What are some of the elementary remedial procedures to multicollinearity (VIF >= 10) in linear regression? We were told to simply just drop that particular independent variable, but someone else suggested we could center the predictor variables (ie., xi = Xi - Xbar). Can somebody explain why centering may also be appropriate in this case?(adsbygoogle = window.adsbygoogle || []).push({});

Thank you very much in advance!

**Physics Forums - The Fusion of Science and Community**

Dismiss Notice

Join Physics Forums Today!

The friendliest, high quality science and math community on the planet! Everyone who loves science is here!

The friendliest, high quality science and math community on the planet! Everyone who loves science is here!

# Regression analysis - case of multicollinearity

Loading...

Similar Threads for Regression analysis case | Date |
---|---|

A F-test regression test, when and how? | Sep 17, 2017 |

A Composing Likert "Subvariables" into a Single Variable | Jul 25, 2017 |

A Follow-Up on F-Test in Multi-Linear Regression | May 11, 2017 |

I How do I find the standardized coefficients? | Apr 3, 2017 |

A "Many-to-One" Mapping of Variables in Logistic Regression | Jan 8, 2017 |

**Physics Forums - The Fusion of Science and Community**