hadivalues: Hadi's influence measure
In abnormally-distributed/cvreg: Cross Validation and Robust Estimation Utilities

Description Usage Arguments Value References

Hadi's measure is based on the fact that influential observations can be present as either regression outliers in the response variable, leverage points in the design matrix, or even both. Motivated for similar reasons as Scwheppe weights, Hadi's measure allows for identification of observations that are in some way unduly influential on a regression fit. This can be used for linear models as well as generalized linear models fit with lm() or glm().

1	hadivalues(fit, plot = T)

`fit`	the model fit (can be an lm or glm object)
`plot`	if TRUE (the default) a plot is generated. Otherwise, a vector of the Haidi Values is returned.

a plot or a vector.

Hadi, A. S. (1992). A new measure of overall potential influence in linear regression. Computational Statistics & Data Analysis, 14(1), 1–27. doi:10.1016/0167-9473(92)90078-t

Chatterjee, S. and Hadi, A. (2012) Regression Analysis by Example. 5th ed.

abnormally-distributed/cvreg documentation built on May 3, 2020, 3:45 p.m.