Abstract
This article presents the Gibbs–Skovgaard algorithm for approximate frequentist inference. The method makes use of the double saddlepoint approximation of Skovgaard to the conditional cumulative distribution function of a sufficient statistic given the remaining sufficient statistics. This approximation is then used in the Gibbs sampler to generate a Markov chain. The equilibrium distribution of this chain approximates the joint distribution of the sufficient statistics associated with the parameters of interest conditional on the observed values of the sufficient statistics associated with the nuisance parameters. This Gibbs–Skovgaard algorithm is applied to the cases of logistic and Poisson regression.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 697-702 |
| Number of pages | 6 |
| Journal | Journal of the American Statistical Association |
| Volume | 89 |
| Issue number | 426 |
| DOIs | |
| State | Published - Jun 1994 |
Funding
*John E. Kolassa is Assistant Professor and Martin A. Tanner is Professor, Department of Biostatistics, University of Rochester, NY 14642. Tanner was supported by National Institutes of Health Grant CA35464. Kolassa was supported by National Institutes of Health Grants T32NS07338, CA35464, and CA63050.
Keywords
- Conditional inference
- Gibbs sampler
- Markov chain
- Monte Carlo
- Saddlepoint approximations
ASJC Scopus subject areas
- Statistics and Probability
- Statistics, Probability and Uncertainty