RAND Statistics Seminar Series

Proxy Pattern-Mixture Analysis for Survey Nonresponse

Presented by Roderick J. Little, Ph.D., University of Michigan
Wednesday, January 14, 2009
1:30 p.m. – 3:00 p.m. PST
Conference Room 5312
RAND Corporation, Santa Monica, CA
Please contact Denise Miller if you would like to attend this seminar.


I consider assessment of nonresponse bias for the mean of a survey variable Y subject to nonresponse. I assume that there are a set of covariates observed for nonrespondents and respondents. To reduce dimensionality I reduce the covariates to a proxy variable X that has the highest correlation with Y, estimated from a regression analysis of respondent data. I consider adjusted estimators of the mean of Y that are maximum likelihood for a pattern-mixture model with different mean and covariance matrix of Y and X for respondents and nonrespondents, assuming missingness is an arbitrary function of a known linear combination of X and Y. I propose a taxonomy for the evidence concerning bias based on the strength of the proxy and the deviation of the mean of X for respondents from its overall mean, and a Bayesian sensitivity analysis that reflects this taxonomy. The relationship of this method to other approaches, including the Heckman model for selectivity bias, is examined. Methods are assessed through simulation and data from the third National Health and Nutrition Examination Survey (NHANES III). This is joint work with Rebecca Andridge at the University of Michigan.

Speaker Bio

Dr. Little is Chair of the Biostatistics Department at the University of Michigan, and previously Professor of Biomathematics at UCLA. He was Editor of the Journal of the American Statistical Association from 1992-1994. He has served as a member of the Committee on National Statistics and a number of National Research Council committees, most recently on Census undercount issues. He has over 150 publications, notably on methods for the analysis of data with missing values and model-based survey inference, and the application of statistics to diverse scientific areas, including medicine, demography, economics, psychiatry, aging and the environment. In 2005 Dr. Little received the Wilks' Memorial Award from the American Statistical Association for his research contributions.

Attending a Seminar

Other Locations/Times:
Washington, D.C. Conf. Rm. 4128: 4:30 p.m. ET
Pittsburgh Conf. Rm. 6202: 4:30 p.m. ET

RAND visitors are welcome to attend and must RSVP at least one day prior to the seminar. To ensure your attendance please contact Denise Miller at dmiller@rand.org with your name, company (or university) affiliation, and national citizenship (for security purposes).

For parking and directions to RAND's Santa Monica office, please see: http://www.rand.org/about/locations/santa-monica.html.

For parking and directions to RAND's Pittsburgh office, please see: http://www.rand.org/about/locations/pittsburgh.html.

For further information and to be added to the mailing list contact Denise Miller at dmiller@rand.org.