1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 55         
 56         /* MathReg2.sas  */
 57         %include '/folders/myfolders/441s16/Lecture/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
       cpu time            0.00 seconds
       
 
 159        title2 'Residual analysis';
 160        
 
 NOTE: The infile '/folders/myfolders/exploremath.data.txt' is:
       Filename=/folders/myfolders/exploremath.data.txt,
       Owner Name=root,Group Name=vboxsf,
       Access Permission=-rwxrwx---,
       Last Modified=18Jan2016:17:34:49,
       File Size (bytes)=44583
 
 NOTE: 579 records were read from the infile '/folders/myfolders/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 80:24    99 at 117:13   
 NOTE: The data set WORK.MATHEX has 579 observations and 34 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.01 seconds
       cpu time            0.01 seconds
       
 161        proc reg plots(only) = ResidualPlot;
 
 162             title3 'Model H: hsgpa hscalc hsengl totscore';
 163             model grade = hsgpa hscalc hsengl totscore;
 164             output out = Explor predicted = yhat
 165                                 residual  = resid
 166                                 rstudent  = delstud;
 167                                          /* Deleted Studentized Residual */
 168        
 169        /* Could have included LCL and UCL for upper and lower limits of a
 170           95% prediction interval for each case in the file */
 171        
 172        
 173        /* What is a big (Studentized deleted) residual? If the model is correct,
 174           each one has a t distribution with n-p-1 = 283 df (practically standard
 175           normal), so the Studentized deleted residual can be treated directly as
 176           a t-test statistic. Values that are too big in absolute value will cause
 177           H0: mu=0 to be rejected. Tests are NOT independent, but use a Bonferroni
 178           correction for n = 289 tests. Get the critical value from proc iml. */
 179        
 
 NOTE: The data set WORK.EXPLOR has 579 observations and 37 variables.
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.59 seconds
       cpu time            0.27 seconds
       
 180        proc iml;
 
 NOTE: IML Ready
 181             title3 'Critical value for Joint t-test on Studentized Residuals';
 182             Alpha = 0.05/289;
 182      !                        print Alpha;
 183             Critval = tinv(1-Alpha/2,283);
 183      !                                     print Critval;
 184        
 NOTE: Exiting IML.
 NOTE: PROCEDURE IML used (Total process time):
       real time           0.04 seconds
       cpu time            0.04 seconds
       
 185        proc univariate normal plot;
 
 186             var delstud;
 187        
 188        /* Tests for normality indicate residuals are not normal. No st resids
 189        greater than critical value. Next, a few more plots. */
 190        
 
 NOTE: PROCEDURE UNIVARIATE used (Total process time):
       real time           0.49 seconds
       cpu time            0.19 seconds
       
 191        proc sgplot;
 
 192             title3 'Plot of Y-hat by Y';
 193             scatter y=grade x=yhat;
 194        
 
 195        proc sgplot;
 NOTE: PROCEDURE SGPLOT used (Total process time):
       real time           0.24 seconds
       cpu time            0.10 seconds
       
 NOTE: There were 579 observations read from the data set WORK.EXPLOR.
 
 196             title3 'Calculus sub-test by deleted studentized residual';
 197             scatter x=calc y=delstud;
 198        
 
 199        proc sgplot;
 NOTE: PROCEDURE SGPLOT used (Total process time):
       real time           0.22 seconds
       cpu time            0.10 seconds
       
 NOTE: There were 579 observations read from the data set WORK.EXPLOR.
 
 200             title3 'Pre-calculus sub-test by deleted studentized residual';
 201             scatter x=precalc y=delstud;
 202        
 
 203        proc sgplot;
 NOTE: PROCEDURE SGPLOT used (Total process time):
       real time           0.24 seconds
       cpu time            0.10 seconds
       
 NOTE: There were 579 observations read from the data set WORK.EXPLOR.
 
 204             title3 'Mother tongue by deleted studentized residual';
 205             scatter x=mtongue y=delstud;
 206        
 207        
 208        
 209        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 221