Using the wbca data in the faraway package. Fit a binary logistic regression model with Class as the response and the other variables as predictors. Find the best logistic regression model from it...

Load data set
#install.packages("faraway")
library(faraway)
## Warning: package 'faraway' was built under R version 4.2.2
data("wbca")
#Data summary
summary(wbca)
## Class Adhes BNucl Chrom
## Min. :0.0000 Min. : 1.000 Min. : 1.000 Min. : 1.000
## 1st Qu.:0.0000 1st Qu.: 1.000 1st Qu.: 1.000 1st Qu.: 2.000
## Median :1.0000 Median : 1.000 Median : 1.000 Median : 3.000
## Mean :0.6505 Mean : 2.816 Mean : 3.542 Mean : 3.433
## 3rd Qu.:1.0000 3rd Qu.: 4.000 3rd Qu.: 6.000 3rd Qu.: 5.000
## Max. :1.0000 Max. :10.000 Max. :10.000 Max. :10.000
## Epith Mitos NNucl Thick
## Min. : 1.000 Min. : 1.000 Min. : 1.000 Min. : 1.000
## 1st Qu.: 2.000 1st Qu.: 1.000 1st Qu.: 1.000 1st Qu.: 2.000
## Median : 2.000 Median : 1.000 Median : 1.000 Median : 4.000
## Mean : 3.231 Mean : 1.604 Mean : 2.859 Mean : 4.436
## 3rd Qu.: 4.000 3rd Qu.: 1.000 3rd Qu.: 4.000 3rd Qu.: 6.000
## Max. :10.000 Max. :10.000 Max. :10.000 Max. :10.000
## UShap USize
## Min. : 1.000 Min. : 1.00
## 1st Qu.: 1.000 1st Qu.: 1.00
## Median : 1.000 Median : 1.00
## Mean : 3.204 Mean : 3.14
## 3rd Qu.: 5.000 3rd Qu.: 5.00
## Max. :10.000 Max. :10.00
colnames(wbca)
## [1] "Class" "Adhes" "BNucl" "Chrom" "Epith" "Mitos" "NNucl" "Thick" "UShap"
## [10] "USize"
#Converting class into factor
wbca$Class=as.factor(wbca$Class)
summary(wbca)
## Class Adhes BNucl Chrom Epith
## 0:238 Min. : 1.000 Min. : 1.000 Min. : 1.000 Min. : 1.000
## 1:443 1st Qu.: 1.000 1st Qu.: 1.000 1st Qu.: 2.000 1st Qu.: 2.000
## Median : 1.000 Median : 1.000 Median : 3.000 Median : 2.000
## Mean : 2.816 Mean : 3.542 Mean : 3.433 Mean : 3.231
## 3rd Qu.: 4.000 3rd Qu.: 6.000 3rd Qu.: 5.000 3rd Qu.: 4.000
## Max. :10.000 Max. :10.000 Max. :10.000 Max. :10.000
## Mitos NNucl Thick UShap
## Min. : 1.000 Min. : 1.000 Min. : 1.000 Min. : 1.000
## 1st Qu.: 1.000 1st Qu.: 1.000 1st Qu.: 2.000 1st Qu.: 1.000
## Median : 1.000 Median : 1.000 Median : 4.000 Median : 1.000
## Mean : 1.604 Mean : 2.859 Mean : 4.436 Mean : 3.204
## 3rd Qu.: 1.000 3rd Qu.: 4.000 3rd Qu.: 6.000 3rd Qu.: 5.000
## Max. :10.000 Max. :10.000 Max. :10.000 Max. :10.000
## USize
## Min. : 1.00
## 1st Qu.: 1.00
## Median : 1.00
## Mean : 3.14
## 3rd Qu.: 5.00
## Max. :10.00
View(wbca)
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.2.2
library(GGally)
## Warning: package 'GGally' was built under R version 4.2.2
## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2
##
## Attaching package: 'GGally'
## The following object is masked from 'package:faraway':
##
## happy
ggpairs(wbca, aes(colour = "class", alpha = 0.4))
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
#install.packages("scatterPlotMatrix")
library(scatterPlotMatrix)
## Warning: package 'scatterPlotMatrix' was built under R version 4.2.2
scatterPlotMatrix(wbca, zAxisDim = "Class")
#---------------------------------------------------------------------------
#Checking distribution of dependent variable
ggplot(wbca, aes(factor(Class),
fill = factor(Class))) + geom_bar()
Class Adhes BNucl Chrom Epith Mitos NNucl Thick
C
lass
Adhes
BN
uclC
hrom
Epith
M
itos
N
N
ucl
Thick
Class Adhes BNucl Chrom Epith Mitos NNucl Thick
C
la
ss
Ad
he
s
BN
uc
l
C
hr
om
Ep
ith
M
ito
s
N
N
uc
l
Th
ic
k
NA NA NA NA NA NA NA
0100
200300
400
2 4 6 8 10
24
68
10
24
68
10
24
68
10
24
68
10
24
68
10
24
68
10
0 12
46
810
2 4 6 8 10 2 4 6 8 10 2 4 6 8 10 2 4 6 8 10 2 4 6 8 10 2 4 6 8 10
summary(wbca$Class)
## 0 1
## 238 443
Step 2: Train and test split
set.seed(1)
#Use 70% of dataset as training set and remaining 30% as testing set
sample <- sample(c(TRUE, FALSE), nrow(wbca), replace=TRUE, prob=c(0.7,0.3))
train <- wbca[sample, ]
test <- wbca[!sample, ]
Step 3 Fit the logistic regression model
full_model = glm(Class ~ ., data = train, family = "binomial")
summary(full_model)
##
## Call:
## glm(formula = Class ~ ., family = "binomial", data = train)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -2.57842 -0.01493 0.06474 0.11186 2.67502
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 10.41091 1.52178 6.841 7.85e-12 ***
## Adhes -0.12851 0.18290 -0.703 0.48230
## BNucl ...