Summary pooint

In this lecture, we covered

• Multicollinearity, this is when two or more explanatory variables are themselves related in an approximately linear way. The more correlation present between explanatory variables, then the more difficult it becomes to assess the amount of variation in the response variable explained by each explanatory variable.

• Selection criterion

  1. \(R^2\) or \(R^2\)adj

  2. Akaike Information Criterion (AIC) is defined as

  3. (Schwarz) Bayesian Information Criterion (BIC or sbc) is defined as

  4. Mallow’s \(C_p\) is defined as

• Search strategy

  1. All subset where we search all possible models.

  2. Stepwise selection where we begin with an initial model and systematically add or remove variables one at a time. We will discuss stepwise selection in the next lecture.