About the Society
Papers, Posters, Syllabi
Submit an Item
Polmeth Mailing List
Below results based on the criteria 'FILTER'
Total number of records returned: 3
Modeling Time Series Count Data: A State-Space Approach to Event Counts
Brandt, Patrick T.
Williams, John T.
non-normal time series
This is a revised version, dated July 16, 1998. Time series count data is prevalent in political science. We argue that political scientists should employ time series methods to analyze time series count data. A simple state-space model is presented that extends the Kalman filter to count data. The properties of this model are outlined and further evaluated by a Monte Carlo study. We then show how time series of counts present special problems by turning to two replications: the number of hospital deaths that are the subject of a recent criminal court case, and Pollins (1996) MIDs data from international relations.
Evaluating Measures of Ideology
Bishin, Benjamin G.
A vigorous debate has arisen over the metric used to measure ideology (Jackson and Kingdon 1992, Poole and Rosenthal 1985, Snyder 1991, Krehbiel 1993). Ideology is difficult to measure because legislator's statements may be politically motivated and insincere. This paper evaluates the accuracy of NOMINATE and ADA scores by comparing them to an independent measure, based on background characteristics, developed herein. By Forecasting the Ideology of Legislators Through Elite Response (FILTER), this measure avoids the problems inherent in use of the roll call vote metric. In addition, the FILTER methodology is generalizable to studies of other deliberative bodies. The results show that FILTER scores are highly correlated with NOMINATE and ADA scores.
Binary and Ordinal Time Series with AR(p) Errors: Bayesian Model Determination for Latent High-Order Markovian Processes
Auxiliary Particle Filter
Markov Chain Monte Carlo (MCMC)
Sampling Importance Resampling(SIR)
To directly and adequately correct serial correlation in binary and ordinal response data, this paper proposes a probit model with errors following a pth-order autoregressive process, and develops simulation-based methods in the Bayesian context to handle computational challenges of posterior estimation, model comparison, and lag order determination. Compared to the extant methods, such as quasi-ML, GCM, and and simulation-based ML estimators, the current method does not rely on the properties of the big variance-covariance matrix or the shape of the likelihood function. In addition, the present model efficiently handles high-order autocorrelated errors that raise computationally formidable difficulties to the conventional methods. By applying a mixed sampler of the Gibbs and Metropolis-Hastings algorithm, the posterior distributions of the parameters do not depend on initial observations. The auxiliary particle filter, complemented by the fixed-lag smoothing, is extended to approximate Bayes Factors for models with latent high-order Markov processes. Computational methods are tested with empirical data. Energy cooperation policies of the International Energy Agency are analyzed in terms of their effects on global oil-supply security. The current model with different lag orders, together with other competitive models, is estimated and compared.