1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 72         
 73         /* mathreg1.sas */
 74         title2 'Regression on the math data: Part One';
 75         %include '/home/u1407221/441s24/SAS06/ReadLabelMath.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              257.46k
       OS Memory           28836.00k
       Timestamp           02/14/2024 07:29:58 PM
       Step Count                        108  Switch Count  0
       Page Faults                       0
       Page Reclaims                     20
       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=10Feb2024:16:04:10,
       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 121:24   
 NOTE: The data set WORK.MATH has 1158 observations and 26 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.02 seconds
       user cpu time       0.00 seconds
       system cpu time     0.00 seconds
       memory              989.34k
       OS Memory           29608.00k
       Timestamp           02/14/2024 07:29:58 PM
       Step Count                        109  Switch Count  2
       Page Faults                       0
       Page Reclaims                     136
       Page Swaps                        0
       Voluntary Context Switches        18
       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.REPLIC has 579 observations and 26 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              1127.96k
       OS Memory           29868.00k
       Timestamp           02/14/2024 07:29:58 PM
       Step Count                        110  Switch Count  2
       Page Faults                       0
       Page Reclaims                     124
       Page Swaps                        0
       Voluntary Context Switches        13
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           264
       
 
 
 NOTE: There were 1158 observations read from the data set WORK.MATH.
 NOTE: The data set WORK.EXPLORE has 579 observations and 17 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              1138.81k
       OS Memory           29868.00k
       Timestamp           02/14/2024 07:29:58 PM
       Step Count                        111  Switch Count  2
       Page Faults                       0
       Page Reclaims                     109
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           264
       
 
 198        
 199        /* id sex tongue rater1 rater2 ethnic
 200              hsgpa hscalc hsengl havecalc
 201              class precalc calc totscore grade passed outcome */
 202        
 203        data dummy; /* Define dummy variables here, for now.
 204                       Later move them to ReadLabelMath.sas.   */
 205             set explore;
 206        /* Dummy variables for ethnic background */
 207        if ethnic=. then e1=.;
 208           else if ethnic=1 then e1=1;
 209           else e1=0;
 210        if ethnic=. then e2=.;
 211           else if ethnic=2 then e2=1;
 212           else e2=0;
 213        if ethnic=. then e3=.;
 214           else if ethnic=3 then e3=1;
 215           else e3=0;
 216        if ethnic=. then e4=.;
 217           else if ethnic=4 then e4=1;
 218           else e4=0;
 219        if ethnic=. then e6=.;
 220           else if ethnic=6 then e6=1;
 221           else e6=0;
 222        
 223        label e1 = 'Asian vs East Ind.'
 224                  e2 = 'East Eur. vs East Ind.'
 225                  e3 = 'Other Eur. vs East Ind.'
 226                  e4 = 'Mid. East & Pak. vs East Ind.'
 227                  e6 = 'Other/DK vs East Ind.';
 228        
 229        if sex = 'Female' then gender=1; else if sex = 'Male' then gender=0;
 230        if tongue = 'English' then mtongue=1; else if tongue='Other' then mtongue=0;
 231        label mtongue = 'English vs. Other';
 232        /* Only use 2 of these if the model has an intercept! */
 233        if class=. then c1=.; else if class=1 then c1=1; else c1=0;
 234        if class=. then c2=.; else if class=2 then c2=1; else c2=0;
 235        if class=. then c3=.; else if class=3 then c3=1; else c3=0;
 236        label c1 = 'Catch-up' c2 = 'Mainstream' c3 = 'Elite';
 237        
 238        /* Commented out
 239        proc freq;
 240             title3 'Check dummy variables';
 241             tables sex*gender / norow nocol nopercent missing;
 242             tables tongue*mtongue / norow nocol nopercent missing;
 243             tables (e1-e4 e6) * ethnic / norow nocol nopercent missing;
 244             tables (c1-c3) * class / norow nocol nopercent missing;
 245        */
 246        
 
