wrtdscv: Use k-fold cross-validation to evaluate WRTDS model fit

Description

Use k-fold cross-validation to evaluate WRTDS model fit based on supplied half-window widths.

Usage

wrtdscv(dat_in, ...)
# S3 method for default
wrtdscv(dat_in, wins, k = 10, seed_val = 123, trace = TRUE, ...)

Value

Overall error is the average of all errors for each fold.

Arguments

dat_in: input tidal or tidalmean object
...: arguments passed to wrtds or getwts, e.g., tau = 0.2 if a tidal object is used for dat_in
wins: list of input half-window widths of the order months, years, and salinity/flow, passed to getwts
k: number of folds to evaluate
seed_val: seed to keep the same dataset divisions between window width comparisons
trace: logical indicating if progress is printed in the console

Details

Default number of folds is ten. Each fold can be evaluated with multiple cores if a parallel back end is created prior to running the function (see the examples). This will greatly increase processing speed unless k is set to a small number.

Examples

Run this code

if (FALSE) {

library(doParallel)
ncores <- detectCores() - 1  
registerDoParallel(cores = ncores)

# half-window widths to evaluate
# months, years, and salinity/flow
wins <- list(0.5, 10, 0.5) 

# get ocv score for k = 10
wrtdscv(tidobjmean, wins = wins)

# get ocv score k = 2, tau = 0.2 
wrtdscv(tidobj, wins = wins, tau = 0.2)
}