Chapter 4 Exploring Data Analysis: Univariate Graphs

We are now going to conduct exploratory data analysis (EDA). When exploring data, it isn’t unusual to generate many graphs to look at a dataset. We want to better understand our data, so all your code and graphs should be geared towards that purpose. While we aren’t worried about creating publication-ready graphs, we do want to develop good habits, so you will learn how to label graphs for easier reading.

EDA is an important part of data analysis. You can use EDA to make discoveries about the world or, you can use EDA to ensure the quality of your data, asking questions about whether the data meets your standards or not. EDA is an iterative cycle that helps you understand what your data says. When you do EDA, you:

• Generate questions about your data
• Search for answers by visualizing, transforming, and/or modeling your data
• Use what you learn to refine your questions and/or generate new questions

Two types of questions help make discoveries within your data. These questions are:

1. What type of variation occurs within my variables? (univariate analysis)
2. What type of covariation occurs between my variables? (bivariate analysis)

We are going to start with question 1: univariate analysis. We will be looking at three types of graphs to explore one variable.

• For categorical data: the bar chart.
• For quantitative data: the histogram and the box plot.

In the next chapter, we will examine bivariate statistics.