Introduction and Needed Packages

Now that we’re equipped with data visualization skills, data wrangling skills, and an understanding of how to import data and the concept of a tidy data format, let’s now proceed with data modeling. The fundamental premise of data modeling is to make explicit the relationship between:

• An outcome variable $𝑦$, also called a dependent variable or response variable

• An explanatory/predictor variable $𝑥$, also called an independent variable or covariate.

Another way to state this is using mathematical terminology. We’ll model the outcome variable $y$as a function of the explanatory/predictor variable $𝑥$. When we say “function” here, we aren’t referring to functions in R like the ggplot() function, but rather as a mathematical function. However, why do we have two different labels, explanatory and predictor, for the variable $𝑥$? That’s because even though the two terms are often used interchangeably, roughly speaking, data modeling serves one of two purposes:

1. Modeling for explanation: When we want to explicitly describe and quantify the relationship between the outcome variable $𝑦$ and a set of explanatory variables $𝑥$, we have to determine the significance of any relationships. We have measures that’ll summarize these relationships, and possibly identify any causal relationships between the variables.

2. Modeling for prediction: When we want to predict an outcome variable $𝑦$ based on the information contained in a set of predictor variables $𝑥$. However, unlike modeling for explanation, we don’t care so much about understanding how all the variables relate and interact with one another. Our focus is on whether we can make good predictions about $𝑦$ using the information in $𝑥$.