1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 55         
 56         /* describemath.sas */
 57         title 'Gender, Ethnicity and Math performance';
 58         title2 'Basic descriptive statistics on the exploratory sample';
 59         
 60         proc format;
 61              value ynfmt  0 = 'No'  1 = 'Yes';
 NOTE: Format YNFMT has been output.
 62              value crsfmt   4 = 'No Resp';
 NOTE: Format CRSFMT has been output.
 63              value nfmt
 64                         1 = 'Asian'
 65                         2 = 'Eastern European'
 66                         3 = 'European not Eastern'
 67                         4 = 'Middle-Eastern  and Pakistani'
 68                         5 = 'East Indian'
 69                         6 = 'Other   and DK' ;
 NOTE: Format NFMT has been output.
 70         
 
 NOTE: PROCEDURE FORMAT used (Total process time):
       real time           0.02 seconds
       cpu time            0.01 seconds
       
 71         data math;
 
 72              infile '/folders/myfolders/exploremath.data.txt';
 73              input id course precalc calc gpa calculus english mark lang $ sex $
 74                    nation1 nation2 sample;
 75         
 76         /* Computed Variables: totscore, passed, grade, hsgpa, hscalc, hsengl,
 77                                tongue, ethnic */
 78         
 79              totscore = precalc+calc;
 80              if (50<=mark<=100) then passed=1; else passed=0;
 81              /* Some missing final marks were zero, and 998=SDF and 999=WDR */
 82              if mark=0 then grade=.;
 83                 else if mark > 100 then grade=.;
 84                 else grade=mark;
 85              /* Missing HS marks were zeros */
 86              if 65 le gpa le 100 then hsgpa = gpa; /* Else missing is automatic */
 87              if 0 < calculus < 101 then hscalc = calculus;
 88              if 0 < english < 101 then hsengl = english;
 89              /* There were just a few French speakers */
 90              if lang='French' then tongue='Other  '; else tongue=lang;
 91              label tongue = 'Mother Tongue (Eng or Other)';
 92              /* Rater 1 knows Middle Eastern names -- otherwise believe Rater 2 */
 93              if nation1=4 then ethnic=nation1; else ethnic=nation2;
 94         
 95              /********************************************************************/
 96         
 97              label
 98                    precalc  = 'Number precalculus correct'
 99                    calc  = 'Number calculus correct'
 100                   totscore = 'Total # right on diagnostic test'
 101                   passed = 'Passed the course'
 102                   grade = 'Final mark'
 103                   hsgpa = 'High School GPA'
 104                   hscalc = 'HS Calculus'
 105                   hsengl = 'HS English'
 106                   lang = 'Mother Tongue'
 107                   nation1 = 'Nationality of name acc to rater1'
 108                   nation2 = 'Nationality of name acc to rater2'
 109                   tongue = 'Mother Tongue (Eng or Other)'
 110                   ethnic = 'Judged Nationality of name'        ;
 111        
 112             format course crsfmt.;
 113             format passed ynfmt.;
 114             format nation1 nation2 ethnic nfmt.;
 115        
 116        /*********************************************************************/
 117        
 
 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 79:24   
 NOTE: The data set WORK.MATH has 579 observations and 21 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.01 seconds
       cpu time            0.02 seconds
       
 118        proc means;
 
 119             title3 'Quantitative Variables';
 120             var precalc calc totscore hsgpa hscalc hsengl grade;
 121        
 
 NOTE: There were 579 observations read from the data set WORK.MATH.
 NOTE: PROCEDURE MEANS used (Total process time):
       real time           0.07 seconds
       cpu time            0.07 seconds
       
 122        proc freq;
 
 123             title3 'Categorical variables';
 124             tables course sex ethnic tongue passed;
 125        
 126        /* Bar chart of ethnic would be nice. */
 127        
 
 NOTE: There were 579 observations read from the data set WORK.MATH.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.07 seconds
       cpu time            0.07 seconds
       
 128        proc univariate normal plot;
 
 129             /* The normal option gives tests of H0: Data are normal.
 130             Plot produces graphics, some of which are informative. */
 131             title3 'Detailed look at grade';
 132             var grade;
 133        
 
 NOTE: PROCEDURE UNIVARIATE used (Total process time):
       real time           3.23 seconds
       cpu time            0.24 seconds
       
 134        proc freq;
 
 135             title3 'Frequency Distribution of Final Grade';
 136             tables grade;
 137        
 138        /* The following suggests that profs in Courses 1 and 3 bumped
 139           the marks discontinuously, while the prof in Course 2 did
 140           something more sophisticated. */
 141        
 
 NOTE: There were 579 observations read from the data set WORK.MATH.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.11 seconds
       cpu time            0.11 seconds
       
 142        proc freq;
 
 143             title3 'Grade separately by course';
 144             where course < 4; /* Exclude no response */
 145             tables grade*course / norow nopercent nopercent;
 146        
 147        
 148        
 149        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 161