Study Notes1 Predictive Modeling with Logistic Regression: impute missing data with proc stdize for continuous variable

/*This is the study notes from SAS online training. It includes why use Logistic Regression, how to clean the data */

/*(impute missing value, cluster rare events levels, variable clustering, variable screening), how to build */

/*logistic regression and how to measure the performance of the model */

libname mydata "D:\SkyDrive\sas_temp";

proc datasets lib=mydata;

contents data=_all_;

run;

*** How to impute the missing data by proc stdize ***;

/*data preparation*/

data pva(drop=control_number);

set mydata.pva_raw_data;

run;

/*use proc means with nmiss to check how many obs are missing for each variable*/

proc means data=pva nmiss min max median;

var donor_age income_group wealth_rating;

run;

/*use array to set indicator for missing obs, if missing then indicatd as 1*/

data pva;

set pva;

array a_mi{*} mi_donor_age mi_income_group mi_wealth_rating;

array a_var{*} donor_age income_group wealth_rating;

do i=1 to dim(a_mi);

a_mi(i)=(a_var(i)=.);

end;

run;

/*group data into 3 groups by recent_response_prop from low to high: first 1/3 grp_resp is 0, next 1/3 of data is 1 */

/*the last 1/3 is 2. In the same way for grp_amt. So totally there are 9 groups of data considering grp_resp and grp_ant */

/*obs numbers in grp_resp level or grp_amt level are similar, but at grp_resp*grp_amt level is different */

proc rank data=pva out=pva groups=3;

var recent_response_prop recent_avg_gift_amt;

ranks grp_resp grp_amt;

run;

proc freq data=pva;

table grp_resp grp_amt / missing list;

table grp_resp*grp_amt / missing list;

run;

/*sort the data by grp_resp and grp_amt*/

proc sort data=pva;

by grp_resp grp_amt;

run;

/*impute the missing data in each group formed by grp_resp*grp_amt, by the median value of non-missing data in that group*/

/*after the imputation, the data will have imputed value as well as the missing value indicator */

proc stdize data=pva method=median reponly out=pva1;

by grp_resp grp_amt;

var donor_age income_group wealth_rating;

run;

/*check the imputed value in each group*/

proc means data=pva median;

class grp_resp grp_amt;

var donor_age income_group wealth_rating;

run;

/*there are some other ways to impute, like cluster imputation using proc fastclus */

/*or using EM, MCMC, Regression to impute in proc mi(see UCLA ATS) */

/*proc mi can also use logistic regression to impute the categorical variables */

/* http://www.ats.ucla.edu/stat/sas/seminars/missing_data/part1.htm */

/* http://www.ats.ucla.edu/stat/sas/seminars/missing_data/part2.htm */