Filter a set of correlated predictors to fewer onesSource:
This function helps to remove highly correlated variables from a set of predictors. It supports multiple options some of which require both environmental predictors and observations, others only predictors.
Some of the options require different packages to be pre-installed, such as
vectorwith variables to keep regardless. These are usually variables for which prior information is known.
Which method to use for constructing the correlation matrix (Options:
Other options for a specific method
vector of variable names to be excluded. If the
function fails due to some reason return
Available options are:
"none"No prior variable removal is performed (Default).
"kendall"Makes use of pairwise comparisons to identify and remove highly collinear predictors (Pearson's
r >= 0.7).
"abess"A-priori adaptive best subset selection of covariates via the
abesspackage (see References). Note that this effectively fits a separate generalized linear model to reduce the number of covariates.
Borutapackage to identify non-informative features.
Using this function on predictors effectively means that a separate model is fitted on the data with all the assumptions that come with in (e.g. linearity, appropriateness of response, normality, etc).