2019
DOI: 10.7717/peerj.6876
|View full text |Cite
|
Sign up to set email alerts
|

Hierarchical generalized additive models in ecology: an introduction with mgcv

Abstract: In this paper, we discuss an extension to two popular approaches to modeling complex structures in ecological data: the generalized additive model (GAM) and the hierarchical model (HGLM). The hierarchical GAM (HGAM), allows modeling of nonlinear functional relationships between covariates and outcomes where the shape of the function itself varies between different grouping levels. We describe the theoretical connection between HGAMs, HGLMs, and GAMs, explain how to model different assumptions about the degree … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

2
647
1
1

Year Published

2019
2019
2024
2024

Publication Types

Select...
7
3

Relationship

0
10

Authors

Journals

citations
Cited by 677 publications
(733 citation statements)
references
References 44 publications
2
647
1
1
Order By: Relevance
“…Seasonal patterns in mean monthly depth data, and diel patterns in the hourly depth data, from the twenty individuals were assessed using a GAMM with individual (animal ID) included as random effects. An AR1 correlation structure was utilised with the corCAR1 function in the 'nlme' package [82] to account for autocorrelation in the seasonal and diel depth data [83].…”
Section: Discussionmentioning
confidence: 99%
“…Seasonal patterns in mean monthly depth data, and diel patterns in the hourly depth data, from the twenty individuals were assessed using a GAMM with individual (animal ID) included as random effects. An AR1 correlation structure was utilised with the corCAR1 function in the 'nlme' package [82] to account for autocorrelation in the seasonal and diel depth data [83].…”
Section: Discussionmentioning
confidence: 99%
“…Initial exploratory examination of pupillary dilation after stimulation was done using generalized additive models (GAMs), fitting smooth functions (spline-based) to pupil size against time, with stimulus intensity, stimulus type (mechanical or chemical) and sex as predictor variables. This was done using the MGCV package in R [44,45]. Non-linear mixed effect models were fit to pupil size against time functions, using the SAEMIX package in R [44], and non-linear regression was done in SPSS for Windows, Version 16.0 (Chicago, SPSS Inc.).…”
Section: Analysesmentioning
confidence: 99%
“…Our goals were (1) to identify major gain and loss motifs, (2) to determine whether there was significant site-to-site variation in weight pattern, and (3) to determine whether there was sufficient similarity across sites to justify a global weight model. Accordingly, we constructed three nested hierarchical GAMs, following Pedersen et al (2019) .…”
Section: Weight Monitoring and Pattern Characterizationmentioning
confidence: 99%