*76*

Logistic Regression is a statistical method that we use to fit a regression model when the response variable is binary.Â ToÂ assess how well a logistic regression model fits a dataset, we can look at the following two metrics:

**Sensitivity:Â**The probability that the model predicts a positive outcome for an observation when indeed the outcome is positive.**Specificity:Â**TheÂ probability that the model predicts a negative outcome for an observation when indeed the outcome is negative.

One easy way to visualize these two metrics is by creating aÂ **ROC curve**, which is a plot that displays the sensitivity and specificity of a logistic regression model.

This tutorial explains how to create and interpret a ROC curve in R using the ggplot2 visualization package.

**Example: ROC Curve Using ggplot2**

Suppose we fit the following logistic regression model in R:

#loadDefaultdataset from ISLR book data #divide dataset into training and test set set.seed(1) sample TRUE, FALSE), nrow(data), replace=TRUE, prob=c(0.7,0.3)) train #fit logistic regression model to training set model binomial", data=train) #use model to make predictions on test set predicted response")

To visualize how well the logistic regression model performs on the test set, we can create a ROC plot using theÂ **ggroc()** function from the pROC package:

#load necessary packages library(ggplot2) library(pROC) #define object to plot rocobj #create ROC plot ggroc(rocobj)

The y-axis displays the sensitivity (the true positive rate) of the model and the x-axis displays the specificity (the true negative rate) of the model.

Note that we can add some styling to the plot and also provide a title that contains the AUC (area under the curve) for the plot:

#load necessary packages library(ggplot2) library(pROC) #define object to plot and calculate AUC rocobj round(auc(test$default, predicted),4) #create ROC plot ggroc(rocobj, colour = 'steelblue', size = 2) + ggtitle(paste0('ROC Curve ', '(AUC = ', auc, ')'))

Note that we can also modify the theme of the plot:

#create ROC plot with minimal theme ggroc(rocobj, colour = 'steelblue', size = 2) + ggtitle(paste0('ROC Curve ', '(AUC = ', auc, ')')) + theme_minimal()

Refer to this article for a guide to the best ggplot2 themes.