We would like to welcome Dr. Xiao-Li Meng, Whipple V.N. Jones Professor of Statistics and Dean of the Graduate School of Arts and Sciences at Harvard University, back to the University of Chicago for the 2015/2016 Workshop on Quantitative Methods in Education, Health and the Social Sciences (QMeHSS). Dr. Meng will be leading this workshop for Friday, November 13h, from 11:00-12:30pm. In addition to Dr. Meng, Dr. Lars Peter Hansen, David Rockefeller Distinguished Service Professor in Economics, Statistics, and the College Research Director of the Becker Friedman Institute, will be joining us a discussant for this exciting workshop. Unlike previous workshops, this one will be held at Stuart Hall Room 104, located at 5835 S. Greenwood Avenue. Please join us in giving both Dr. Meng and Dr. Hansen a warm reception as we look forward to stimulating discussion on a very interesting topic. We look forward to seeing you there.
I Got More Data, My Model is More Refined, but My Estimator is Getting Worse? Am I Just Dumb?
Xiao-Li Meng (Harvard University)
Abstract: Possibly, but more likely you are merely a victim of conventional wisdom. More data or better models by no means guarantee better estimators (e.g., with smaller mean squared error), when you are not following probabilistically principled methods such as MLE (for large samples) or Bayesian approaches. Estimating equations are particularly dangerous in this regard, almost a necessary price for their robustness. These points will be demonstrated via common tasks of estimating regression parameters and correlations, under simple models such as bivariate normal and ARCH(1). Some general strategies for detecting and avoiding such pitfalls are suggested, including checking for self-efficiency (Meng, 1994, Statistical Science) and adopting a guiding working model.
Of course, Bayesians are not automatically immune either to being a victim of conventional wisdom. A simple example is given in the context of a stationary AR(1) model where the so-called “non-informative” Jeffreys prior can get arbitrarily close to a point mass at a unit root, hardly non-informative by any measure.
download the paper here: I Got More Data, My Model is More Refined, but My Estimator is Getting Worse? Am I Just Dumb?
This talk is based on Meng and Xie (2014, Econometric Reviews, 33: 218-250; Special issue in honor of Arnold Zellner).
Xiao-Li Meng, Official Website http://statistics.fas.harvard.edu/people/xiao-li-meng