1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 72         
 73         /* describemath0.sas */
 74         title 'Gender, Ethnicity and Math performance';
 75         title2 'Basic descriptive statistics on the combined sample';
 76         
 77         proc format;
 78              value ynfmt  0 = 'No'  1 = 'Yes';
 NOTE: Format YNFMT is already on the library WORK.FORMATS.
 NOTE: Format YNFMT has been output.
 79              value crsfmt   4 = 'No Resp';
 NOTE: Format CRSFMT is already on the library WORK.FORMATS.
 NOTE: Format CRSFMT has been output.
 80              value nfmt
 81                        1  = 'Chinese'
 82                        2  = 'Japanese'
 83                        3  = 'Korean'
 84                        4  = 'Vietnamese'
 85                        5  = 'Other Asian'
 86                        6  = 'Eastern European'
 87                        7  = 'Hispanic'
 88                        8  = 'English-speaking'
 89                        9  = 'French'
 90                       10   = 'Italian'
 91                       11   = 'Greek'
 92                       12   = 'Germanic'
 93                       13   = 'Other European'
 94                       14   = 'Middle-Eastern'
 95                       15   = 'Pakistani'
 96                       16   = 'East Indian'
 97                       17   = 'Sub-Saharan'
 98                       18  = 'OTHER or DK';
 NOTE: Format NFMT is already on the library WORK.FORMATS.
 NOTE: Format NFMT has been output.
 99         
 100             value ncfmt
 101                        1 = 'Asian'
 102                        2 = 'Eastern European'
 103                        3 = 'European not Eastern'
 104                        4 = 'Middle-Eastern  and Pakistani'
 105                        5 = 'East Indian'
 106                        6 = 'Other   and DK' ;
 NOTE: Format NCFMT is already on the library WORK.FORMATS.
 NOTE: Format NCFMT has been output.
 107        
 
 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              248.37k
       OS Memory           27044.00k
       Timestamp           02/13/2024 06:18:54 PM
       Step Count                        34  Switch Count  0
       Page Faults                       0
       Page Reclaims                     27
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           32
       
 
 108        data math;
 109             infile '/home/u1407221/441s24/data/math.data.txt';
 110             input id course precalc calc gpa calculus english mark lang $ sex $
 111                   nation1 nation2 sample;
 112        
 113        /* Computed Variables: totscore, passed, grade, hsgpa, hscalc, hsengl,
 114                               tongue, class, ethnic */
 115        
 116             totscore = precalc+calc;
 117             if (50<=mark<=100) then passed=1; else passed=0;
 118             /* Some missing final marks were zero, and 998=SDF and 999=WDR */
 119             if mark=0 then grade=.;
 120                else if mark > 100 then grade=.;
 121                else grade=mark;
 122             /* Missing HS marks were zeros */
 123             if 65 le gpa le 100 then hsgpa = gpa; /* Else missing is automatic */
 124             if 1 le calculus le 100 then hscalc = calculus;
 125             if 1 le english le 100 then hsengl = english;
 126             /* There were just a few French speakers */
 127             if lang='French' then tongue='Other  '; else tongue=lang;
 128             label tongue = 'Mother Tongue (Eng or Other)';
 129             class = course;
 130             if class = 4 then class = .;
 131        
 132        
 133        /********* Nationality According to the 2 raters **********/
 134             if         1 <= nation1 <= 5 then rater1 = 1;
 135             else if    nation1 = 6 then rater1 = 2;
 136             else if    7 <= nation1 <= 13 then rater1 = 3;
 137             else if    14 <= nation1 <= 15 then rater1 = 4;
 138             else if    nation1 = 16 then rater1 = 5;
 139             else       rater1 = 6;
 140             if         1 <= nation2 <= 5 then rater2 = 1;
 141             else if    nation2 = 6 then rater2 = 2;
 142             else if    7 <= nation2 <= 13 then rater2 = 3;
 143             else if    14 <= nation2 <= 15 then rater2 = 4;
 144             else if    nation2 = 16 then rater2 = 5;
 145             else       rater2 = 6;
 146             /* Rater 1 knows Middle Eastern names -- otherwise believe Rater 2 */
 147             if rater1=4 then ethnic=rater1; else ethnic=rater2;
 148             /********************************************************************/
 149        
 150             label
 151                   precalc  = 'Number precalculus correct'
 152                   calc  = 'Number calculus correct'
 153                   totscore = 'Total # right on diagnostic test'
 154                   passed = 'Passed the course'
 155                   grade = 'Final mark'
 156                   hsgpa = 'High School GPA'
 157                   hscalc = 'HS Calculus'
 158                   hsengl = 'HS English'
 159                   lang = 'Mother Tongue'
 160                   rater1 = 'Nationality of name acc to rater1'
 161                   rater2 = 'Nationality of name acc to rater2'
 162                   tongue = 'Mother Tongue (Eng or Other)'
 163                   ethnic = 'Judged Nationality of name'        ;
 164        
 165             format course crsfmt.;
 166             format passed ynfmt.;
 167             format nation1 nation2 nfmt.;
 168             format rater1 rater2 ethnic ncfmt.;
 169        
 170        /*********************************************************************/
 171        
 172        /* Check created variables */
 173        
 174        /* Do this for transformed quantitative variables - Lots of output
 175        proc print data=math;
 176             var mark grade;
 177        */
 178        
 179        /* Check created variables
 180        proc freq data=math;
 181             tables lang*tongue / norow nocol nopercent missing;
 182             tables course*class / norow nocol nopercent missing;
 183             tables nation1*rater1 / norow nocol nopercent missing;
 184             tables nation2*rater2 / norow nocol nopercent missing;
 185             tables (rater1 rater2) * ethnic / norow nocol nopercent missing;
 186        */
 187        
 188        /* Could use  "by"  , like this to get separate results for each sample.
 189        proc sort data=math;
 190             by sample;
 191        proc means data=math;
 192             title3 'Quantitative Variables';
 193             by sample;
 194             var precalc calc totscore hsgpa hscalc hsengl grade;
 195        */
 196        
 
