170 likes | 492 Views
Multiple Imputation. Multiple Regression. Input From SPSS. *** Mult-Imput_M-Reg.sas ***; PROC IMPORT OUT= WORK.IntroQuest DATAFILE = " C:UsersVatiDocumentsStatDataIntroQIntroQ .sav " DBMS=SPSS REPLACE ; Run; Use the Import Wizard to bring the data into SAS.
E N D
Multiple Imputation Multiple Regression
Input From SPSS *** Mult-Imput_M-Reg.sas ***; PROCIMPORT OUT= WORK.IntroQuest DATAFILE= "C:\Users\Vati\Documents\StatData\IntroQ\IntroQ.sav" DBMS=SPSS REPLACE; Run; • Use the Import Wizard to bring the data into SAS.
Check For Missing Data procmeans n nmiss; run;
Oh Crap ! • We have a lot of missing data on SATM • Missingness on SATM is associated with statophobia and year. • It is not missing completely at random. • Need to employ multiple imputation.
Create Five Imputations • ProcMI seed=69301 out=MIdata; var gender ideal nucoph SATM year; run;
Patterns of Missingness • Most frequent pattern of missing data is missing on SATM only .
Analyze the Imputed Data ProcRegoutest = MRbyImputcovout; Model Statoph = gender ideal nucoph SATM year / stb; By _Imputation_; run; ProcMIAnalyze; modeleffects intercept gender ideal nucoph SATM year; run; • See the complete output here: XYZZY • In every imputation, Gender, SATM, and Year have significant effects.
ProcMIAnalyze Output • Pools the results from the five imputations. • The variance in the scores is partitioned between that among imputations and that within imputations. • Ideally, little of the variance is due to differences among imputations.
“Relative Increase in Variance” is the increase in variance due to having missing data imputed (relative to the condition where no data are missing). Low is good. • “Fraction of Missing Information,” is an index of how much more precise the parameter estimate would have been if there had been no missing data. Low is good.
“Relative efficiency” tells you how much poweryou have for the number of imputations you have employed relative to what you would have if you used an uncountably large number of imputations. • High is good.
Conclusions • Women report greater fear of the stats course than do men. • Reported Math Aptitude is inversely correlated with fear of stats.