8. Binary logistic regression models

Amy Atkinson

Lab preparation

Before the lab, please watch the following short video. This walks you through how to perform a binary logistic regression model in R.

If you want to have a play around with the script yourself, the R markdown script and dataset can be downloaded here.

Lab

Overview

Today I’ll provide you with one main research questions which will require you to complete the statistical test covered in the lecture. You can work in groups or individually.

You can write your script as a .R or Rmd file. Use the lab preparation video and script, lecture slides, and previous content covered in the statistics modules to help you.

The presentation given at the start of the lab can be downloaded here.

Datasets

The datasets for this lab can be downloaded here.

Main research Question

You are interested in whether the country an individual lives (UK/Australia) predicts reptile ownership (Yes/No). The dataset to use is “reptile_data.csv”

In the dataset, the outcome variable (reptile) is coded as “Y” and “N”:

  • Y = Yes
  • N = No

To make sure we should all end up with the same output, set UK as your reference category.

Optional extra dataset

I’ve also uploaded a second dataset (pen_colour.csv). If you finish the above analysis, you could have a go at performing a binary logistic regression model on tbis dataset as well. Alternatively, you could attempt this after the lab. The dataset (pen_colour.csv) can be downloaded using the link under the “Datasets” heading above.

Here, you are interested in whether pen colour (Black/Blue) predicts whether an individual passes their exam (Yes/No).

Set black as the reference category.

Hints and tips

Your script should aim to answer and interpret the research question above.

Start a new session on the server, then load in the required libraries (tidyverse, DescTools) and the dataset.

  1. Prepare our data for analysis
  2. Explore our data
  3. Run the binary logistic regression model
  4. Evaluate the model
  5. Evaluate the individual predictors
  6. Predicted probabilities
  7. Interpret the output

Model script

A model script showing one way of answering the reptile research question above using R will be available here from 9am on Monday of Week 19.

A model script showing one way of answering the (optional) pen research question will be available here from 9am on Monday of Week 19.

Feedback on student scripts

Here is feedback on the one valid student submission this week.

Back to top