1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 68         
 69         /************************** senic2.sas ***************************/
 70         title 'Open SENIC Data';
 71         title2 'Descriptive stats with better labels';
 72         
 73         proc format;
 73       !               /* Value labels used in data step below */
 74              value yesnofmt 1 = 'Yes'   0 = 'No' ;
 NOTE: Format YESNOFMT is already on the library WORK.FORMATS.
 NOTE: Format YESNOFMT has been output.
 75              value regfmt   1 = 'Northeast'
 76                             2 = 'North Central'
 77                             3 = 'South'
 78                             4 = 'West' ;
 NOTE: Format REGFMT is already on the library WORK.FORMATS.
 NOTE: Format REGFMT has been output.
 79         
 
 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              264.37k
       OS Memory           22944.00k
       Timestamp           12/21/2023 06:56:44 PM
       Step Count                        147  Switch Count  0
       Page Faults                       0
       Page Reclaims                     14
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           32
       
 
 80         data senic;
 81              infile '/home/u1407221/441s24/SAS02/openSENIC2.data.txt' firstobs=2;
 82              input   id region mdschl $ census nbeds nurses lngstay age
 83                      xratio culratio infpercent;
 84              label region     = 'Region of U.S.A.'
 85                    mdschl     = 'Medical school affiliation'
 86                    census     = 'Aver # patients in hospital per day'
 87                    nbeds      = 'Average # beds during study period'
 88                    nurses     = 'Aver # nurses during study period'
 89                    lngstay    = 'Av length of hospital stay, in days'
 90                    age        = 'Average patient age'
 91                    xratio     = '# x-rays / # no signs of pneumonia'
 92                    culratio   = '# cultures  / # no hosp acq infect'
 93                    infpercent = 'Percent acquiring infection in hospital';
 94         
 95              /* Fix up problems */
 96              if mdschl = '?' then mdschl = ' '; /* Blank = missing for character vars */
 97              if age = 999 then age = .;
 98              if infpercent = 999 then infpercent = .;
 99         
 100             /***** Recodes, computes & ifs  *****/
 101             if 0<age<=53 then agecat = '53 & under';
 102             else if age>53 then agecat='Over 53';
 103             label   agecat = 'Average patient age';
 104             quality=(2*nurses+nbeds+10*culratio
 105                          +10*xratio-2*lngstay);
 106             if mdschl eq 'No' then quality=quality/2;
 107             if (region eq 3) then quality=quality-100;
 108             label quality = 'Jerry''s bogus hospital quality index';
 109        
 110             /* Make dummy variables. Proc reg needs them, proc glm does not. */
 111             if mdschl = 'No' then mschool = 0;
 112                else if mdschl = 'Yes' then mschool = 1;
 113             /* Region  */
 114             if region = 1 then ne = 1;           /* Northeast */
 115                else if region = . then ne = .;
 116                else ne = 0;
 117             if region = 2 then nc = 1;           /* North Central */
 118                else if region = . then nc = .;
 119                else nc = 0;
 120             if region = 3 then s = 1;            /* South */
 121                else if region = . then s = .;
 122                else s = 0;
 123             if region = 4 then w = 1;            /* West */
 124                else if region = . then w = .;
 125                else w = 0;
 126        
 127             format nc ne s w yesnofmt.; /* Associate vars with printing format */
 128             format region regfmt.;      /* Note the period. */
 129        
 130        /* First priority is to check the dummy variables. */
 131        
 
 NOTE: The infile '/home/u1407221/441s24/SAS02/openSENIC2.data.txt' is:
       Filename=/home/u1407221/441s24/SAS02/openSENIC2.data.txt,
       Owner Name=u1407221,Group Name=oda,
       Access Permission=-rw-r--r--,
       Last Modified=21Dec2023:11:37:19,
       File Size (bytes)=8585
 
 NOTE: 100 records were read from the infile '/home/u1407221/441s24/SAS02/openSENIC2.data.txt'.
       The minimum record length was 83.
       The maximum record length was 83.
 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).
       3 at 104:16   3 at 106:44   2 at 107:43   
 NOTE: The data set WORK.SENIC has 100 observations and 18 variables.
 NOTE: DATA statement used (Total process time):
       real time           0.02 seconds
       user cpu time       0.00 seconds
       system cpu time     0.00 seconds
       memory              822.25k
       OS Memory           23204.00k
       Timestamp           12/21/2023 06:56:44 PM
       Step Count                        148  Switch Count  2
       Page Faults                       0
       Page Reclaims                     117
       Page Swaps                        0
       Voluntary Context Switches        20
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           272
       
 
 132        proc freq;
 133             tables mschool*mdschl / norow nocol nopercent missing;
 
 NOTE: There were 100 observations read from the data set WORK.SENIC.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.01 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              2084.78k
       OS Memory           23724.00k
       Timestamp           12/21/2023 06:56:44 PM
       Step Count                        149  Switch Count  4
       Page Faults                       0
       Page Reclaims                     191
       Page Swaps                        0
       Voluntary Context Switches        22
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           536
       
 
 134        proc freq;
 135             tables (ne nc s w) * region / norow nocol nopercent missing;
 136        
 137        /* Descriptive Statistics */
 138        
 