 NOTE: There were 579 observations read from the data set WORK.EXPLORE.
 NOTE: The data set WORK.DUMMY has 579 observations and 27 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              1133.09k
       OS Memory           29868.00k
       Timestamp           02/14/2024 07:29:58 PM
       Step Count                        112  Switch Count  2
       Page Faults                       0
       Page Reclaims                     97
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 247        proc reg plots=none corr data=dummy; /* Suppress diagnostic plots for now*/
 248             title3 'Model A: Predict University Calculus Grade from HS Information';
 249             model grade = hsgpa hscalc hsengl;
 250        
 251        /* It is very interesting to know what proportion of the remaining
 252           variation is explained by each variable, controlling for the other two.
 253           F = t-squared, and
 254                               a = sF/(n-p + sF)
 255        */
 256        
 
 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              5057.93k
       OS Memory           31680.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        113  Switch Count  2
       Page Faults                       0
       Page Reclaims                     415
       Page Swaps                        0
       Voluntary Context Switches        14
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           80
       
 
 257        proc iml;
 NOTE: IML Ready
 258             title3 'Proportion of remaining variation for HS information';
 259             n = 323;
 259      !               p = 4;
 259      !                      s = 1;
 260             print "hsgpa controlling for hscalc and hsengl";
 261             t = 8.00;
 261      !                F = t**2;
 261      !                           a = s*F/(n-p + s*F);
 262             print a;
 263        
 264             print "hscalc controlling for hsgpa and hsengl";
 265             t = 3.14;
 265      !                F = t**2;
 265      !                           a = s*F/(n-p + s*F);
 266             print a;
 267        
 268             print "hsengl controlling for hsgpa and hscalc";
 269             t = -3.26;
 269      !                 F = t**2;
 269      !                            a = s*F/(n-p + s*F);
 270             print a;
 271        
 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              543.46k
       OS Memory           30116.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        114  Switch Count  1
       Page Faults                       0
       Page Reclaims                     58
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           8
       
 
 272        proc reg plots = none;
 273             title3 'Model B: Predict University Calculus Grade from Diagnostic Test';
 274             model grade = precalc calc;
 275        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.03 seconds
       user cpu time       0.04 seconds
       system cpu time     0.00 seconds
       memory              2551.12k
       OS Memory           31936.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        115  Switch Count  2
       Page Faults                       0
       Page Reclaims                     273
       Page Swaps                        0
       Voluntary Context Switches        23
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           48
       
 
 276        proc reg plots = none;
 277             title3 'Making a mistake on purpose';
 278             model grade = totscore precalc calc;
 279        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.03 seconds
       user cpu time       0.04 seconds
       system cpu time     0.00 seconds
       memory              2605.12k
       OS Memory           32192.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        116  Switch Count  2
       Page Faults                       0
       Page Reclaims                     321
       Page Swaps                        0
       Voluntary Context Switches        19
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           72
       
 
 280        proc reg plots = none;
 281             title3 'Model C: Do the diagnostic test and HS info both contribute?';
 282             model grade = hsgpa hscalc hsengl precalc calc;
 283             Diagnostic_Test:  test  precalc=calc=0;
 284             HS_Information:   test  hsgpa=hscalc=hsengl=0;
 285        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.05 seconds
       user cpu time       0.06 seconds
       system cpu time     0.00 seconds
       memory              2609.37k
       OS Memory           32192.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        117  Switch Count  2
       Page Faults                       0
       Page Reclaims                     261
       Page Swaps                        0
       Voluntary Context Switches        17
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           88
       
 
 286        proc iml;
 NOTE: IML Ready
 287             title3 'Proportion of remaining variation explained by diagnostic test';
 288             print "Precalc and calc controlling for hsgpa hscalc hsengl";
 289             n = 289;
 289      !               p = 6;
 289      !                      s = 2;
 289      !                             F = 8.28;
 290             a = s*F/(n-p + s*F);
 290      !                           print a;
 291        
 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              543.56k
       OS Memory           30372.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        118  Switch Count  1
       Page Faults                       0
       Page Reclaims                     57
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           16
       
