Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.14/114778
59 Visitors
60 Hits
0 Downloads
- Title
- Stable computation of maximum likelihood estimates in identity link Poisson regression
- Related
- Journal of computational and graphical statistics, Vol. 19, Issue 3 (2010), p.666-683
- DOI
- 10.1198/jcgs.2010.09127
- Publisher
- American Statistical Association
- Date
- 2010
- FoR/RFCD Code(s)
-
010400 Statistics
- Author/Creator
- Marschner, Ian C
- Description
- Identity link Poisson regression is useful when the mean of a count variable depends additively on a collection of predictor variables. It is particularly important in epidemiology, for modeling absolute differences in disease incidence rates as a function of covariates. A complication of such models is that standard computational methods for maximum likelihood estimation can be numerically unstable due to the nonnegativity constraints on the Poisson means. Here we present a straightforward and flexible method that provides stable maximization of the likelihood function over the constrained parameter space. This is achieved by conducting a sequence of maximizations within subsets of the parameter space, after which the global maximum is identified from among the subset maxima. The method adapts and extends EM algorithms that are useful in specialized applications involving Poisson deconvolution, but which do not apply in more general regression contexts. As well as allowing categorical and continuous covariates, the method has the flexibility to accommodate covariates with an unspecified isotonic form. Its computational reliability makes it particularly useful in bootstrap analyses, which may require stable convergence for thousands of implementations. Computations are illustrated using epidemiological data on occupational mortality, and biological data on crab population counts. This article has supplementary material online.
- Description
- 18 page(s)
- Subject Keyword
- 010400 Statistics
- Subject Keyword
- EM algorithm
- Subject Keyword
- generalized linear model
- Subject Keyword
- isotonic regression
- Subject Keyword
- parameter constraint
- Subject Keyword
- rate difference
- Resource Type
- journal article
- Organisation
- Macquarie University. Dept. of Statistics
- Identifier
- http://hdl.handle.net/1959.14/114778
- Identifier
- ISSN:1537-2715
- Identifier
- mq-rm-2010000345
- Language
- eng
- Reviewed
List Of Titles