 NOTE: There were 100 observations read from the data set WORK.SENIC.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.04 seconds
       user cpu time       0.05 seconds
       system cpu time     0.00 seconds
       memory              1291.75k
       OS Memory           23980.00k
       Timestamp           12/21/2023 06:56:44 PM
       Step Count                        150  Switch Count  4
       Page Faults                       0
       Page Reclaims                     204
       Page Swaps                        0
       Voluntary Context Switches        24
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           544
       
 
 139        proc freq;
 140             title2 'Frequency distributions of categorical variables';
 141             tables region mdschl agecat nc ne s w;
 142        
 
 NOTE: There were 100 observations read from the data set WORK.SENIC.
 NOTE: PROCEDURE FREQ used (Total process time):
       real time           0.04 seconds
       user cpu time       0.04 seconds
       system cpu time     0.00 seconds
       memory              1201.06k
       OS Memory           23720.00k
       Timestamp           12/21/2023 06:56:44 PM
       Step Count                        151  Switch Count  3
       Page Faults                       0
       Page Reclaims                     177
       Page Swaps                        0
       Voluntary Context Switches        21
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           280
       
 
 143        proc sgplot; /* Bar charts for categorical variables */
 144             title2 'Bar Chart of Region';
 145             vbar region;
 
 146        proc sgplot;
 NOTE: PROCEDURE SGPLOT used (Total process time):
       real time           0.10 seconds
       user cpu time       0.04 seconds
       system cpu time     0.01 seconds
       memory              8073.84k
       OS Memory           31276.00k
       Timestamp           12/21/2023 06:56:45 PM
       Step Count                        152  Switch Count  3
       Page Faults                       0
       Page Reclaims                     2222
       Page Swaps                        0
       Voluntary Context Switches        153
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           616
       
 NOTE: There were 100 observations read from the data set WORK.SENIC.
 
 147             title2 'Bar Chart of Medical School Affiliation';
 148             vbar mdschl;
 149        
 
 150        proc means;
 NOTE: PROCEDURE SGPLOT used (Total process time):
       real time           0.07 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              2330.43k
       OS Memory           31660.00k
       Timestamp           12/21/2023 06:56:45 PM
       Step Count                        153  Switch Count  3
       Page Faults                       0
       Page Reclaims                     579
       Page Swaps                        0
       Voluntary Context Switches        152
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           360
       
 NOTE: There were 100 observations read from the data set WORK.SENIC.
 
 151             title2 'Table of means and standard deviations';
 152             var census nbeds nurses lngstay age xratio culratio infpercent quality;
 153        
 
 NOTE: There were 100 observations read from the data set WORK.SENIC.
 NOTE: PROCEDURE MEANS used (Total process time):
       real time           0.03 seconds
       user cpu time       0.03 seconds
       system cpu time     0.01 seconds
       memory              6423.12k
       OS Memory           35512.00k
       Timestamp           12/21/2023 06:56:45 PM
       Step Count                        154  Switch Count  2
       Page Faults                       0
       Page Reclaims                     1362
       Page Swaps                        0
       Voluntary Context Switches        24
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           8
       
 
 154        proc univariate normal plot;
 155             title2 'A close look at infection percent';
 156             var infpercent;  /* Could be a list of variables */
 157        
 158        /* Boxplots for different values of a grouping variable */
 159        /* Need to sort by the grouping variable first */
 
 NOTE: PROCEDURE UNIVARIATE used (Total process time):
       real time           0.14 seconds
       user cpu time       0.08 seconds
       system cpu time     0.00 seconds
       memory              3929.43k
       OS Memory           32856.00k
       Timestamp           12/21/2023 06:56:45 PM
       Step Count                        155  Switch Count  1
       Page Faults                       0
       Page Reclaims                     520
       Page Swaps                        0
       Voluntary Context Switches        224
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           440
       
 
 160        proc sort;
 161             by region;
 
 NOTE: There were 100 observations read from the data set WORK.SENIC.
 NOTE: The data set WORK.SENIC has 100 observations and 18 variables.
 NOTE: PROCEDURE SORT used (Total process time):
       real time           0.00 seconds
       user cpu time       0.00 seconds
       system cpu time     0.00 seconds
       memory              933.78k
       OS Memory           31912.00k
       Timestamp           12/21/2023 06:56:45 PM
       Step Count                        156  Switch Count  2
       Page Faults                       0
       Page Reclaims                     122
       Page Swaps                        0
       Voluntary Context Switches        12
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           264
       
 
 162        proc boxplot;
 163             title2 'Infection Risk by Region';
 164             plot infpercent*region;
 165        
 166        run;
 
 NOTE: Since an input data set was not specified, data set SENIC is assumed as a DATA= data set.
 NOTE: Processing beginning for PLOT statement number 1.
 NOTE: There were 100 observations read from the data set WORK.SENIC.
 NOTE: PROCEDURE BOXPLOT used (Total process time):
       real time           0.13 seconds
       user cpu time       0.06 seconds
       system cpu time     0.01 seconds
       memory              9437.37k
       OS Memory           39184.00k
       Timestamp           12/21/2023 06:56:45 PM
       Step Count                        157  Switch Count  1
       Page Faults                       0
       Page Reclaims                     2002
       Page Swaps                        0
       Voluntary Context Switches        520
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           368
       
 
 167        
 168        
 169        
 170        
 171        
 172        
 173        
 174        
 175        
 176        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 186