Cholesky residuals for assessing normal errors in a linear model with correlated outcomes

Publisher:
American Statistical Association
Publication Type:
Journal Article
Citation:
Journal Of The American Statistical Association, 2004, 99 (466), pp. 383 - 394
Issue Date:
2004-01
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2011008547OK.pdf2.22 MB
Adobe PDF
Despite the widespread popularity of linear models for correlated outcomes (e.g., linear mixed models and time series models), distribution diagnostic methodology remains relatively underdeveloped in this context. In this article we present an easy-to-implement approach that lends itself to graphical displays of model fit. Our approach involves multiplying the estimated marginal residual vector by the Cholesky decomposition of the inverse of the estimated marginal variance matrix. The resulting "rotated" residuals are used to construct an empirical cumulative distribution function and pointwise standard errors. The theoretical framework, including conditions and asymptotic properties, involves technical details that are motivated by Lange and Ryan. Pierce, and Randles. Our method appears to work well in a variety of circumstances. including models having independent units of sampling (clustered data) and models for which all observations are correlated (e. g.. a single time series). Our methods can produce satisfactory results even for models that do not satisfy all of the technical conditions stated in our theory.
Please use this identifier to cite or link to this item: