LGDtoolkit (version 0.2.0)

kfold.vld: K-fold model cross-validation

Description

kfold.vld performs k-fold model cross-validation. The main goal of this procedure is to generate main model performance metrics such as absolute mean square error, root mean square error or R-squared based on resampling method. Note that functions' argument model accepts "lm" and "glm" class but for "glm" only "quasibinomial("logit")" family will be considered.

Usage

kfold.vld(model, k = 10, seed = 1984)

Value

The command kfold.vld returns a list of two objects.

The first object (iter), returns iteration performance metrics.

The second object (summary), is the data frame of iterations averages of performance metrics.

Arguments

model

Model in use, an object of class inheriting from "lm"

k

Number of folds. If k is equal or greater than the number of observations of modeling data frame, then validation procedure is equivalent to leave one out cross-validation (LOOCV) method. For LOOCV, R-squared is not calculated. Default is set to 10.

seed

Random seed needed for ensuring the result reproducibility. Default is 1984.

Examples

library(monobin)
library(LGDtoolkit)
data(lgd.ds.c)
#discretized some risk factors
num.rf <- c("rf_01", "rf_02", "rf_03", "rf_09", "rf_16")
for	(i in 1:length(num.rf)) {
num.rf.l <- num.rf[i]
lgd.ds.c[, num.rf.l] <- sts.bin(x = lgd.ds.c[, num.rf.l], y = lgd.ds.c[, "lgd"])[[2]]	
}
str(lgd.ds.c)
#run linear regression model
reg.mod.1 <- lm(lgd ~ ., data = lgd.ds.c[, c(num.rf, "lgd")])
summary(reg.mod.1)$coefficients
#perform k-fold validation
LGDtoolkit::kfold.vld(model = reg.mod.1 , k = 10, seed = 1984)
#run fractional logistic regression model
lgd.ds.c$lgd[lgd.ds.c$lgd > 1] <- 1
reg.mod.2 <- glm(lgd ~ ., family = quasibinomial("logit"), data = lgd.ds.c[, c(num.rf, "lgd")])
summary(reg.mod.2)$coefficients
LGDtoolkit::kfold.vld(model = reg.mod.2 , k = 10, seed = 1984)