Add doc to describe variable inflation factor added to GLM

[exalate-issue-sync]

No description provided.

[exalate-issue-sync]

Wendy Wong commented: This is how the variable inflation factors are constructed:

The variable inflation factor for numerical predictor x is built as follows:

Set numerical predictor x as the response and use the same predictors as before except x.

Build a GLM regression model.

Take the R2 of the in 2 and the variable inflation factor is 1.0/(1.0-R2).

VIF can be calculated with cross-validation turned on.

Repeat the above for all the other numerical predictors to get the variable inflation factors for them as well.

[exalate-issue-sync]

Wendy Wong commented: Here is a good explanation of what VIF is:

h3. What is a Variation Inflation Factor?

As the name suggests, a variance inflation factor (VIF) quantifies how much the variance is inflated. But what variance? Recall that we learned previously that the standard errors — and hence the variances — of the estimated coefficients are inflated when multicollinearity exists. A variance inflation factor exists for each of the predictors in a multiple regression model. For example, the variance inflation factor for the estimated regression coefficient bj —denoted VIFj —is just the factor by which the variance of bj is "inflated" by the existence of correlation among the predictor variables in the model.

[h2o-ops]

JIRA Issue Details

Jira Issue: PUBDEV-8829
Assignee: hannah.tillman
Reporter: Wendy Wong
State: Resolved
Fix Version: 3.38.0.1
Attachments: N/A
Development PRs: Available

[h2o-ops]

Linked PRs from JIRA

#6314