1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 61         
 62         /************************ math0.3.sas *************************/
 63         title 'Prediction of Performance in First-year Calculus';
 64         title2 'Read exploratory data, create and test new variables';
 65         
 66         proc format;
 67              value ynfmt  0 = 'No'  1 = 'Yes';
 NOTE: Format YNFMT is already on the library WORK.FORMATS.
 NOTE: Format YNFMT has been output.
 68              value crsfmt 1 = 'Catch-up' 2 = 'Mainstrm' 3 = 'Elite' 4 = 'No Resp';
 NOTE: Format CRSFMT is already on the library WORK.FORMATS.
 NOTE: Format CRSFMT has been output.
 69              value nfmt
 70                         1 = 'Asian'
 71                         2 = 'Eastern European'
 72                         3 = 'European not Eastern'
 73                         4 = 'Middle-Eastern  and Pakistani'
 74                         5 = 'East Indian'
 75                         6 = 'Other   and DK' ;
 NOTE: Format NFMT is already on the library WORK.FORMATS.
 NOTE: Format NFMT has been output.
 76         
 
 NOTE: PROCEDURE FORMAT used (Total process time):
       real time           0.00 seconds
       cpu time            0.00 seconds
       
 77         data mathex;
 
 78              infile '/folders/myfolders/441s18/Lecture/exploremath.data.txt';
 79              input id course precalc calc gpa calculus english mark lang $ sex $
 80                    nation1 nation2 sample;
 81              /****** Fix problems located in first run ******/
 82              if course = 4 then course = .; /* No response is missing */
 83              /* Missing HS marks were zeros */
 84              if 60 le gpa le 100 then hsgpa = gpa; /* Else missing is automatic */
 85              if 0 < calculus < 101 then hscalc = calculus;
 86              if 0 < english < 101 then hsengl = english;
 87              /* Some missing university calculus marks were zero,
 88                 and 998=SDF and 999=WDR */
 89              if mark=0 then grade=.;
 90                 else if mark > 100 then grade=.;
 91                 else grade=mark;
 92              /* There were just a few French speakers */
 93              if lang='French' then tongue='Other  '; else tongue=lang;
 94              label tongue = 'Mother Tongue (Eng or Other)';
 95         
 96              /****** Create and check more new variables ******/
 97              totscore = precalc+calc; /* Total score on diagnostic test */
 98              if (50<=mark<=100) then passed=1; else passed=0;
 99              /* Rater 1 knows Middle Eastern names -- otherwise believe Rater 2 */
 100             if nation1=4 then ethnic=nation1; else ethnic=nation2;
 101             if 0 le grade le 60 then gsplit='60orLess';
 102                  else if 60 lt grade le 100 then gsplit='Over60';
 103                  /* Got median=60 from proc univariate */
 104             /* Dummy variables for ethnic background:
 105                Only use 2 of these if the model has an intercept */
 106        if ethnic=. then e1=.;
 107           else if ethnic=1 then e1=1;
 108           else e1=0;
 109        if ethnic=. then e2=.;
 110           else if ethnic=2 then e2=1;
 111           else e2=0;
 112        if ethnic=. then e3=.;
 113           else if ethnic=3 then e3=1;
 114           else e3=0;
 115        if ethnic=. then e4=.;
 116           else if ethnic=4 then e4=1;
 117           else e4=0;
 118        if ethnic=. then e5=.;
 119           else if ethnic=5 then e5=1;
 120           else e5=0;
 121        if ethnic=. then e6=.;
 122           else if ethnic=6 then e6=1;
 123           else e6=0;
 124        label e1 = 'Asian'
 125              e2 = 'East Eur.'
 126              e3 = 'Other Eur.'
 127              e4 = 'Mid. East & Pak.'
 128              e5 = 'East Ind.'
 129              e6 = 'Other/DK';
 130        /* gender is a dummy variable for sex */
 131        if sex = 'Female' then gender=1; else if sex = 'Male' then gender=0;
 132        /* Course: Only use 2 of these if the model has an intercept */
 133        if course=. then c1=.; else if course=1 then c1=1; else c1=0;
 134        if course=. then c2=.; else if course=2 then c2=1; else c2=0;
 135        if course=. then c3=.; else if course=3 then c3=1; else c3=0;
 136        label c1 = 'Catch-up' c2 = 'Mainstream' c3 = 'Elite';
 137        
 138        
 139        
 140        
 141             format course crsfmt.;
 142             format nation1 nation2 ethnic nfmt.;
 143             format passed ynfmt.;
 144        
 145             label
 146                   precalc  = 'Number precalculus correct'
 147                   calc  = 'Number calculus correct'
 148                   totscore = 'Total # right on diagnostic test'
 149                   passed = 'Passed the course'
 150                   grade = 'Final mark (if any)'
 151                   hsgpa = 'High School GPA'
 152                   hscalc = 'HS Calculus'
 153                   hsengl = 'HS English'
 154                   lang = 'Mother Tongue'
 155                   nation1 = 'Nationality of name acc to rater1'
 156                   nation2 = 'Nationality of name acc to rater2'
 157                   tongue = 'Mother Tongue (Eng or Other)'
 158                   ethnic = 'Judged Nationality of name'
 159                   gsplit = 'Median split on final grade'
 160                   ;
 161        
 
 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=January 18, 2016 17:34:49 o'clock,
       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 97:24   
 NOTE: The data set WORK.MATHEX has 579 observations and 32 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.01 seconds
       cpu time            0.01 seconds
       
 162        proc freq data=mathex;
 
 163             title3 'Check created variables';
 164             tables lang * tongue              / norow nocol nopercent missing;
 165             tables grade * (passed gsplit)    / norow nocol nopercent missing;
 166             tables (nation1 nation2) * ethnic / norow nocol nopercent missing;
 167             tables ethnic * (e1-e6)           / norow nocol nopercent missing;
 168             tables sex * gender               / norow nocol nopercent missing;
 169             tables (c1-c3) * course           / norow nocol nopercent missing;
 170        
 171        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           1.14 seconds
       cpu time            1.12 seconds
       
 172        proc freq data=mathex;
 
 173             title3 'Frequency distributions of variables to be used';
 174             tables  course sex nation1 nation2 calc precalc
 175                     hsgpa -- ethnic;
 176             /* Note hsgpa -- ethnic = hsgpa hscalc hsengl
 177                     grade tongue totscore passed ethnic */
 178        
 179        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.83 seconds
       cpu time            0.82 seconds
       
 180        proc freq;
 
 181             title3 'Frequency distributions of categorical variables';
 182             tables course sex ethnic passed / missing;
 183        
 
 NOTE: There were 579 observations read from the data set WORK.MATHEX.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.10 seconds
       cpu time            0.09 seconds
       
 184        proc means;
 
 185             title3  'Quantitative Variables';
 186             var hsgpa hscalc hsengl calc precalc totscore grade;
 187        
 188        
 189        
 190        
 191        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 204