1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 61         
 62         /* basicmath.sas */
 63         %include '/folders/myfolders/441s18/Lecture/mathread1.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
       
 
 177        
 
 NOTE: The infile '/folders/myfolders/441s18/Lecture/exploremath.data.txt' is:
       Filename=/folders/myfolders/441s18/Lecture/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/441s18/Lecture/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 100:24   99 at 101:18   
 NOTE: The data set WORK.MATHEX has 579 observations and 25 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.01 seconds
       cpu time            0.01 seconds
       
 178        proc freq;
 
 179             title3 'Frequency distributions of categorical variables';
 180             tables sex gender ethnic tongue course passed gsplit;
 181        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.12 seconds
       cpu time            0.11 seconds
       
 182        proc means;
 
 183             title3 'Basic Descriptive Statistics on Quantitative Variables';
 184             var hsgpa hscalc hsengl  calc precalc totscore diff grade;
 185        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE MEANS used (Total process time):
       real time           0.06 seconds
       cpu time            0.05 seconds
       
 186        proc univariate normal plot;
 
 187             var grade;
 188        
 189        /* Explore with elementary tests */
 190        
 
 NOTE: PROCEDURE UNIVARIATE used (Total process time):
       real time           0.83 seconds
       cpu time            0.25 seconds
       
 191        proc means n mean stddev t probt;
 
 192             title3 'Calculus vs. Pre-calculus scale';
 193             var diff;
 194        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE MEANS used (Total process time):
       real time           0.03 seconds
       cpu time            0.03 seconds
       
 195        proc freq;
 
 196             title3 'Some Relationships between categorical variables';
 197             tables tongue*sex / chisq;
 198             tables ethnic*sex / nocol nopercent chisq;
 199             tables sex*course / nocol nopercent chisq;
 200             tables ethnic * tongue / nocol nopercent chisq;
 201        
 202        /* Follow up ethnic * tongue to seek directional conclusions */
 203        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.18 seconds
       cpu time            0.17 seconds
       
 204        proc freq;
 
 205             title3 'Ethnic by Tongue: Asians vs. Eastern Europeans';
 206             where ethnic = 1 or ethnic = 2;
 207             tables ethnic * tongue / nocol nopercent chisq;
 208        
 
 NOTE: There were 194 observations read from the data set WORK.MATHEX.
       WHERE ethnic in (1, 2);
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.06 seconds
       cpu time            0.06 seconds
       
 209        proc freq;
 
 210             title3 'Ethnic by Tongue: Asians vs. Other Europeans';
 211             where ethnic = 1 or ethnic = 3;
 212             tables ethnic * tongue / nocol nopercent chisq;
 213        
 
 NOTE: There were 326 observations read from the data set WORK.MATHEX.
       WHERE ethnic in (1, 3);
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.06 seconds
       cpu time            0.05 seconds
       
 214        proc freq;
 
 215             title3 'Ethnic by Tongue: Asians vs. Middle East';
 216             where ethnic = 1 or ethnic = 4;
 217             tables ethnic * tongue / nocol nopercent chisq;
 218        
 
 NOTE: There were 203 observations read from the data set WORK.MATHEX.
       WHERE ethnic in (1, 4);
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.07 seconds
       cpu time            0.05 seconds
       
 219        proc freq;
 
 220             title3 'Ethnic by Tongue: Asians vs. East Indian';
 221             where ethnic = 1 or ethnic = 5;
 222             tables ethnic * tongue / nocol nopercent chisq;
 223        
 
 NOTE: There were 209 observations read from the data set WORK.MATHEX.
       WHERE ethnic in (1, 5);
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.06 seconds
       cpu time            0.05 seconds
       
 224        proc freq;
 
 225             title3 'Ethnic by Tongue: Asians vs. Other / DK';
 226             where ethnic = 1 or ethnic = 6;
 227             tables ethnic * tongue / nocol nopercent chisq;
 228        
 
 NOTE: There were 171 observations read from the data set WORK.MATHEX.
       WHERE ethnic in (1, 6);
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.06 seconds
       cpu time            0.05 seconds
       
 229        proc freq;
 
 230             title3 'Eastern European vs. Other European';
 231             where ethnic = 2 or ethnic = 3;
 232             tables ethnic * tongue / nocol nopercent chisq;
 233        
 
 NOTE: There were 258 observations read from the data set WORK.MATHEX.
       WHERE ethnic in (2, 3);
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.06 seconds
       cpu time            0.04 seconds
       
 234        proc freq;
 
 235             title3 'Eastern European vs. Middle Eastern';
 236             where ethnic = 2 or ethnic = 4;
 237             tables ethnic * tongue / nocol nopercent chisq;
 238        
 239        /* And so on. There are 6 choose 2 = 15 pairwise comparisons */
 240        
 241        /* Passing the course is an important response variable*/
 242        
 
 NOTE: There were 135 observations read from the data set WORK.MATHEX.
       WHERE ethnic in (2, 4);
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.06 seconds
       cpu time            0.05 seconds
       
 243        proc freq;
 
 244             title3 'Passing the course';
 245             tables (sex ethnic tongue course) * passed / nocol nopercent chisq;
 246        
 247        /* Categorical Predictors of Grade, one at a time */
 248        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.17 seconds
       cpu time            0.15 seconds
       
 249        proc glm;
 
 250             title3 'Sex and Grade';
 251             class gender; /* Could have used sex instead */
 252             model grade=gender;
 253        
 
 NOTE: PROCEDURE GLM used (Total process time):
       real time           0.38 seconds
       cpu time            0.15 seconds
       
 254        proc glm;
 
 255             title3 'Ethnic and Grade';
 256             class ethnic;
 257             model grade=ethnic;
 258        
 
 NOTE: PROCEDURE GLM used (Total process time):
       real time           0.41 seconds
       cpu time            0.17 seconds
       
 259        proc glm;
 
 260             title3 'Mother tongue and Grade';
 261             class tongue;
 262             model grade=tongue;
 263             means tongue; /* Means broken down by tongue */
 264        
 
 NOTE: PROCEDURE GLM used (Total process time):
       real time           0.61 seconds
       cpu time            0.23 seconds
       
 265        proc glm;
 
 266             title3 'Course and Grade';
 267             class course;
 268             model grade=course;
 269        
 270        /*  Relationships between quantitative variables*/
 271        
 
 NOTE: PROCEDURE GLM used (Total process time):
       real time           0.38 seconds
       cpu time            0.13 seconds
       
 272        proc corr;
 
 273             title3 'Correlations between quantitative variables';
 274             var hsgpa hscalc hsengl  calc precalc totscore diff grade passed;
 275        
 
 NOTE: PROCEDURE CORR used (Total process time):
       real time           0.16 seconds
       cpu time            0.15 seconds
       
 276        proc reg plots = none;
 
 277             title3 'Preliminary regression on grade try 1: Initial sample size is n=579';
 278             model grade = gender mtongue e1-e4 e6 c1 c3 hsgpa hscalc hsengl  calc precalc totscore;
 279        
 280        
 281        
 282        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 295