prep_MRF_covariates_spatial: Cross-multiply response and covariate variables and build...
In nicholasjclark/MRFcov: Markov Random Fields with Additional Covariates

View source: R/prep_MRF_covariates_spatial.R

prep_MRF_covariates_spatial

R Documentation

Cross-multiply response and covariate variables and build spatial splines

Description

This function performs the cross-multiplication necessary for prepping datasets to be used in MRFcov_spatial models.

Usage

prep_MRF_covariates_spatial(data, n_nodes, coords)

Arguments

`data`	Dataframe. The input data where the `n_nodes` left-most variables are outcome variables to be represented by nodes in the graph
`n_nodes`	Integer. The index of the last column in data which is represented by a node in the final graph. Columns with index greater than n_nodes are taken as covariates. Default is the number of columns in data, corresponding to no additional covariates
`coords`	A two-column `dataframe` (with `nrow(coords) == nrow(data)`) representing the spatial coordinates of each observation in `data`. Ideally, these coordinates will represent Latitude and Longitude GPS points for each observation. The coordinates are used to create smoothed Gaussian Process spatial regression splines via `smooth.construct2`. Here, the basis dimension of the smoothed term is chosen based on the number of unique GPS coordinates in `coords`. If this number is less than `100`, then this number is used. If the number of unique coordiantes is more than `100`, a value of `100` is used (this parameter needs to be large in order to ensure enough degrees of freedom for estimating 'wiggliness' of the smooth term; see `choose.k` for details).

Details

Observations of nodes (species) in data are prepped for MRFcov_spatial analysis by multiplication. This function is useful if users wish to prep the spatial splines beforehand and split the data manually for out-of-sample cross-validation. To do so, prep the splines here and set prep_splines = FALSE in MRFcov_spatial