1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 NOTE: ODS statements in the SAS Studio environment may disable some output features.
 71         
 72         /* mathlogreg1.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              244.40k
       OS Memory           29860.00k
       Timestamp           02/05/2020 04:53:34 PM
       Step Count                        151  Switch Count  0
       Page Faults                       0
       Page Reclaims                     25
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           32
       
 
 177        
 
 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 34 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              897.18k
       OS Memory           30376.00k
       Timestamp           02/05/2020 04:53:34 PM
       Step Count                        152  Switch Count  2
       Page Faults                       0
       Page Reclaims                     111
       Page Swaps                        0
       Voluntary Context Switches        18
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           520
       
 
 178        proc freq;
 179             title2 'Course by passed with proc freq';
 180             tables course2 * passed / nocol nopercent chisq;
 181        /* Note 'No resp' is missing for course2 */
 182        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.05 seconds
       user cpu time       0.05 seconds
       system cpu time     0.00 seconds
       memory              3420.28k
       OS Memory           31408.00k
       Timestamp           02/05/2020 04:53:34 PM
       Step Count                        153  Switch Count  5
       Page Faults                       0
       Page Reclaims                     405
       Page Swaps                        0
       Voluntary Context Switches        26
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           536
       
 
 183        proc logistic;
 184             title2 'Course by passed with dummy vars: Compare LR Chisq = 34.4171';
 185             model passed (event='Yes') = c1 c3; /* Omit c2 so Mainstream is reference category */
 186             /* Wald chi-squared tests */
 187             course:       test c1=c3=0;
 188             Course1_vs_2: test c1=0;
 189             Course1_vs_3: test c1=c3;
 190             Course2_vs_3: test c3=0;
 191        
 192        /*
 193        Question: The estimated odds of passing the course are ___ times as great for a
 194                  student in the elite course, compared to a student in the mainstream course.
 195        
 196        Question: With 95% confidence, the chances of a student passing the catch-up
 197                  course are between ___% and ___% as great as the chances of passing the
 198                  mainstream course.
 199        
 200                  Note the deliberately vague but useful word "chances."
 201        
 202        A few details about the output :
 203        
 204             The higher the minus 2 Log Likelihood, the lower the (estimated) maximum
 205             probability of observing these responses. It is a meaure of lack of
 206             model fit. The Akaike information criterion and Schwarz's Bayesian
 207             criterion both impose a further penalty for number of explanatory
 208             variables. Small is good.
 209        
 210             "Association of Predicted Probabilities and Observed Responses":
 211                  * Every case has Y=0 or Y=1.
 212                  * Every case has a p-hat.
 213                  * Pick a case with Y=0, and another case with Y=1. That's a pair.
 214                  * If the case with Y=0 has a lower p-hat than the case with Y=1,
 215                    the pair is concordant.
 216        */
 217        
 
 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           0.08 seconds
       user cpu time       0.09 seconds
       system cpu time     0.00 seconds
       memory              2577.34k
       OS Memory           32952.00k
       Timestamp           02/05/2020 04:53:35 PM
       Step Count                        154  Switch Count  1
       Page Faults                       0
       Page Reclaims                     325
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           56
       
 
 218        proc iml;
 NOTE: IML Ready
 219             title2 'Estimate prob. of passing for for course=3: Compare 31/39 = 0.7949';
 220             b0 = 0.4077;
 220      !                   b1 = -1.4838;
 220      !                                 b2 = 0.9468;
 221             c1 = 0;
 221      !              c3=1;
 222             lcombo = b0 + b1*c1 + b2*c3;
 223             probpass = exp(lcombo) / (1+exp(lcombo));
 224             print "Estimated probability of passing course 3 (Elite) is " probpass;
 225        
 226        
 NOTE: Exiting IML.
 NOTE: PROCEDURE IML used (Total process time):
       real time           0.01 seconds
       user cpu time       0.01 seconds
       system cpu time     0.01 seconds
       memory              499.96k
       OS Memory           31908.00k
       Timestamp           02/05/2020 04:53:35 PM
       Step Count                        155  Switch Count  1
       Page Faults                       0
       Page Reclaims                     173
       Page Swaps                        0
       Voluntary Context Switches        7
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           24
       
