2017
DOI: 10.1111/eth.12713
|View full text |Cite
|
Sign up to set email alerts
|

Generalized estimating equations: A pragmatic and flexible approach to the marginalGLMmodelling of correlated data in the behavioural sciences

Abstract: Within behavioural research, non-normally distributed data with a complicated structure are common. For instance, data can represent repeated observations of quantities on the same individual. The regression analysis of such data is complicated both by the interdependency of the observations (response variables) and by their non-normal distribution. Over the last decade, such data have been more and more frequently analysed using generalized mixed-effect models. Some researchers invoke the heavy machinery of m… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
91
0
2

Year Published

2018
2018
2023
2023

Publication Types

Select...
8
1
1

Relationship

2
8

Authors

Journals

citations
Cited by 144 publications
(93 citation statements)
references
References 19 publications
(25 reference statements)
0
91
0
2
Order By: Relevance
“…Estimating Equations with Gamma error structure (GEE-g) (Pekár & Brabec, 2018). We used the geglme function from the geepack package (Yan & Fine, 2004) within the R environment (R Core Team, 2015).…”
Section: Statistical Analysesmentioning
confidence: 99%
“…Estimating Equations with Gamma error structure (GEE-g) (Pekár & Brabec, 2018). We used the geglme function from the geepack package (Yan & Fine, 2004) within the R environment (R Core Team, 2015).…”
Section: Statistical Analysesmentioning
confidence: 99%
“…The occurrence of different stages of Mexcala were related to the occurrence of six most abundant ant species by means of generalised estimating equations with Poisson distribution (GEE-p) from the geepack 36 within R 37 . GEE is an extension of GLM for correlated data 38 and was used in order to take into account joined occurrence of different stages of Mexcala on the same tree (i.e. nested observations).…”
Section: Methodsmentioning
confidence: 99%
“…For this, the function rarefaction from [38] based on the function rarefy from package vegan [39] was used. Then, the abundance among guilds of spiders (i.e., count data) was compared for each sampling date using generalized estimating equations (GEE) with Poisson distribution, an extension of generalized linear models (GLM) [40,41] followed by a posthoc Tukey test. In all cases, the correlation structure used was "exchangeable" (i.e., a single correlation parameter, ρ) and the grove was used for clustering.…”
Section: Field Sampling Schemementioning
confidence: 99%