Modelos mixtos aplicados a la productividad de hojarasca
Mixed models applied to the litterfall productivity
Abstract (en)
A methodology is developed to adjust a linear mixed model incorporating a variancecovariance structure starting from a the classical linear regression model following Zuur strategy, Zuur et al. (2009). Different diagnostic plots of residuals and likelihood ratio tests are used to choose fixed and random effects and to find an appropriate covariance structure to capture the heteroskedasticity and serial correlation of model residuals. Ecological data from Murcia (2013) research around the river basin Pamplonita (Norte de Santander, Colombia) are used in this paper, different measurements are taken in the high Andean and sub-Andean forests. The weight of litter fallen from 40 collectors located in two forest was quantified for 12 months. This data are analyzed using mixed models.
Abstract (es)
Se propone una metodología para realizar un ajuste de un modelo lineal mixto incorporando una estructura de varianza y de correlación serial adecuada partiendo desde el modelo de regresión lineal clásico siguiendo la estrategia de Zuur et al. (2009). Se utilizan diferentes gráficos de diagnóstico de los residuales y pruebas de razón de verosimilitud a fin de garantizar que la inclusión de determinados efectos fijos y aleatorios esté justificado e igualmente para hallar una estructura de varianzas y covarianzas que permita capturar la heteroscedasticidad y la correlación serial de los residuales del modelo. Se utilizan datos ecológicos tomados de un estudio llevado a cabo por Murcia (2013) en los alrededores de la cuenca del rio Pamplonita (Norte de Santader, Colombia), en dicho estudio se tomaron diferentes mediciones en los bosque altoandino y subandino, el peso de caída de hojarasca de 40 colectores ubicados en los dos bosques es cuantificado durante doce meses. Estos datos son analizados utilizando modelos mixtos.
References
Davis, C. (2002), Statistical Methods for the Analysis of Repeated Measurements, Springer.
Fitzmaurice, G. (2008), Longitudinal Data Analysis, Chapman and Hill.
Gelman, A. (2007), Data Analysis Using Regression and Multilevel/Hierarchical Models, Cambridge University Press, New York.
Laird, N. M. & Ware, J. H. (1982), ‘Random effects models for longitudinal data’, Biometrics 38(4), 963–974.
Murcia, A. (2013), ‘Respiración del suelo en una comunidad sucesional de pastizal del bosque altoandino en la cuenca del río pamplonita’, Caldasia 30(2), 337– 353.
Pinheiro, J., Bates, D., DebRoy, S., Sarkar, D. & R Core Team (2014), nlme: Linear and Nonlinear Mixed Effects Models, http://cran.r-project.org/package=nlme edn.
Rao, C. R. (1973), Linear statistical inference and its applications, Wiley, New York.
Verbeke, G. & Molenberghs, G. (2000), Linear Mixed Model for Longitudinal Data, Springer, New York.
Zuur, A., Ieno, E., Walker, N., Saveliev, A. & Smith, G. (2009), Mixed Effects Models and Extensions in Ecology with R, Springer, New York.
How to Cite
License
The authors maintain the rights to the articles and therefore they are free to share, copy, distribute, execute and publicly communicate the work under the following conditions:
Recognize the credits of the work in the manner specified by the author or licensor (but not in a way that suggests that, you have their support or that they support your use of their work).
Comunicaciones en Estadística is licensed under Creative Commons Atribución-NoComercial-CompartirIgual 4.0 Internacional (CC BY-NC-SA 4.0)
Universidad Santo Tomás preserves the patrimonial rights (copyright) of the published works, and favors and allows the reuse of them under the aforementioned license.
