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

PSC In The News

RSS Feed icon

ISR's Scott Page says diverse teams produce optimal results

Bound, Geronimus, et al. find estimates of decreasing longevity among low-SES whites sensitive to measures and interpretations

Thompson casts doubt on the rehabilitative intentions of prison labor

More News

Highlights

Seefeldt discusses her book Abandoned Families, Wed, March 29, 4 PM, Annenberg Auditorium

U-M participants at PAA Annual Meeting, April 27-29

Heather Ann Thompson wins Bancroft Prize for History for 'Blood in the Water'

Michigan ranks in USN&WR top-10 grad schools for sociology, public health, labor economics, social policy, social psychology

More Highlights

Next Brown Bag

Mon, April 10, 2017, noon:
Elizabeth Bruch

Multiple imputation using multivariate gh transformations

Publication Abstract

He, Y., and Trivellore Raghunathan. 2012. "Multiple imputation using multivariate gh transformations." Journal of Applied Statistics, 39(10): 2177-2198.

Multiple imputation has emerged as a popular approach to handling data sets with missing values. For incomplete continuous variables, imputations are usually produced using multivariate normal models. However, this approach might be problematic for variables with a strong non-normal shape, as it would generate imputations incoherent with actual distributions and thus lead to incorrect inferences. For non-normal data, we consider a multivariate extension of Tukey's gh distribution/transformation [38] to accommodate skewness and/or kurtosis and capture the correlation among the variables. We propose an algorithm to fit the incomplete data with the model and generate imputations. We apply the method to a national data set for hospital performance on several standard quality measures, which are highly skewed to the left and substantially correlated with each other. We use Monte Carlo studies to assess the performance of the proposed approach. We discuss possible generalizations and give some advices to practitioners on how to handle non-normal incomplete data.

DOI:10.1080/02664763.2012.702268 (Full Text)

Browse | Search : All Pubs | Next