Generalized linear mixed models (GLMM) in community ecology studies using the R statistical environment
Keywords:
community ecology, regression analysis, GLMM, R statistical environmentAbstract
Data analysis in community ecology often has certain difficulties, since standard parametric methods are inapplicable due to the fact that ecological data rarely normal distributed, there are no linear relationships between variables, there may be collinearity between explanatory variables and overdispersion in data sets. The proposed article considers an approach based on the use of regression generalized linear mixed models (GLMM), which allows analyzing data from synecological studies taking into account the above difficulties, as well as including not only quantitative but also qualitative predictors in the analysis. Using our own results of studies of ground beetle assemblages in several types of forests, the stages of GLMM implementation in the R statistical environment are demonstrated. A simple program code for GLMM is proposed, available for use by novice researchers. The protocol for exploratory data analysis is considered in detail, the use of appropriate packages, including lme4, performance, car, etc. is justified.
References
- Shitikov VK, Mastitskiy SE. Klassifikatsiya, regressiya i drugiye algoritmy Data Mining s ispol’zovaniyem R [Classification, Regression and Other Data Mining Algorithms Using R]. [Place unknown]: Elektronnaya kniga; 2017. 351 р. Russian.
- Legendre P, Legendre L. Numerical Ecology. 3rd edition. Amsterdam: Elsevier Science. BV; 2012. 990 p.
- Kabacov RI. R in Action. Data analysis and graphics with R. Shelter Island, New York: Manning Publications Co.; 2012. 580 р.
- Borcard D, Gillet F, Legendre P. Numerical Ecology with R. Wien: Springer Nature; 2011. 319 p.
- McCune B, Grace JB. Analysis of ecological communities. Gleneden Beach: MjMSoftware Design; 2002. 304 p.
- Mastitskiy SE, Shitikov VK. Statisticheskiy analiz i vizualizatsiya dannykh s pomoshch’yu R [Statistical analysis and data visualization using R]. Moscow: DMK Press; 2015. 496 p. Russian.
- Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2nd edition. New York: Springer; 2009. 745 p.
- Zuur AF, Ieno EN, Walker N, Saveliev, AA, Smith GM. Mixed Effects Models and Extensions in Ecology With R. New York: Springer; 2009. 574 р.
- Zuur AF, Ieno EN, Smith GM. Analyzing Ecological Data. New York: Springer; 2007. 672 р.
- Faraway JJ. Extending the linear model with R: generalized linear, mixed effects and nonparametric regression models. Volume 124. Chapman & Hall/CRC Taylor & Francis Group; 2017. 331 р.
- Chetverikov AA, Lineynyye modeli so smeshannymi effektami v kognitivnykh issledovaniyakh [Linear models with mixed effects in cognitive research]. Rossiyskiy zhurnal kognitivnoy nauki. 2015;2(1):41–51. Russian.
- R Development Core Team (2024) R: A language and environment for statistical computing. R Foundation for Statistical Computing. [Internet, cited 2024 December 12]. Vienna: Austria. Available from: https://www.R-project.org.
- Bates D, Maechler M, Bolker B, Walker S. Fitting linear mixed-effects models using lme4. Journal of Statistical Software. 2015;67:1–48.
- Zuur AF, Ieno EN, Elphick CS. A protocol for data exploration to avoid common statistical problems. Methods of Ecology and Evolution. 2010;1:3–14.
