SUMMARY The Bayesian approach to comparing models involves calculating the posterior probability of each plausible model. For high-dimensional contingency tables, the set of plausible models is veryâ€¦ (More)

PETROS DELLAPORTASâˆ—, JONATHAN J. FORSTERâ€ and IOANNIS NTZOUFRASâˆ—âˆ— âˆ—Department of Statistics, Athens University of Economics and Business, Patission 76, 10434 Athens, Greece petros@aueb.gr â€ Departmentâ€¦ (More)

We consider how to compare different conditional independence specifications for ordinal categorical data, by calculating a posterior distribution over classes of graphical models. The approach isâ€¦ (More)

We develop Metropolis-Hastings algorithms for exact conditional inference, including goodness-offit tests, confidence intervals and residual analysis, for binomial and multinomial logistic regressionâ€¦ (More)

Categorical data frequently arise in applications in the social sciences. In such applications,the class of log-linear models, based on either a Poisson or (product) multinomial responseâ€¦ (More)

BACKGROUND Population forecasts are widely used for public policy purposes. Methods to quantify the uncertainty in forecasts tend to ignore model uncertainty and to be based on a single model.â€¦ (More)

Journal of the Royal Statistical Society. Seriesâ€¦

1996

The value of using exact rather than asymptotic tests to measure intermarriage in the United Kingdom is examined. "We develop Markov chain Monte Carlo methods for estimating the exact conditionalâ€¦ (More)

We propose an approach for assessing the risk of individual identification in the release of categorical data. This requires the accurate calculation of predictive probabilities for those cells in aâ€¦ (More)