The following sources discuss the issues generally and may be a goof
pointer to the literature on VIF. Particularly the Schroeder paper.
@article{Yi:Evaluation,
AUTHOR = {Youjae Yi},
TITLE = {On the Evaluation of Main Effects in Multiplicative
Regression Models.},
JOURNAL = {Journal of the Market Research Society},
VOLUME = {31},
NUMBER = {1},
MONTH = {January},
YEAR = {1989},
PAGES = {133-138}
}
@article{Gordon:Issues,
AUTHOR = {Robert A. Gordon},
TITLE = {Issues in Multiple Regression},
JOURNAL = {American Journal of Sociology},
VOLUME = {73},
NUMBER = {5},
MONTH = {March},
YEAR = {1968},
PAGES = {592-616}
}
@misc{Lynch:Multicollinearity,
author = {Scott M. Lynch},
title = {Multicollinearity},
year = {2003},
url = {\url{
http://www.princeton.edu/~slynch/soc504/multicollinearity.pdf}},
note = "[Online; accessed 11-October-2013]"
}
@article{Schroeder:Multicollinearity,
AUTHOR = {Mary Ann Schroeder
and Janice Lander
and Stacey Levine-Silverman},
TITLE = {Diagnosing and Dealing with Multicollinearity},
JOURNAL = {Western Journal of Nursing Research},
VOLUME = {12},
NUMBER = {2},
YEAR = {1990},
PAGES = {175-187}
}
@book{Afifi:Computer,
AUTHOR = {A. Afifi and V. Clark},
TITLE = {Computer-aided Multivariate Analysis},
PUBLISHER = {Wadsworth, Belmont California},
YEAR = {1984}
}
On Sun, Jul 26, 2015 at 5:00 PM, Wensui Liu <liuwensui at gmail.com>
wrote:
> Dear All
> I have a general question about VIF.
> While there are multiple rules of thumb about the threshold value of
> VIF, e.g. 4 or 10, implying multicollinearity, I am wondering if
> anyone can point me to some literature supporting these rules of
> thumb.
>
> Thank you so much!
> wensui
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
[[alternative HTML version deleted]]