1          OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 70         
 71         /********************* cars2.sas ***************************/
 72         title 'Regression on Metric Cars Data';
 73         
 74         /* Read data directly from Excel spreadsheet */
 75         proc import datafile="/home/brunner0/441s18/mcars4.xlsx"
 76                     out=cars dbms=xlsx replace;
 77                     getnames=yes;
 78         /* Input data file is mcars4.xlsx
 79            Ouput data set is called cars
 80            dbms=xlsx      The input file is an Excel spreadsheet.
 81                           Necessary to read an Excel spreadsheet directly under unix/linux
 82                           Works in PC environment too except for Excel 4.0 spreadsheets
 83                           If there are multiple sheets, use sheet="sheet1" or something.
 84            replace      If the data set cars already exists, replace it.
 85            getnames=yes   Use column names as variable names.                  */
 86         
 
 NOTE: One or more variables were converted because the data type is not supported by the V9 engine. For more details, run with 
       options MSGLEVEL=I.
 NOTE: The import data set has 100 observations and 4 variables.
 NOTE: WORK.CARS data set was successfully created.
 NOTE: PROCEDURE IMPORT used (Total process time):
       real time           0.01 seconds
       user cpu time       0.01 seconds
       system cpu time     0.00 seconds
       memory              2618.75k
       OS Memory           28840.00k
       Timestamp           01/06/2018 03:04:54 AM
       Step Count                        18  Switch Count  1
       Page Faults                       0
       Page Reclaims                     934
       Page Swaps                        0
       Voluntary Context Switches        12
       Involuntary Context Switches      0
       Block Input Operations            24
       Block Output Operations           264
       
 87         proc print;
 
 88         
 
 NOTE: There were 100 observations read from the data set WORK.CARS.
 NOTE: PROCEDURE PRINT used (Total process time):
       real time           0.12 seconds
       user cpu time       0.13 seconds
       system cpu time     0.00 seconds
       memory              2548.46k
       OS Memory           29096.00k
       Timestamp           01/06/2018 03:04:54 AM
       Step Count                        19  Switch Count  0
       Page Faults                       0
       Page Reclaims                     902
       Page Swaps                        0
       Voluntary Context Switches        0
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           48
       
 89         data auto;
 
 90              set cars;
 91              mpg = 100/lper100k * 0.6214/0.2642;
 92              Country = Cntry; /* I just like the spelling more */
 93              label Country  = 'Location of Head Office'
 94                    lper100k = 'Litres per 100 kilometers'
 95                    mpg      = 'Miles per Gallon'
 96                    weight   = 'Weight in kg'
 97                    length   = 'Length in meters';
 98         /* Indicator dummy vars: Ref category is Japanese */
 99              if country = 'US' then c1=1;  else c1=0;
 100             if country = 'Europ' then c2=1;  else c2=0;
 101             /* Interaction Terms */
 102             cw1 = c1*weight; cw2 = c2*weight;
 103         cL1 = c1*length; cL2 = c2*length;
 104        /* This way of creating dummy variables is safe only because
 105           Country is never missing. If it could be missing, better is
 106             if country = ' ' then c1 = .;
 107                else if country = 'US' then c1=1;
 108                else c1=0;
 109             if country =  ' ' then c2 = .;
 110                else if country = 'Europ' then c2=1;
 111                else c2=0;
 112        Note that a blank space is the missing value code for character variables,
 113        while a period is missing for numeric variables.  */
 114        
 
 NOTE: There were 100 observations read from the data set WORK.CARS.
 NOTE: The data set WORK.AUTO has 100 observations and 12 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              809.96k
       OS Memory           29612.00k
       Timestamp           01/06/2018 03:04:54 AM
       Step Count                        20  Switch Count  1
       Page Faults                       0
       Page Reclaims                     183
       Page Swaps                        0
       Voluntary Context Switches        7
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           264
       
 115        proc freq;
 
 116             title2 'Check dummy variables';
 117             tables (c1 c2)*country / norow nocol nopercent;
 118        
 119        /* First an analysis with country only. */
 120        
 121        /* Questions for every significance test:
 122             * What is E(y|x) for the model SAS is using?
 123             * Give the null hypothesis in symbols.
 124             * Do you reject H0 at alpha = 0.05? Answer Yes or No.
 125             * In plain, non-statistical language, what do you conclude? */
 126        
 127        
 
 NOTE: There were 100 observations read from the data set WORK.AUTO.
 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              1772.59k
       OS Memory           30384.00k
       Timestamp           01/06/2018 03:04:54 AM
       Step Count                        21  Switch Count  3
       Page Faults                       0
       Page Reclaims                     557
       Page Swaps                        0
       Voluntary Context Switches        15
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           528
       
 128        proc means;
 
 129             title2 'Litres per 100 k Broken Down by Country';
 130             class Country;
 131             var lper100k;
 132        
 
 NOTE: There were 100 observations read from the data set WORK.AUTO.
 NOTE: PROCEDURE MEANS used (Total process time):
       real time           0.02 seconds
       user cpu time       0.03 seconds
       system cpu time     0.01 seconds
       memory              9047.03k
       OS Memory           39356.00k
       Timestamp           01/06/2018 03:04:54 AM
       Step Count                        22  Switch Count  2
       Page Faults                       0
       Page Reclaims                     2364
       Page Swaps                        0
       Voluntary Context Switches        23
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           24
       
