Multivariate Regression and ANOVA Models with Outliers: A Comparative Approach

Wolfgang Polasek

No 136, Economics Series from Institute for Advanced Studies

Abstract: Assuming a normal-Wishart modelling framework we compare two methods for finding outliers in a multivariate regression (MR) system. One method is the add-1-dummy approach which needs fewer parameters and a model choice criterion while the other method estimates the outlier probability for each observation by a Bernoulli mixing outlier location shift model. For the simple add-1-dummy model the Bayes factors and the posterior probabilities can be calculated explicitly. In the probabilistic mixing model we show how the posterior distribution can be obtained by a Gibbs sampling algorithm. The number of outliers is determined using the marginal likelihood criterion. The methods are compared for test scores of language examination data of Fuller (1987): The results are similar but differ in their strength of their empirical evidence.

Keywords: Multivariate regression; Multivariate one-way ANOVA; Outliers; Gibbs sampling; Marginal likelihoods; Sensitivity analysis (search for similar items in EconPapers)
JEL-codes: C11 C39 (search for similar items in EconPapers)
Pages: 20 pages
Date: 2003-09
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://irihs.ihs.ac.at/id/eprint/1510 First version, 2003 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ihs:ihsesp:136

Ordering information: This working paper can be ordered from
Institute for Advanced Studies - Library, Josefstädterstr. 39, A-1080 Vienna, Austria

Access Statistics for this paper

More papers in Economics Series from Institute for Advanced Studies Josefstädterstr. 39, A-1080 Vienna, Austria. Contact information at EDIRC.
Bibliographic data for series maintained by Doris Szoncsitz ().