Exploratory Data Analysis

Directions

Today we will demonstrate our understanding of exploratory data analysis using a dataset of crawdads measured in Grinnell, IA. With a partner, investigate two questions:

1. How are the crawdads’ physical characteristics (sex, weight, and length) associated with one another?
2. How are physical characteristics associated with the presence of injuries?

For each question, choose which variables to examine and use graphical and numerical summaries to describe any associations you find. You are welcome to explore broadly, but your final report should include only the code, output, and explanations relevant to your two questions.

You and your partner will submit a single report to Gradescope. You may use resources from the course website, your homework, and your labs, but you may not use AI assistance.

---

A successful report will include the following:

Graphical Summaries

• Two plots, one for each question
• Plots should have appropriate labels for the axes and an appropriate title.
• A few sentences (2-3) interpreting each plot in the context of the questions asked

Numerical Summaries

• Provide an overview of the dataset such as the number of variables and observations
• Include at least one two-way table, along with an odds ratio OR conditional proportions to describe any association
• At least one grouped numerical summary using dplyr, along with a short description of that summary

General Information

• With all plots, tables, and written sentences, the final document shouldn’t exceed three pages (but it can be fewer)
• Don’t forget to add your name and your partner’s name at the top
• Include only code and output relevant to your questions; do not print the entire data frame
• Conclude with a few sentences answering both questions and describing the evidence for any associations (or lack of clear association) that you found.

Once you are finished, Knit the document to a PDF and assess whether or not it looks and reads like something you would feel comfortable sending to a professional collaborator. Once you are satisfied with your document, submit it to Gradescope.

An Rmd template with the data and proper formatting is provided here.