Get startedGet started for free

Logistic probabilities

Predictions of a logistic regression model give the probability of receiving an outcome of 1, ignoring or specific to a group depending on the model specifications.

A company has gathered data on whether individuals clicked on an ad, Click, and wants to know about the amount of time spent on the site, TimeSearching in relation to clicking the ad. You ran a logistic regression and determined the model is a good fit when ignoring groups. The company is interested in the likelihood the ad will be clicked when spending 52 minutes on the site.

The webdata dataset and logmodel logistic regression model have been loaded for you.

This exercise is part of the course

A/B Testing in R

View Course

Exercise instructions

  • Store the data to predict, 52 minutes with the same naming scheme as the original data column, then store this object in a data frame named timepredict.
  • Determine the likelihood of the ad being likely to be clicked if 52 minutes are spent on the site using the model logmodel and the new timepredict data.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Store the data to predict
___
timepredict <- data.frame(___)

# Determine the likelihood of an ad being clicked
predict(___, newdata = ___, type = ___)
Edit and Run Code