 
 292        proc iml;
 NOTE: IML Ready
 293             title3 'Proportion of remaining variation explained by HS info';
 294             print "Hsgpa hscalc hsengl controlling for precalc and calc";
 295             n = 289;
 295      !               p = 6;
 295      !                      s = 3;
 295      !                             F = 46.97;
 296             a = s*F/(n-p + s*F);
 296      !                           print a;
 297        
 NOTE: Exiting IML.
 NOTE: PROCEDURE IML used (Total process time):
       real time           0.00 seconds
       user cpu time       0.01 seconds
       system cpu time     0.01 seconds
       memory              499.03k
       OS Memory           30372.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        119  Switch Count  1
       Page Faults                       0
       Page Reclaims                     55
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           8
       
 
 298        proc reg plots = none;
 299             title3 'Model D: See if class makes a contribution';
 300             model grade = hsgpa hscalc hsengl precalc calc c1 c3;
 301             class: test c1=c3=0;
 302             Diagnostic_Test:  test  precalc=calc=0;
 303        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.05 seconds
       user cpu time       0.06 seconds
       system cpu time     0.00 seconds
       memory              2616.81k
       OS Memory           32192.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        120  Switch Count  2
       Page Faults                       0
       Page Reclaims                     260
       Page Swaps                        0
       Voluntary Context Switches        22
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           72
       
 
 304        proc glm;
 305             title3 'Model D again with proc glm';
 306             class class;
 307             model grade =  hsgpa hscalc hsengl precalc calc class;
 308             contrast 'Replicate Test of Class' class 1 -1  0,
 309                                                class 0  1 -1;
 310             contrast 'Diagnostic Test F = 9.06' precalc 1, calc 1;
 311        
 
 NOTE: PROCEDURE GLM used (Total process time):
       real time           0.05 seconds
       user cpu time       0.05 seconds
       system cpu time     0.00 seconds
       memory              1981.43k
       OS Memory           31672.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        121  Switch Count  3
       Page Faults                       0
       Page Reclaims                     224
       Page Swaps                        0
       Voluntary Context Switches        24
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           312
       
 
 312        proc reg plots = none;
 313             title3 'Model E: Include Language, Sex and Ethnic Background';
 314             model grade = hsgpa hscalc hsengl precalc calc
 315                           mtongue gender e1-e4 e6;
 316             TroubleVars: test mtongue=gender=e1=e2=e3=e4=e6=0;
 317             Nationality: test e1=e2=e3=e4=e6=0;
 318        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.06 seconds
       user cpu time       0.06 seconds
       system cpu time     0.01 seconds
       memory              2700.75k
       OS Memory           32448.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        122  Switch Count  2
       Page Faults                       0
       Page Reclaims                     319
       Page Swaps                        0
       Voluntary Context Switches        25
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           80
       
 
 319        proc reg plots = none;
 320             title3 'Model F: Discarding Gender and Nationality';
 321             model grade = hsgpa hscalc hsengl precalc calc mtongue;
 322             EnglishTongue: test hsengl=mtongue=0;
 323        
 
 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              2550.09k
       OS Memory           32704.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        123  Switch Count  2
       Page Faults                       0
       Page Reclaims                     289
       Page Swaps                        0
       Voluntary Context Switches        17
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           136
       
 
 324        proc iml;
 NOTE: IML Ready
 325             title3 'Proportion of remaining variation explained by mother tongue';
 326             print "Mtongue controlling for hsgpa hscalc hsengl precalc calc";
 327             n = 287;
 327      !               p = 7;
 327      !                      s = 1;
 327      !                             t = -2.23 ;
 327      !                                         F = t**2;
 328             a = s*F/(n-p + s*F);
 328      !                           print a;
 329        
 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              528.12k
       OS Memory           30884.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        124  Switch Count  1
       Page Faults                       0
       Page Reclaims                     57
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           24
       