 NOTE: The infile '/home/u1407221/441s24/data/math.data.txt' is:
       Filename=/home/u1407221/441s24/data/math.data.txt,
       Owner Name=u1407221,Group Name=oda,
       Access Permission=-rw-r--r--,
       Last Modified=10Feb2024:16:04:10,
       File Size (bytes)=90324
 
 NOTE: 1158 records were read from the infile '/home/u1407221/441s24/data/math.data.txt'.
       The minimum record length was 76.
       The maximum record length was 76.
 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).
       180 at 116:24   
 NOTE: The data set WORK.MATH has 1158 observations and 24 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              968.14k
       OS Memory           27816.00k
       Timestamp           02/13/2024 06:18:54 PM
       Step Count                        35  Switch Count  2
       Page Faults                       0
       Page Reclaims                     152
       Page Swaps                        0
       Voluntary Context Switches        16
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           536
       
 
 197        proc means data=math;
 198             title3 'Quantitative Variables';
 199             class sample;
 200             var precalc calc totscore hsgpa hscalc hsengl grade;
 201        
 
 NOTE: There were 1158 observations read from the data set WORK.MATH.
 NOTE: PROCEDURE MEANS used (Total process time):
       real time           0.06 seconds
       user cpu time       0.06 seconds
       system cpu time     0.01 seconds
       memory              9823.56k
       OS Memory           35772.00k
       Timestamp           02/13/2024 06:18:55 PM
       Step Count                        36  Switch Count  2
       Page Faults                       0
       Page Reclaims                     1982
       Page Swaps                        0
       Voluntary Context Switches        18
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           8
       
 
 202        proc freq data=math;
 203             title3 'Categorical variables';
 204             tables sample * (course sex ethnic tongue passed) / norow nocol nopercent missing;
 205        
 206        run;
 
 NOTE: There were 1158 observations read from the data set WORK.MATH.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.07 seconds
       user cpu time       0.07 seconds
       system cpu time     0.00 seconds
       memory              1817.29k
       OS Memory           31408.00k
       Timestamp           02/13/2024 06:18:55 PM
       Step Count                        37  Switch Count  5
       Page Faults                       0
       Page Reclaims                     285
       Page Swaps                        0
       Voluntary Context Switches        33
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           568
       
 
 206      !      quit;
 207        
 208        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 220