Using logistic regression to derive odds ratios for categorical variables

OK, now, let’s make a logistic regression model for research question number 2: Are ST depression level, age, and cholesterol associated with the presence of CAD?

For this model, we will use the CAD status coded as 1 and 0 or yes/no variables. We will set ST depression, age, and serum cholesterol as the independent variables:

Figure 9.10 – CAD status prediction model with added serum cholesterol

This time, we will be using the binary logistic regression, because the dependent variable is a categorical binary variable coded as 1 and 0. Let’s see the code for this:

import pandas as pd
import statsmodels.api as sm
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
# Define the formula for logistic regression
formula = 'cad ~ oldpeak + age + chol'
# Create the logistic regression model
logit_model = sm.Logit.from_formula(formula...