Activity Number:
|
38
|
Type:
|
Topic Contributed
|
Date/Time:
|
Sunday, August 11, 2002 : 4:00 PM to 5:50 PM
|
Sponsor:
|
Section on Bayesian Stat. Sciences*
|
Abstract - #300519 |
Title:
|
Bayesian Shrinkage Forecasts of Individual and Aggregate Outcomes
|
Author(s):
|
Arnold Zellner*+
|
Affiliation(s):
|
University of Chicago
|
Address:
|
1101 E. 58th Street, Chicago, Illinois, 60637, USA
|
Keywords:
|
Bayesian shrinkage ; Estimation of totals ; Prediction of sums ; Balanced loss function
|
Abstract:
|
Bayesian shrinkage a la Stein and others can improve estimation of individual parameters and forecasts of individual future outcomes. In this paper the issue of the impact of shrinkage on the estimation of a sum of individual parameters and on the prediction of the sum of individual outcomes is analyzed. Quadratic loss and "balanced" loss functions will be employed. The latter are linear combinations of "goodness of fit" and "precision of estimation" loss functions. Several examples will be analyzed in detail to illustrate general principles.
|