Inference for generalized additive mixed models via penalized marginal likelihood

TL;DR

This paper introduces a new estimation method for generalized additive mixed models that improves the accuracy of smoothing parameter estimation over traditional Laplace approximation methods.

Contribution

It proposes a novel estimation strategy based on penalized marginal likelihood that ensures statistically correct estimates.

Findings

Enhanced accuracy in smoothing parameter estimation

Estimates with correct statistical properties

Improved inference in generalized additive mixed models

Abstract

The Laplace approximation is sometimes not sufficiently accurate for smoothing parameter estimation in generalized additive mixed models. A novel estimation strategy is proposed that solves this problem and leads to estimates exhibiting the correct statistical properties.