On Bayesian Modeling of Fat Tails and Skewness
- 1 March 1998
- journal article
- research article
- Published by Informa UK Limited in Journal of the American Statistical Association
- Vol. 93 (441), 359-371
- https://doi.org/10.1080/01621459.1998.10474117
Abstract
We consider a Bayesian analysis of linear regression models that can account for skewed error distributions with fat tails. The latter two features are often observed characteristics of empirical datasets, and we formally incorporate them in the inferential process. A general procedure for introducing skewness into symmetric distributions is first proposed. Even though this allows for a great deal of flexibility in distributional shape, tail behavior is not affected. Applying this skewness procedure to a Student t distribution, we generate a “skewed Student” distribution, which displays both flexible tails and possible skewness, each entirely controlled by a separate scalar parameter. The linear regression model with a skewed Student error term is the main focus of the article. We first characterize existence of the posterior distribution and its moments, using standard improper priors and allowing for inference on skewness and tail parameters. For posterior inference with this model, we suggest a numerical procedure using Gibbs sampling. The latter proves very easy to implement and renders the analysis of quite challenging problems a practical possibility. Some examples illustrate the use of this model in empirical data analysis.Keywords
This publication has 15 references indexed in Scilit:
- Modeling and Inference with υ-Spherical DistributionsJournal of the American Statistical Association, 1995
- Marginal Likelihood from the Gibbs OutputJournal of the American Statistical Association, 1995
- Bayesian Inference for Stable DistributionsJournal of the American Statistical Association, 1995
- Measuring Skewness with Respect to the ModeThe American Statistician, 1995
- Explaining the Gibbs SamplerThe American Statistician, 1992
- Priors for Macroeconomic Time Series and Their ApplicationPublished by Federal Reserve Bank of Minneapolis ,1992
- A Data-Analytic Look at Skewness and Elongation in Common-Stock-Return DistributionsJournal of Business & Economic Statistics, 1991
- Sampling-Based Approaches to Calculating Marginal DensitiesJournal of the American Statistical Association, 1990
- Non-Uniform Random Variate GenerationPublished by Springer Science and Business Media LLC ,1986
- The Weighted Likelihood Ratio, Linear Hypotheses on Normal Location ParametersThe Annals of Mathematical Statistics, 1971