 133        proc reg plots = none; /* Suppress diagnostic plots for now*/
 
 134             title2 'Regression with Just Country';
 135             model lper100k = c1 c2;
 136             USvsEURO: test c1=c2;
 137        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.06 seconds
       user cpu time       0.06 seconds
       system cpu time     0.00 seconds
       memory              2629.78k
       OS Memory           33984.00k
       Timestamp           01/06/2018 03:04:54 AM
       Step Count                        23  Switch Count  2
       Page Faults                       0
       Page Reclaims                     870
       Page Swaps                        0
       Voluntary Context Switches        17
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           56
       
 138        proc reg plots = none;
 
 139             title2 'Country, Weight and Length';
 140             model lper100k = c1 c2 weight length;
 141             country: test c1 = c2 = 0;     /* Country controlling for wgt, length */
 142             USvsEURO: test c1=c2;          /* US vs. Europe controlling for wgt, length */
 143             wgt_len: test weight=length=0; /* wgt, length controlling for Country */
 144        
 145        /* Proportions of remaining variation, using a = sF/(n-p+sF) */
 146        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.08 seconds
       user cpu time       0.08 seconds
       system cpu time     0.00 seconds
       memory              2371.21k
       OS Memory           33984.00k
       Timestamp           01/06/2018 03:04:54 AM
       Step Count                        24  Switch Count  2
       Page Faults                       0
       Page Reclaims                     264
       Page Swaps                        0
       Voluntary Context Switches        12
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           96
       
 147        proc iml;
 
 NOTE: IML Ready
 148             title2 'Proportion of remaining variation';
 149             print "Country controlling for Weight and Length";
 150             n = 100;
 150      !               p = 3;
 150      !                      s = 2;
 151             F = 6.90;
 151      !                 a = s*F/(n-p + s*F);
 152             print a;
 153        
 154             print "Weight and Length controlling for Country";
 155             F = 115.16;
 155      !                   a = s*F/(n-p + s*F);
 156             print a;
 157        
 NOTE: Exiting IML.
 NOTE: PROCEDURE IML used (Total process time):
       real time           0.01 seconds
       user cpu time       0.02 seconds
       system cpu time     0.00 seconds
       memory              418.56k
       OS Memory           32164.00k
       Timestamp           01/06/2018 03:04:54 AM
       Step Count                        25  Switch Count  1
       Page Faults                       0
       Page Reclaims                     196
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           0
       
 158        proc reg plots = none;
 
 159             title2 'Country, Weight and Length with Interactions';
 160             model lper100k = c1 c2 weight length cw1 cw2 cL1 cL2;
 161             country: test c1 = c2 = 0;     /* Is it really still country?  */
 162             Interactions: test cw1 = cw2 = cL1 = cL2 = 0;
 163        
 164        /* Centering an explanatory variable by subtracting off the mean affects the
 165        intercept, but not the relationships among variables. I want to create a new
 166        data set with weight and length centered, and to avoid confusion
 167        I will make sure the variables are nicely labelled. */
 168        
 
 NOTE: PROCEDURE REG used (Total process time):
       real time           0.07 seconds
       user cpu time       0.08 seconds
       system cpu time     0.00 seconds
       memory              2526.53k
       OS Memory           33984.00k
       Timestamp           01/06/2018 03:04:54 AM
       Step Count                        26  Switch Count  2
       Page Faults                       0
       Page Reclaims                     262
       Page Swaps                        0
       Voluntary Context Switches        14
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           72
       
 169        proc standard mean=0 data=auto out=cntrd;
 
 170             var weight length;
 171        
 172        /* In the new data set "cntrd," weight and length are adjusted to have mean
 173        zero (the sample means have been subtracted from each observation). If I had
 174        said mean=0 std=1, they would have been converted to z-scores.  All the other
 175        variables (including the product terms) are as they were before, and the
 176        labels are the same as before too. */
 177        
 
 NOTE: The data set WORK.CNTRD has 100 observations and 12 variables.
 NOTE: PROCEDURE STANDARD used (Total process time):
       real time           0.00 seconds
       user cpu time       0.00 seconds
       system cpu time     0.00 seconds
       memory              690.50k
       OS Memory           32684.00k
       Timestamp           01/06/2018 03:04:54 AM
       Step Count                        27  Switch Count  1
       Page Faults                       0
       Page Reclaims                     120
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           264
       
 178        data centered;
 
 179             set cntrd;  /* Now centered has everything in cntrd */
 180            /* Re-create Interaction Terms and re-label explanatory vars*/
 181             cw1 = c1*weight; cw2 = c2*weight;
 182             cL1 = c1*length; cL2 = c2*length;
 183             label weight = 'Weight in kg (Centered)'
 184                   length = 'Length in cm (Centered)';
 185        
 186        /* By default, SAS procedures use the most recently created data set,
 187           but specify it anyway. */
 188        
 
 NOTE: There were 100 observations read from the data set WORK.CNTRD.
 NOTE: The data set WORK.CENTERED has 100 observations and 12 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              808.18k
       OS Memory           32684.00k
       Timestamp           01/06/2018 03:04:54 AM
       Step Count                        28  Switch Count  1
       Page Faults                       0
       Page Reclaims                     123
       Page Swaps                        0
       Voluntary Context Switches        8
       Involuntary Context Switches      0
       Block Input Operations            0
       Block Output Operations           264
       
 189        proc reg plots=none simple data=centered;
 
 190             title2 'Weight and length are now centered: Mean=0';
 191             model lper100k = c1 c2 weight length cw1 cw2 cL1 cL2;
 192             country: test c1 = c2 = 0;     /* Does this make better sense? */
 193             Interactions: test cw1 = cw2 = cL1 = cL2 = 0;
 194        
 195        
 196        
 197        
 198        
 199        
 200        
 201        
 202        OPTIONS NONOTES NOSTIMER NOSOURCE NOSYNTAXCHECK;
 214