 
 330        proc reg plots = none;
 331             title3 'Model G:  Drop mtongue and calc';
 332             title4 'Compare  R-Square = 0.4556, Adj R-Sq = 0.4460 From Model 3';
 333             model grade = hsgpa hscalc hsengl precalc;
 334        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.03 seconds
       user cpu time       0.03 seconds
       system cpu time     0.00 seconds
       memory              2537.59k
       OS Memory           32704.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        125  Switch Count  3
       Page Faults                       0
       Page Reclaims                     260
       Page Swaps                        0
       Voluntary Context Switches        29
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           48
       
 
 335        proc iml;
 NOTE: IML Ready
 336             title3 'Proportion of remaining variation explained by Pre-calculus';
 337             print "precalc controlling for hsgpa hscalc hsengl";
 338             n = 289;
 338      !               p = 5;
 338      !                      s = 1;
 338      !                             t = 3.63 ;
 338      !                                        F = t**2;
 339             a = s*F/(n-p + s*F);
 339      !                           print a;
 340        
 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              500.40k
       OS Memory           30884.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        126  Switch Count  1
       Page Faults                       0
       Page Reclaims                     57
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           8
       
 
 341        proc reg plots = none;
 342             title3 'Model H: Combine precalc and calc instead of dropping calc';
 343             title4 'Compare  R-Square = 0.4492 from Model G';
 344             model grade = hsgpa hscalc hsengl totscore;
 345        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.03 seconds
       user cpu time       0.03 seconds
       system cpu time     0.00 seconds
       memory              2536.25k
       OS Memory           32704.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        127  Switch Count  3
       Page Faults                       0
       Page Reclaims                     260
       Page Swaps                        0
       Voluntary Context Switches        28
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           64
       
 
 346        proc iml;
 NOTE: IML Ready
 347             title3 'Proportion of remaining variation explained by Pre-calculus';
 348             print "totscore controlling for hsgpa hscalc hsengl";
 349             n = 289;
 349      !               p = 5;
 349      !                      s = 1;
 349      !                             t = 3.92 ;
 349      !                                        F = t**2;
 350             a = s*F/(n-p + s*F);
 350      !                           print a;
 351             print "For prediction, I am happy with Model H: hsgpa hscalc hsengl totscore";
 352        
 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              500.62k
       OS Memory           30884.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        128  Switch Count  1
       Page Faults                       0
       Page Reclaims                     57
       Page Swaps                        0
       Voluntary Context Switches        11
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           16
       
 
 353        proc reg plots = none;
 354             title3 'Model I: Same as Model H but including Mother Tongue';
 355             model grade = hsgpa hscalc hsengl totscore mtongue;
 356        /* A slightly better model except for the lawsuit. */
 357        
 358        /* For stepwise selection, note Mallow's Cp is Cp = SSE_p/MSE_F - n + 2(p+1)
 359           Small is good. */
 360        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.03 seconds
       user cpu time       0.03 seconds
       system cpu time     0.00 seconds
       memory              2541.90k
       OS Memory           32704.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        129  Switch Count  2
       Page Faults                       0
       Page Reclaims                     259
       Page Swaps                        0
       Voluntary Context Switches        18
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           64
       
 
 361        proc reg plots = none;
 362             title3 'Try automatic (stepwise) selection';
 363             model grade = hsgpa hscalc hsengl precalc calc totscore
 364                           mtongue gender e1-e4 e6
 365                           / selection = stepwise slentry = 0.05 slstay = 0.05 ;
 366                           /* Default slentry = slstay = 0.15 */
 367        quit;
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.12 seconds
       user cpu time       0.12 seconds
       system cpu time     0.00 seconds
       memory              2575.09k
       OS Memory           32960.00k
       Timestamp           02/14/2024 07:29:59 PM
       Step Count                        130  Switch Count  2
       Page Faults                       0
       Page Reclaims                     315
       Page Swaps                        0
       Voluntary Context Switches        21
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           120
       
 
 368        
 369        
 370        
 371        
 372        
 373        
 374        
 375        
 376        
 377        
 378        
 379        
 380        
 381        
 382        
 383        
 384        
 385        
 386        
 387        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 399