Statistics and Data Science: A Modeling Approach

Part II: Modeling Variation

In this section of the course we develop the concept of statistical model. We start with the simplest model, sometimes called the “empty model.” From there we move to more complex models.

We create statistical models in order to:

  • Explain variation in an outcome variable using one or more explanatory variables, and to better understand the Data Generating Process;

  • Predict the values of future observations, or samples;

  • Guide changes we can make to improve the outcomes of the system we are studying.