Exercise

# Logistic regression with glm()

Linear regression and logistic regression are special cases of a broader type of models called *generalized linear models* ("GLMs"). A linear regression makes the assumption that the residuals follow a Gaussian (normal) distribution. By contrast, a logistic regression assumes that residuals follow a binomial distribution.

Here, you'll model how the length of relationship with a customer affects churn.

`churn`

is available.

Instructions

**100 XP**

- Fit a logistic regression of
`has_churned`

versus`time_since_first_purchase`

using the`churn`

dataset. Assign to`mdl_churn_vs_relationship`

.