1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 70         
 71         /* MathReg3.sas  */
 72         %include '/home/brunner0/441s20/readexplor.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           30884.00k
       Timestamp           02/01/2020 08:40:44 PM
       Step Count                        119  Switch Count  0
       Page Faults                       0
       Page Reclaims                     29
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           32
       
 
 189                 /* Creates data table explore */
 190        %include '/home/brunner0/441s20/readreplic.sas';
 
 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 98:24    99 at 134:18   
 NOTE: The data set WORK.EXPLORE 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              1014.21k
       OS Memory           31656.00k
       Timestamp           02/01/2020 08:40:44 PM
       Step Count                        120  Switch Count  3
       Page Faults                       0
       Page Reclaims                     158
       Page Swaps                        0
       Voluntary Context Switches        25
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 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              273.84k
       OS Memory           31396.00k
       Timestamp           02/01/2020 08:40:44 PM
       Step Count                        121  Switch Count  0
       Page Faults                       0
       Page Reclaims                     14
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           0
       
 
 303                 /* Creates data table replic  */
 304        title2 'Predict Grade for Replication Sample';
 305        
 306        /* Plan:
 307        
 308        1. Non-obvious findings from the exploration (based on Model I,
 309            which predicts grade from hsgpa hscalc hsengl totscore mtongue) were
 310              a. HS Engl neg
 311              b. mtongue neg
 312              c. totscore positive (diagnostic test matters)
 313           Test these on the replication with a Bonferroni correction for 3 tests.
 314           The other two results (HS GPA and HS Calculus) were obvious.
 315        
 316        2. See if prediction intervals work as advertised for Model H, which
 317           predicts grade from hsgpa hscalc hsengl totscore.
 318        
 319        3. Compare prediction of letter grade for the models with and without
 320           the diagnostic test.
 321        
 322        
 323        First, just illustrate use of different data tables in the same run.  */
 324        
 
 NOTE: The infile '/home/brunner0/441s20/replicmath.data.txt' is:
       Filename=/home/brunner0/441s20/replicmath.data.txt,
       Owner Name=brunner0,Group Name=oda,
       Access Permission=-rw-r--r--,
       Last Modified=26Jan2020:18:49:13,
       File Size (bytes)=38214
 
 NOTE: 579 records were read from the infile '/home/brunner0/441s20/replicmath.data.txt'.
       The minimum record length was 64.
       The maximum record length was 64.
 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).
       81 at 218:24   81 at 254:18   
 NOTE: The data set WORK.REPLIC 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              924.90k
       OS Memory           31656.00k
       Timestamp           02/01/2020 08:40:44 PM
       Step Count                        122  Switch Count  3
       Page Faults                       0
       Page Reclaims                     92
       Page Swaps                        0
       Voluntary Context Switches        22
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 325        proc freq data = explore;
 326             title3 'Exploratory Sample';
 327             tables outcome;
 
 NOTE: There were 579 observations read from the data set WORK.EXPLORE.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.03 seconds
       user cpu time       0.03 seconds
       system cpu time     0.00 seconds
       memory              2760.93k
       OS Memory           32172.00k
       Timestamp           02/01/2020 08:40:44 PM
       Step Count                        123  Switch Count  3
       Page Faults                       0
       Page Reclaims                     211
       Page Swaps                        0
       Voluntary Context Switches        16
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           272
       
 
 328        proc freq data = replic;
 329             title3 'Replication Sample';
 330             tables outcome;
 331        
 332        /* Now test the three findings: Point 1 above */
 333        
 
 NOTE: There were 579 observations read from the data set WORK.REPLIC.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.01 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              977.12k
       OS Memory           32428.00k
       Timestamp           02/01/2020 08:40:44 PM
       Step Count                        124  Switch Count  3
       Page Faults                       0
       Page Reclaims                     185
       Page Swaps                        0
       Voluntary Context Switches        21
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           264
       
 
 334        proc reg data = replic  plots = none;
 335             title3 'Try to replicate HS Engl neg, mtongue neg, totscore pos';
 336             title4 'with a Bonferroni correction (check p < 0.05/3 = 0.01666667)';
 337             model grade = hsgpa hscalc hsengl totscore mtongue;
 338        
 339        /* Make combined data table, look at prediction intervals: Point 2 */
 340        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.05 seconds
       user cpu time       0.05 seconds
       system cpu time     0.01 seconds
       memory              2711.15k
       OS Memory           33984.00k
       Timestamp           02/01/2020 08:40:44 PM
       Step Count                        125  Switch Count  3
       Page Faults                       0
       Page Reclaims                     297
       Page Swaps                        0
       Voluntary Context Switches        32
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           64
       
 
 341        data predict;
 342             set explore replic;
 343             keeper =  grade+hsgpa+hscalc+hsengl+totscore;
 344             /* keeper will be missing if any of the vars are missing */
 345             if keeper ne .; /* Discards all other cases */
 346             grade2 = grade; /* Save value of grade for future use */
 347             if sample=2 then grade=. ;
 348             /* Response variable is now missing for replication sample.
 349                But it is preserved in grade2 */
 350        
 