 
 227        proc logistic;
 228             title2 'Use the class and contrast statements';
 229             class course2 / param=ref;  /* This param option makes the ALPHABETICALLY
 230                                            last category (Mainstream) the reference
 231                                            category. Default is effect coding. */
 232             model passed (event='Yes') = course2;
 233             contrast 'Catch-up vs Mainstream' course2  1  0;
 234             contrast 'Elite vs Mainstream' course2     0  1;
 235             contrast 'Catch-up vs Elite' course2       1 -1;
 236        
 237        /* Contrast is a little tricky in proc logistic compared to proc glm.
 238           It lets you specify a set of linear combinations of regression
 239           coefficients to test against zero. It is essential to know exactly
 240           what the dummy variable coding scheme is. This can still be more
 241           convenient than defining your own dummy variables in the data step. */
 242        
 
 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           0.09 seconds
       user cpu time       0.10 seconds
       system cpu time     0.00 seconds
       memory              2385.53k
       OS Memory           33208.00k
       Timestamp           02/05/2020 04:53:35 PM
       Step Count                        156  Switch Count  1
       Page Faults                       0
       Page Reclaims                     224
       Page Swaps                        0
       Voluntary Context Switches        9
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           56
       
 
 243        proc logistic;
 244             title2 'Course controlling for score on diagnostic test';
 245             class course2 / param=ref;
 246             model passed (event='Yes') = course2 totscore;
 247             contrast 'Course controlling for totscore' course2 1 0,
 248                                                        course2 0 1;
 249        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              2435.90k
       OS Memory           33208.00k
       Timestamp           02/05/2020 04:53:35 PM
       Step Count                        157  Switch Count  1
       Page Faults                       0
       Page Reclaims                     209
       Page Swaps                        0
       Voluntary Context Switches        10
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           80
       
 
 250        
 251        /* Estimate a probability of passing without typing in the
 252         * estimated regression coefficients: Use the Output Delivery
 253         * System (ODS). All the tables in a SAS results file have names.
 254         * You can find out what they are with a web search on
 255         * "proc logistic ods table names" , which will take you to the
 256         * manual. Easier is to do a preliminary run with ods trace on,
 257         * which writes the table names on the log file as they are produced.
 258         */
 259        
 260        ods trace on;
 261        proc logistic data=mathex;
 262             title2 'What are the ods table names?';
 263             model passed (event='Yes') = c1 c3 totscore;
 264        run;
 
 
 Output Added:
 -------------
 Name:       ModelInfo
 Label:      Model Information
 Template:   Stat.Logistic.ModelInfo
 Path:       Logistic.ModelInfo
 -------------
 
 Output Added:
 -------------
 Name:       NObs
 Label:      Observations Summary
 Template:   Stat.Logistic.NObs
 Path:       Logistic.NObs
 -------------
 
 Output Added:
 -------------
 Name:       ResponseProfile
 Label:      Response Profile
 Template:   Stat.Logistic.ResponseProfile
 Path:       Logistic.ResponseProfile
 -------------
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 
 Output Added:
 -------------
 Name:       ConvergenceStatus
 Label:      Convergence Status
 Template:   Stat.Logistic.MConvergenceStatus
 Path:       Logistic.ConvergenceStatus
 -------------
 NOTE: Convergence criterion (GCONV=1E-8) satisfied.
 
