Home > Publications . Search All . Browse All . Country . Browse PSC Pubs . PSC Report Series

PSC In The News

RSS Feed icon

Bleakley says reversing US trade policies could be 'recipe for slowdown'

Novak, Geronimus, and Martinez-Cardoso find fear of immigration can affect Latino birth outcomes

Frey's Scenario F simulation mentioned in account of the Democratic Party's tribulations

More News


Post-doc fellowship in computational social science for summer or fall 2017, U-Penn

Workshops on EndNote, NIH reporting, and publication altmetrics, Jan 26 through Feb 7, ISR

2017 PAA Annual Meeting, April 27-29, Chicago

NIH funding opportunity: Etiology of Health Disparities and Health Advantages among Immigrant Populations (R01 and R21), open Jan 2017

More Highlights

Next Brown Bag

Mon, Jan 23, 2017 at noon:
Decline of cash assistance and child well-being, Luke Shaefer

On the Performance of Sequential Regression Multiple Imputation Methods with Non Normal Error Distributions

Publication Abstract

He, Y.L., and Trivellore Raghunathan. 2009. "On the Performance of Sequential Regression Multiple Imputation Methods with Non Normal Error Distributions." Communications in Statistics: Simulation and Computation, 38(4): 856-883.

Sequential regression multiple imputation has emerged as a popular approach for handling incomplete data with complex features. In this approach, imputations for each missing variable are produced based on a regression model using other variables as predictors in a cyclic manner. Normality assumption is frequently imposed for the error distributions in the conditional regression models for continuous variables, despite that it rarely holds in real scenarios. We use a simulation study to investigate the performance of several sequential regression imputation methods when the error distribution is flat or heavy tailed. The methods evaluated include the sequential normal imputation and its several extensions which adjust for non normal error terms. The results show that all methods perform well for estimating the marginal mean and proportion, as well as the regression coefficient when the error distribution is flat or moderately heavy tailed. When the error distribution is strongly heavy tailed, all methods retain their good performances for the mean and the adjusted methods have robust performances for the proportion; but all methods can have poor performances for the regression coefficient because they cannot accommodate the extreme values well. We caution against the mechanical use of sequential regression imputation without model checking and diagnostics.

DOI:10.1080/03610910802677191 (Full Text)

Browse | Search : All Pubs | Next