 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).
       486 at 343:21   21 at 343:27    4 at 343:34     65 at 343:41    
 NOTE: There were 579 observations read from the data set WORK.EXPLORE.
 NOTE: There were 579 observations read from the data set WORK.REPLIC.
 NOTE: The data set WORK.PREDICT has 582 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              1820.68k
       OS Memory           32944.00k
       Timestamp           02/01/2020 08:40:44 PM
       Step Count                        126  Switch Count  2
       Page Faults                       0
       Page Reclaims                     132
       Page Swaps                        0
       Voluntary Context Switches        12
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 351        proc reg plots = none   data = predict;
 352                             /* Data table predict is the default anyway */
 353             title3 'Model H: hsgpa hscalc hsengl totscore: R-sq = 0.4532';
 354             model grade = hsgpa hscalc hsengl totscore;
 355             output out = predataH   predicted = Yhat
 356                                     L95       = lowpred
 357                                     U95       = hipred;
 358             /* Data table predataH has everything in predict plus
 359                Yhat and the lower and upper 95% prediction limits. */
 360        
 
 NOTE: The data set WORK.PREDATAH has 582 observations and 40 variables.
 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              3133.56k
       OS Memory           34244.00k
       Timestamp           02/01/2020 08:40:44 PM
       Step Count                        127  Switch Count  4
       Page Faults                       0
       Page Reclaims                     344
       Page Swaps                        0
       Voluntary Context Switches        40
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           576
       
 
 361        proc print;
 362             title3 'Look at predictions for the replication sample';
 363             var id sample grade2 Yhat lowpred hipred;
 364             where sample = 2;
 365        /* Should predicted marks be used to advise students? */
 366        
 367        /* Does 95 Percent Prediction Interval really contain 95 percent of grades?
 368           Recall that the data fail all tests for normality, and the prediction
 369           intervals are based on normal theory.  */
 370        
 
 NOTE: There were 293 observations read from the data set WORK.PREDATAH.
       WHERE sample=2;
 NOTE: PROCEDURE PRINT used (Total process time):
       real time           0.41 seconds
       user cpu time       0.42 seconds
       system cpu time     0.00 seconds
       memory              1754.50k
       OS Memory           32940.00k
       Timestamp           02/01/2020 08:40:45 PM
       Step Count                        128  Switch Count  6
       Page Faults                       0
       Page Reclaims                     172
       Page Swaps                        0
       Voluntary Context Switches        27
       Involuntary Context Switches      1
       Block Input Operations            0
       Block Output Operations           248
       
 
 371        data predictB;
 372             set predataH;
 373             if (lowpred < grade2 < hipred) then ininterval='Yes';
 374                else ininterval='No';
 375        
 
 NOTE: There were 582 observations read from the data set WORK.PREDATAH.
 NOTE: The data set WORK.PREDICTB has 582 observations and 41 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              1349.25k
       OS Memory           33196.00k
       Timestamp           02/01/2020 08:40:45 PM
       Step Count                        129  Switch Count  2
       Page Faults                       0
       Page Reclaims                     99
       Page Swaps                        0
       Voluntary Context Switches        14
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 376        proc freq;
 377             title3 'Does 95 Percent Prediction Interval Work?';
 378             tables sample * ininterval / nocol nopercent;
 379        
 380        /* Keep trying. Try to predict letter grade. */
 381        
 
 NOTE: There were 582 observations read from the data set WORK.PREDICTB.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.02 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              1396.90k
       OS Memory           33456.00k
       Timestamp           02/01/2020 08:40:45 PM
       Step Count                        130  Switch Count  5
       Page Faults                       0
       Page Reclaims                     219
       Page Swaps                        0
       Voluntary Context Switches        38
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           536
       
 
 382        data predictC;
 383             set predictB;
 384             if         80 <= grade2 <= 100 then lgrade = 'A';
 385                else if 70 <= grade2 <=  79 then lgrade = 'B';
 386                else if 60 <= grade2 <=  69 then lgrade = 'C';
 387                else if 50 <= grade2 <=  59 then lgrade = 'D';
 388                else if  0 <= grade2 <=  49 then lgrade = 'F';
 389             label lgrade = 'Letter Grade';
 390             pregrade = round(Yhat);
 391             if         80 <= pregrade <= 100 then prelgrade = 'A';
 392                else if 70 <= pregrade <=  79 then prelgrade = 'B';
 393                else if 60 <= pregrade <=  69 then prelgrade = 'C';
 394                else if 50 <= pregrade <=  59 then prelgrade = 'D';
 395                else if  0 <= pregrade <=  49 then prelgrade = 'F';
 396             label prelgrade = 'Predicted Letter Grade';
 397        
 
