@article {10.3844/ojbsci.2024.195.207,
article_type = {journal},
title = {Comparison of Collinearity Indices for Linear Models in Agricultural Trials},
author = {Rivas, Danny Villegas and Sánchez, José M. Palacios and Rivero, Cristina A. Alzamora and Del Carpio, Carlos M. Franco and Carrera, César Osorio and Vasquez, Martin Grados and Calderón, Luis Ramírez and Rojas, Karin Ponce and Figueroa, José Jorge Rodríguez and Narrea, Felicia L. Cáceres and Pachas, Delia A. Saravia and Felipe, Arrieta Benoutt and Neyra Flores, Arturo N. and Zata Pupuche, Pedro E. and Falcón, Carlos Fabián and Chipana Fernández, Yolanda Maribel Mercedes and Rosas, Víctor Hugo Fernández and Polo, Francisco Alejandro Espinoza and Chunga Pingo, Gaby Esther and Merejildo Vera, Mercy Carolina and Cerna Muñoz, Carlos Alfredo and Miranda Diaz, Luis Orlando and Hernández López, Miguel Ángel and Vejarano Campos, Martín Desiderio and Bazán, Erick Delgado and Campaña, Zadith Garrido and Carranza, José Paredes and Ventura, Leyli J. Aguilar and Monroy Correa, Graciela M. and Chicana Becerra, Ruth A. and Barboza, Jhonny Richard Rodriguez and Quipas Bellizza, Mariella M. and Escudero Vilchez, Fernando Emilio and Salazar Llerena, Silvia Liliana},
volume = {24},
number = {2},
year = {2023},
month = {Dec},
pages = {195-207},
doi = {10.3844/ojbsci.2024.195.207},
url = {https://thescipub.com/abstract/ojbsci.2024.195.207},
abstract = {The deleterious consequences of collinearity in linear regression on the precision of estimators of regression coefficients and the interpretability of the fitted model are widely recognized. In this study, we compare several methodologies for assessing collinearity in linear models and explore the effect of outliers on collinearity. The robustness of collinearity measures (individual and overall) is validated through two detailed Monte Carlo simulation study which also considers the effect of outliers on collinearity indices. The methods are illustrated with two real-world agricultural and fish morphology l data sets to show potential applications. The results do not provide any evidence for an effect from outliers on collinearity identification using the collinearity indices (individual and overall). The FG and Fj collinearity indices more robust as both sample size and collinearity degree increase. The VIF (individual measure) had a better performance on the fitted model with a greater number of parameters.},
journal = {OnLine Journal of Biological Sciences},
publisher = {Science Publications}
}