Learning Predictive Analytics with Python by 2016

Author:2016
Language: eng
Format: epub, mobi
Publisher: Packt Publishing

For a model with p possible predictor variables, there can be 2p-1 possible models; hence, as the number of predictors increases, the selection becomes tedious.

It would have been a tedious task to choose from so many possible models. Thankfully, there are a few guidelines to filter some of these and then navigate towards the most efficient one. The following are the guidelines:

Keep the variables with low p-values and eliminate the ones with high p-values

Inclusion of a variable to the model should ideally increase the value of R2 (although it is not a very reliable indicator of the same and looking at the adjusted R2 is preferred. The concept of adjusted R2 and why it is a better indicator than R2 will be explained later in this chapter).

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.