JSM Preliminary Online Program
This is the preliminary program for the 2008 Joint Statistical Meetings in Denver, Colorado.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2008 Program page

Activity Number: 142
Type: Contributed
Date/Time: Monday, August 4, 2008 : 10:30 AM to 12:20 PM
Sponsor: Section on Bayesian Statistical Science
Abstract - #302504
Title: A Bayesian Time Series Model for Death Penalty Public Opinion
Author(s): Kenneth E. Shirley*+ and Andrew Gelman
Companies: Columbia University and Columbia University
Address: Applied Statistics Center, 2700 Broadway Apt 4N, New York, NY, 10025,
Keywords: Multilevel models ; Death penalty ; Bayesian computing ; Sample survey ; Time series models
Abstract:

Since 1974, the General Social Survey, given annually, has asked respondents whether they support the death penalty. We model 20+ years of these individual-level binary outcomes using a multilevel logistic regression model. The model includes explanatory variables like demographic information on individuals, as well as indicators of which state the respondent lives in. We are primarily interested in modeling trends within and between states across time; to do so, we explore a variety of autoregressive models. The statistical challenges in this problem include how to model the time series component of public opinion, how to incorporate a large number of high-level interactions without overfitting, and how to perform the Bayesian computation to fit a complicated model to a large data set.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2008 program


JSM 2008 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised September, 2008