EUVIMEDEUVIMED entdecken
Crossref

Estimation and interpretation problems and solutions when using proportion covariates in linear regression models

Denis Valle iD, Jeffrey Mintz iD, Ismael Verrastro Brack iD

Ecology · 2024-04 · 105 (4)

DOI: 10.1002/ecy.4256 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ecology, online erschienen am 15.02.2024. Verfasst von Denis Valle und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Forest, Fisheries, and Geomatics Sciences, University of Florida, Gainesville, Florida, USA. Hauptthemen laut MEDLINE: Models, Statistical. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: NSF Division of Biological Infrastructure (DBI), National Institute of Food and Agriculture.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Proportion variables, also known as compositional data, are very common in ecology. Unfortunately, few scientists are aware of how compositional data, when used as covariates, can adversely impact statistical analysis. We describe here how proportion covariates result in multicollinearity and parameter identifiability problems. Using simulated data on bird species richness as a function of land use, we show how these problems manifest when fitting a wide range of models in R, both in a frequentist and Bayesian framework. In particular, we show that similar models can often generate substantially different parameter estimates, leading to very different conclusions. Dropping a covariate or the intercept from the model can solve the multicollinearity and parameter identifiability problems. Unfortunately, these solutions do not fix the inherent challenges associated with interpreting parameter estimates. To this end, we propose focusing the interpretation on the difference of slope parameters to avoid the inherent unidentifiability of individual parameters. We also propose conditional plots with two x ‐axes and marginal plots as visualization techniques that can help users better interpret their modeling results. We illustrate these problems and proposed solutions using empirical data from the North American Breeding Bird Survey. The practical and straightforward approaches suggested in this article will help the fitting of linear models and interpretation of its results when some of the covariates are proportions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Models, StatisticalLinear ModelsBayes Theorem

Stichwörter der Autor:innen

compositional covariatesconditional plotinferencelinear modelmarginal plotmulticollinearityparameter identifiabilityparameter interpretation

Autor:innen und Institutionen

  • School of Forest, Fisheries, and Geomatics Sciences, University of Florida, Gainesville, Florida, USA.
  • School of Natural Resources and Environment, University of Florida, Gainesville, Florida, USA.

ORCID-Profile: Denis Valle, Jeffrey Mintz, Ismael Verrastro Brack

Förderung

  • NSF Division of Biological Infrastructure (DBI)
  • National Institute of Food and Agriculture

Zitieren

APA

Valle, D., Mintz, J., & Brack, I. V. (2024). Estimation and interpretation problems and solutions when using proportion covariates in linear regression models. Ecology, 105(4). https://doi.org/10.1002/ecy.4256

Vancouver

Valle D, Mintz J, Brack IV. Estimation and interpretation problems and solutions when using proportion covariates in linear regression models. Ecology. 2024;105(4). doi:10.1002/ecy.4256

BibTeX
@article{Valle2024,
  author = {Valle, Denis and Mintz, Jeffrey and Brack, Ismael Verrastro},
  title = {Estimation and interpretation problems and solutions when using proportion covariates in linear regression models},
  journal = {Ecology},
  year = {2024},
  volume = {105},
  number = {4},
  doi = {10.1002/ecy.4256}
}
Kostenlos starten →