Visualization the Effects of Collinearity in Distributed Lag Models and Other Linear Models

Tool to assessing whether the results of a study could be influenced by collinearity. Simulations under a given hypothesized truth regarding effects of an exposure on the outcome are used and the resulting curves of lagged effects are visualized. A user's manual is provided, which includes detailed examples (e.g. a cohort study looking for windows of vulnerability to air pollution, a time series study examining the linear association of air pollution with hospital admissions, and a time series study examining the non-linear association between temperature and mortality). The methods are described in Basagana and Barrera-Gomez (2021) .

collin

Collinearity can be a problem in regression models. When examining the effects of an exposure at different time points, constrained distributed lag models (https://CRAN.R-project.org/package=dlnm) can alleviate some of the problems caused by collinearity. Still, some consequences of collinearity may remain and they are often unexplored. This package is a tool to assess whether unexpected results of a study could be influenced by collinearity. Essentially, the package provides a graphical comparison of the effects estimated in the real analysis with the effects estimates that would be obtained in a scenario with an alternative true pattern effect for the association of interest. The package can be also applied to regression models that do not include a distributed lag structure.

Getting started

• The last version released on CRAN can be installed within an R session by executing:

install.packages("collin")

• The package collin is available on the Comprehensive R Archive Network (CRAN), with info at the related web page https://CRAN.R-project.org/package=collin.

• Once the package has been installed, a summary of the main functions is available by executing:

help(collin)

• A comprehensive tutorial, including a number of detailed examples, is available by executing:

vignette("collin")

References

The methodology used in the package is described in

• Basagaña X, Barrera-Gómez J. Reflection on modern methods: visualizing the effects of collinearity in distributed lag models. International Journal of Epidemiology. 2021;51(1):334-344. DOI: 10.1093/ije/dyab179. URL: https://academic.oup.com/ije/article/51/1/334/6359467