Journal Title
Title of Journal: Stat Comput
|
Abbravation: Statistics and Computing
|
|
|
|
|
|
|
|
Authors: Nathaniel E Helwig
Publish Date: 2015/11/12
Volume: 26, Issue: 6, Pages: 1319-1336
Abstract
Linear mixedeffects LME regression models are a popular approach for analyzing correlated data Nonparametric extensions of the LME regression model have been proposed but the heavy computational cost makes these extensions impractical for analyzing large samples In particular simultaneous estimation of the variance components and smoothing parameters poses a computational challenge when working with large samples To overcome this computational burden we propose a twostage estimation procedure for fitting nonparametric mixedeffects regression models Our results reveal that compared to currently popular approaches our twostage approach produces more accurate estimates that can be computed in a fraction of the timeUnlike the REML–VC algorithm presented for known varvecvarPsi the computational cost for unknown varvecvarPsi will generally not be insensitive to the sample size n This is because the mathbf C=mathbf Wprime varvecvarPsi 1mathbf W +varvecvarSigma 0 matrix will have to be iteratively updated ie recalculated for each new varvecvarPsi In this case it may possible to apply the rounding parameter approximation proposed by Helwig and Ma in press to reduce the data to u ll n unique data points which would reduce the computational burden involved with the iterative formation of mathbf C However for simple parameterizations of varvecvarPsi eg firstorder autoregressive it may be more computationally efficient to perform a grid search ie fix the parameters in varvecnu and use the REML–VC algorithm for known varvecvarPsi This sort of approach would be easily parallelizable and assuming the number of nu k parameters is small could be much more efficient than estimating the nu k parameters using a REML approach
Keywords:
.
|
Other Papers In This Journal:
|