Analysis of a longitudinal multilevel experiment using GAMLSSs

TL;DR

This paper explores the use of generalized additive models for location, scale, and shape (GAMLSSs) with random effects in the analysis of hierarchical plant growth data, comparing it to traditional linear mixed models.

Contribution

It introduces the application of mixed GAMLSSs for hierarchical data analysis, a novel approach not previously used for mixed modeling.

Findings

Mixed GAMLSSs provide flexible modeling of hierarchical data.

Comparison shows GAMLSSs can outperform linear mixed models in certain scenarios.

Demonstrates the applicability of GAMLSSs in plant growth experiments.

Abstract

The standard procedures for analysing hierarquical or grouped data are by (non)linear mixed models or generalized mixed models. However, the generalized additive models for location, scale and shape (GAMLSSs) also allow different types of random effects to be included in the model formulation. Even though already popular in many areas of research, this type of models have not been found to be used for mixed modeling purposes yet. Therefore, this paper describes the analysis of an experiment with plants' growth using mixed GAMLSSs, comparing it to a linear mixed model approach.