Imputation using proc surveyimpute

Question — Sun, 07 Feb 2021 19:22:03 GMT

Hi ,

I have used the code below to impute the missing from a Survey that I am working on.

My goal is to make sure that after imputation, the distribution of variables of imputed recipients matches the distribution of donors (non missing). But I am having a problem with the variable region, after imputation the distribution isn't matching the donors (see below). Is there anyway, to fix this region distribution in the code below, is there any option that will make every region representative etc..?

Thank you

proc surveyimpute data=hotdeck_source method=hotdeck(selection=ABB);

ndonors=5 seed=773269;

var income;

class var1 var2 var3 var4 var5;

Id unitID;

cells var1 var2 var3 var4 var5
output out=hotdeck_result1 donorid;

run;

Donors		Imputed recipients
Region	Percentage	Region	Percentage
East Midlands	8%	East Midlands	1%
East of England	6%	East of England	0%
London	5%	London	10%
North East	5%	North East	0%
North West	10%	North West	1%
Northern Ireland	5%	Northern Ireland	75%
Scotland	19%	Scotland	5%
South East	11%	South East	2%
South West	8%	South West	2%
Wales	5%	Wales	1%
West Midlands	8%	West Midlands	3%
Yorks and the Humber	9%	Yorks and the Humber	0%

Re: Imputation using proc surveyimpute

gcjfernandez — Mon, 08 Mar 2021 17:32:28 GMT

Try SAS Surveyimpute method=FEFI (Efficient Fractional Imputation (FEFI). Please refer the paper: https://support.sas.com/resources/papers/proceedings16/SAS3520-2016.pdf

Re: Imputation using proc surveyimpute

Question — Tue, 09 Mar 2021 18:17:45 GMT

Thank you Fernández, will try.

Best wishes

topic Re: Imputation using proc surveyimpute in Statistical Procedures

Imputation using proc surveyimpute

Re: Imputation using proc surveyimpute

Re: Imputation using proc surveyimpute