 277             print "precalc controlling for hsgpa hscalc hsengl";
 278             n = 289;
 278      !               p = 5;
 278      !                      s = 1;
 278      !                             t = 3.63 ;
 278      !                                        F = t**2;
 279             a = s*F/(n-p + s*F);
 279      !                           print a;
 280        
 NOTE: Exiting IML.
 NOTE: PROCEDURE IML used (Total process time):
       real time           0.01 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              476.78k
       OS Memory           32932.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        53  Switch Count  1
       Page Faults                       0
       Page Reclaims                     133
       Page Swaps                        0
       Voluntary Context Switches        9
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           24
       
 
 281        proc reg plots = none;
 282             title3 'Model H: Combine precalc and calc instead of dropping calc';
 283             title4 'Compare  R-Square = 0.4492 from Model G';
 284             model grade = hsgpa hscalc hsengl totscore;
 285        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.04 seconds
       user cpu time       0.04 seconds
       system cpu time     0.00 seconds
       memory              2544.71k
       OS Memory           34752.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        54  Switch Count  3
       Page Faults                       0
       Page Reclaims                     259
       Page Swaps                        0
       Voluntary Context Switches        33
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           48
       
 
 286        proc iml;
 NOTE: IML Ready
 287             title3 'Proportion of remaining variation explained by Pre-calculus';
 288             print "totscore controlling for hsgpa hscalc hsengl";
 289             n = 289;
 289      !               p = 5;
 289      !                      s = 1;
 289      !                             t = 3.92 ;
 289      !                                        F = t**2;
 290             a = s*F/(n-p + s*F);
 290      !                           print a;
 291             print "For prediction, I am happy with Model H: hsgpa hscalc hsengl totscore";
 292        
 NOTE: Exiting IML.
 NOTE: PROCEDURE IML used (Total process time):
       real time           0.01 seconds
       user cpu time       0.01 seconds
       system cpu time     0.00 seconds
       memory              528.50k
       OS Memory           32932.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        55  Switch Count  1
       Page Faults                       0
       Page Reclaims                     133
       Page Swaps                        0
       Voluntary Context Switches        9
       Involuntary Context Switches      1
       Block Input Operations            0
       Block Output Operations           24
       
 
 293        proc reg plots = none;
 294             title3 'Model I: Same as Model H but including Mother Tongue';
 295             model grade = hsgpa hscalc hsengl totscore mtongue;
 296        /* A slightly better model except for the lawsuit. */
 297        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.04 seconds
       user cpu time       0.04 seconds
       system cpu time     0.00 seconds
       memory              2550.81k
       OS Memory           34752.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        56  Switch Count  2
       Page Faults                       0
       Page Reclaims                     261
       Page Swaps                        0
       Voluntary Context Switches        23
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           48
       
 
 298        proc reg plots = none;
 299             title3 'Try automatic (stepwise) selection';
 300             model grade = hsgpa hscalc hsengl precalc calc totscore
 301                           mtongue gender e1-e4 e6
 302                           / selection = stepwise slentry = 0.05 slstay = 0.05 ;
 303                           /* Default slentry = slstay = 0.15 */
 304        quit;
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.15 seconds
       user cpu time       0.15 seconds
       system cpu time     0.00 seconds
       memory              2635.15k
       OS Memory           34752.00k
       Timestamp           02/03/2020 05:33:49 PM
       Step Count                        57  Switch Count  2
       Page Faults                       0
       Page Reclaims                     269
       Page Swaps                        0
       Voluntary Context Switches        20
       Involuntary Context Switches      12
       Block Input Operations            0
       Block Output Operations           120
       
 
 305        
 306        
 307        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 318