An efficient algorithm for REML in heteroscedastic regression
- Author(s)
- Smyth, GK;
- Details
- Publication Year 2002-12,Volume 11,Issue #4,Page 836-847
- Journal Title
- JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
- Publication Type
- Journal Article
- Abstract
- This article considers REML (residual or restricted maximum likelihood) estimation for heteroscedastic linear models. An explicit algorithm is given for REML scoring which yields the REML estimates together with their standard errors and likelihood values. The algorithm includes a Levenberg-Marquardt restricted step modification that ensures that the REML likelihood increases at each iteration. This article shows how the complete computation, including the REML information matrix, may be carried out in O(n) operations.
- Publisher
- AMER STATISTICAL ASSOC
- Keywords
- MODELING VARIANCE HETEROGENEITY; GENERALIZED LINEAR-MODELS; MAXIMUM-LIKELIHOOD; DISPERSION; DIAGNOSTICS; DESIGNS; SERIES
- Publisher's Version
- https://doi.org/10.1198/106186002871
- Terms of Use/Rights Notice
- Refer to copyright notice on published article.
Creation Date: 2002-12-01 12:00:00