You are not currently logged in.
Access your personal account or get JSTOR access through your library or other institution:
If You Use a Screen ReaderThis content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Alternative Markov Models for Describing Change in Party Identification
Douglas Dobson and Duane A. Meeter
American Journal of Political Science
Vol. 18, No. 3 (Aug., 1974), pp. 487-500
Published by: Midwest Political Science Association
Stable URL: http://www.jstor.org/stable/2110627
Page Count: 14
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Preview not available
This paper utilizes panel data collected by the Survey Research Center to assess the fit of data on party identification to three alternative models--all of which are Markovian in nature. The models are given by: (1) P(t) = D + (I - D)M; (2) P(t) = D(t) + (I - D(t))M; (3) P(t) = D(t) + (I - D(t))M(t). Thus they decompose the Markov process into two distinct processes, determining when a move will occur and the outcome of a move, given that it did occur. When the data for the total sample are considered, changes in party identification are found to fit the model described by (3). By partitioning chi-square values for diagonal estimates and examining standardized residuals for off-diagonal estimates, sources of time variation are investigated.
American Journal of Political Science © 1974 Midwest Political Science Association