MGSC 372 Lecture Notes - Lecture 8: Variance Inflation Factor, Multicollinearity, Correlation And Dependence
10 May 2017
School
Department
Course
Professor
Document Summary
The next slide shows how to calculate press for the model with variables (cid:2871) and (cid:2872). Observation data: values of independent variable are uncontrolled. Experimental data: values of independent variable are controlled via a designed experiment. The variables advert, special, and place are experimental variables. The general manager decides how much advertising budget to allocate to each store, and how many in-house specials to assign. He also selects stores in montreal and toronto. The variable size is observational we assume that the stores sampled are already in business and the manager has no control over the size of the random sample of stores selected in the two locations. Variable values can be assigned in such a way that independent variables are not correlated so that multicollinearity can be eliminated. For example, we saw that the variables advert and special were designed to have zero correlation. Randomization can be controlled by assigning a desired range of values to the independent variables.