 NOTE: There were 582 observations read from the data set WORK.PREDICTB.
 NOTE: The data set WORK.PREDICTC has 582 observations and 44 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              1368.81k
       OS Memory           33196.00k
       Timestamp           02/01/2020 08:40:45 PM
       Step Count                        131  Switch Count  2
       Page Faults                       0
       Page Reclaims                     102
       Page Swaps                        0
       Voluntary Context Switches        17
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 398        proc freq;
 399             title3 'Accuracy of predicting Letter Grades From Model H';
 400             tables sample*prelgrade*lgrade / nocol nopercent;
 401             /* Will yield separate table for each sample. */
 402        
 403        /* Predict grade for a new student with hsgpa=80 hscalc=90 hsengl=70
 404           totscore=15. For just a prediction (no interval), proc glm is easier. */
 405        
 
 NOTE: There were 582 observations read from the data set WORK.PREDICTC.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.08 seconds
       user cpu time       0.09 seconds
       system cpu time     0.00 seconds
       memory              1345.62k
       OS Memory           33456.00k
       Timestamp           02/01/2020 08:40:45 PM
       Step Count                        132  Switch Count  5
       Page Faults                       0
       Page Reclaims                     213
       Page Swaps                        0
       Voluntary Context Switches        38
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           560
       
 
 406        proc glm data = explore;
 407             model grade = hsgpa hscalc hsengl totscore;
 408             estimate 'New Student' intercept 1  hsgpa 80  hscalc 90  hsengl 70
 409                                    totscore 15;
 410        
 411        /* Prediction for Y_{n+1} is the same as estimate of E[Y|X]. CI from proc glm
 412           is for E[Y|X]. PREDICTION interval for Y_{n+1} is wider. */
 413        
 
 NOTE: PROCEDURE GLM used (Total process time):
       real time           0.09 seconds
       user cpu time       0.10 seconds
       system cpu time     0.00 seconds
       memory              1961.28k
       OS Memory           33976.00k
       Timestamp           02/01/2020 08:40:45 PM
       Step Count                        133  Switch Count  2
       Page Faults                       0
       Page Reclaims                     221
       Page Swaps                        0
       Voluntary Context Switches        13
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           312
       
 
 414        data student;
 415             hsgpa=80; hscalc=90; hsengl=70; totscore=15; id = -27;
 416        
 
 NOTE: The data set WORK.STUDENT has 1 observations and 5 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              609.25k
       OS Memory           33192.00k
       Timestamp           02/01/2020 08:40:45 PM
       Step Count                        134  Switch Count  2
       Page Faults                       0
       Page Reclaims                     92
       Page Swaps                        0
       Voluntary Context Switches        14
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           264
       
 
 417        data together;
 418             set explore student;
 419             /* All variables not assigned will be missing for observation -27 */
 420        
 
 NOTE: There were 579 observations read from the data set WORK.EXPLORE.
 NOTE: There were 1 observations read from the data set WORK.STUDENT.
 NOTE: The data set WORK.TOGETHER has 580 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              1624.78k
       OS Memory           33712.00k
       Timestamp           02/01/2020 08:40:45 PM
       Step Count                        135  Switch Count  2
       Page Faults                       0
       Page Reclaims                     132
       Page Swaps                        0
       Voluntary Context Switches        15
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 421        proc reg plots = none;
 422             title3 'Model H: hsgpa hscalc hsengl totscore: R-sq = 0.4532';
 423             model grade = hsgpa hscalc hsengl totscore;
 424             output out = guess      predicted = PredictedY
 425                                     L95       = LowerLimit
 426                                     U95       = UpperLimit;
 427        
 
 NOTE: The data set WORK.GUESS has 580 observations and 38 variables.
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.05 seconds
       user cpu time       0.05 seconds
       system cpu time     0.00 seconds
       memory              3151.62k
       OS Memory           35524.00k
       Timestamp           02/01/2020 08:40:45 PM
       Step Count                        136  Switch Count  4
       Page Faults                       0
       Page Reclaims                     340
       Page Swaps                        0
       Voluntary Context Switches        30
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           592
       
 
 428        data newguess;
 429             set guess;
 430             if id < 0; /* Discard all other cases */
 431        
 
 NOTE: There were 580 observations read from the data set WORK.GUESS.
 NOTE: The data set WORK.NEWGUESS has 1 observations and 38 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              1184.46k
       OS Memory           33964.00k
       Timestamp           02/01/2020 08:40:45 PM
       Step Count                        137  Switch Count  2
       Page Faults                       0
       Page Reclaims                     122
       Page Swaps                        0
       Voluntary Context Switches        15
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           264
       
 
 432        proc print;
 433             title3 'hsgpa=80 hscalc=90 hsengl=70 totscore=15';
 434             var predictedY LowerLimit UpperLimit;
 435        quit;
 
 NOTE: There were 1 observations read from the data set WORK.NEWGUESS.
 NOTE: PROCEDURE PRINT used (Total process time):
       real time           0.01 seconds
       user cpu time       0.01 seconds
       system cpu time     0.01 seconds
       memory              772.15k
       OS Memory           33704.00k
       Timestamp           02/01/2020 08:40:45 PM
       Step Count                        138  Switch Count  1
       Page Faults                       0
       Page Reclaims                     72
       Page Swaps                        0
       Voluntary Context Switches        9
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           8
       
 
 436        
 437        
 438        
 439        
 440        
 441        
 442        
 443        
 444        
 445        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 456