r.squared {LGDtoolkit}

Coefficient of determination

Description

r.squared returns coefficient of determination for risk factors supplied in data frame db. Implemented algorithm processes numerical as well as categorical risk factor.
Usually, this procedure is applied as starting point of bivariate analysis in LGD model development.

Usage

r.squared(db, target)

Arguments

db

Data frame of risk factors and target variable supplied for bivariate analysis.

target

Name of target variable within db argument.

Value

The command r.squared returns the data frames with a following statistics: name of the processed risk factor (rf), type of processed risk factor (rf.type), number of missing and infinite observations (miss.inf), percentage of missing and infinite observations (miss.inf.pct), coefficient of determination (r.squared)

Examples

library(monobin)
library(LGDtoolkit)
data(lgd.ds.c)
r.squared(db = lgd.ds.c, target = "lgd")
#add categorical risk factor
lgd.ds.c$rf_03_bin <- sts.bin(x = lgd.ds.c$rf_03, y = lgd.ds.c$lgd)[[2]]
r.squared(db = lgd.ds.c, target = "lgd")
#add risk factor with all missing, only one complete case and zero variance risk factor
lgd.ds.c$rf_20 <- NA
lgd.ds.c$rf_21 <- c(1, rep(NA, nrow(lgd.ds.c) - 1))
lgd.ds.c$rf_22 <- c(c(1, 1), rep(NA, nrow(lgd.ds.c) - 2))
r.squared(db = lgd.ds.c, target = "lgd")