• Kaixin Wang

Variable Selection, Modeling and Model Evaluation in Linear Regression

Updated: Jan 21

In this module, we will use the results from Exploratory Data Analysis (EDA) in the previous module and start building the linear regression model using Python.


Topics in this chapter include:


* variable selection

* build a linear model using two packages in Python: sklearn and statsmodel packages

* diagnostics plots of the model

* evaluation of the model based on criterion such as test root-mean-square error (RMSE) and adjusted R-squared

* comparison between different models





A PDF version of this tutorial can be accessed here.


©2019-2020 by the OSCR Project in UCLA