 Output Added:
 -------------
 Name:       FitStatistics
 Label:      Fit Statistics
 Template:   Stat.Logistic.FitStatistics
 Path:       Logistic.FitStatistics
 -------------
 
 Output Added:
 -------------
 Name:       GlobalTests
 Label:      Global Tests
 Template:   Stat.Logistic.GlobalTests
 Path:       Logistic.GlobalTests
 -------------
 
 Output Added:
 -------------
 Name:       ParameterEstimates
 Label:      Parameter Estimates
 Template:   Stat.Logistic.ParameterEstimates
 Path:       Logistic.ParameterEstimates
 -------------
 
 Output Added:
 -------------
 Name:       OddsRatios
 Label:      Odds Ratios
 Template:   Stat.Logistic.OddsRatios
 Path:       Logistic.OddsRatios
 -------------
 
 Output Added:
 -------------
 Name:       Association
 Label:      Association Statistics
 Template:   Stat.Logistic.Association
 Path:       Logistic.Association
 -------------
 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       0.08 seconds
       system cpu time     0.00 seconds
       memory              2353.96k
       OS Memory           33208.00k
       Timestamp           02/05/2020 04:53:35 PM
       Step Count                        158  Switch Count  1
       Page Faults                       0
       Page Reclaims                     201
       Page Swaps                        0
       Voluntary Context Switches        9
       Involuntary Context Switches      9
       Block Input Operations            0
       Block Output Operations           56
       
 
 264      !      /* Need run with ods trace */
 265        ods trace off;
 266        
 267        ods output ParameterEstimates = estimout;
 268        /* The ParameterEstimates table will be written to a SAS data
 269           set called estimout. */
 270        proc logistic data=mathex;
 271             title2 'Save parameter estimates using ods';
 272             model passed (event='Yes') = c1 c3 totscore;
 273        
 
 NOTE: PROC LOGISTIC is modeling the probability that passed='Yes'.
 NOTE: Convergence criterion (GCONV=1E-8) satisfied.
 NOTE: The data set WORK.ESTIMOUT has 4 observations and 7 variables.
 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       0.08 seconds
       system cpu time     0.00 seconds
       memory              2688.43k
       OS Memory           33468.00k
       Timestamp           02/05/2020 04:53:35 PM
       Step Count                        159  Switch Count  3
       Page Faults                       0
       Page Reclaims                     296
       Page Swaps                        0
       Voluntary Context Switches        25
       Involuntary Context Switches      1
       Block Input Operations            0
       Block Output Operations           328
       
 
 274        proc print data=estimout;
 275        
 
 NOTE: There were 4 observations read from the data set WORK.ESTIMOUT.
 NOTE: PROCEDURE PRINT used (Total process time):
       real time           0.01 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              670.34k
       OS Memory           32424.00k
       Timestamp           02/05/2020 04:53:35 PM
       Step Count                        160  Switch Count  0
       Page Faults                       0
       Page Reclaims                     62
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           8
       
 
 276        proc iml;
 NOTE: IML Ready
 277             title2 'Estimated Probabilty of Passing';
 278             use estimout;
 279             read all var {Estimate} into b;
 280             print "Estimated regression coefficients";
 281             print b;
 282             /* Student in the catch-up class who got 10 right out of 20 */
 283             x1 = {1, 1, 0, 10};
 283      !                          /* Rows are separated by commas */
 284             pihat1 = exp(x1`*b)/(1+exp(x1`*b));
 285             print "Student in the catch-up class who got 10 right out of 20" pihat1;
 286             /* Student in the elite class who got all 20 right */
 287             x2 = {1, 0, 1, 20};
 287      !                          /* Rows are separated by commas */
 288             Pihat2 = exp(x2`*b)/(1+exp(x2`*b));
 289             print "Student in the elite class who got 20 right out of 20" pihat2;
 290        
 291        quit;
 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              782.56k
       OS Memory           32424.00k
       Timestamp           02/05/2020 04:53:35 PM
       Step Count                        161  Switch Count  1
       Page Faults                       0
       Page Reclaims                     168
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           16
       
 
 292        
 293        
 294        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 305