RAND Statistics Seminar Series
A Coverage Approach to Evaluating Mean Square Error
Presented by Alan H. Dorfman, Ph.D., Bureau of Labor & Statistics, Washington., D.C.
Thursday, May 13, 2010
1:30 p.m. – 3:00 p.m. ET
Conference Room 6207, RAND Corporation, Pittsburgh, PA
Washington, D.C., Conf. Rm. 4132 1:30 p.m. ET
Santa Monica, CA, Conf. Rm. 2309 10:30 a.m. PT
Please contact Denise Miller if you would like to attend this seminar.
We describe an approach to evaluating the mean square error of a possibly biased estimatorθ1 , using confidence intervals of a corresponding unbiased estimatorθ^. This approach has the remarkable property of not requiring an estimate, implicit or explicit, of the bias of θ1—the method is indifferent to the bias/variance breakdown of θ1's mean square error. The method was developed to evaluate competing biased estimators which incorporate data from a large wage survey in producing estimates of wages based primarily on a small detailed wage survey.
Our speaker is Senior Mathematical Statistician in the Office of Survey Methods Research at the Bureau of Labor Statistics and a Fellow of the American Statistical Association. He has taught at Temple University, Tulane University, and Johns Hopkins, where he earlier received his Ph. D. in Biostatistics. He also taught for a period at St. John's College, “the Great Books School”. He has published many journal articles and is co-author of a book “Finite Population Sampling and Inference: A Prediction Approach”, which attempts to bring survey sampling into better alignment with mainstream statistical thought and practice.
Attending a Seminar
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 email@example.com 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 firstname.lastname@example.org.