Heteroskedasticity Diagnostics for Linear Regression Models
Implements numerous methods for detecting heteroskedasticity
(sometimes called heteroscedasticity) in the classical linear regression
model. These include a test based on Anscombe (1961)
< https://projecteuclid.org/ euclid.bsmsp/1200512155>, Ramsey's (1969)
BAMSET Test , the tests of Bickel
(1978) , Breusch and Pagan (1979)
with and without the modification
proposed by Koenker (1981) , Carapeto and
Holt (2003) , Cook and Weisberg (1983)
(including their graphical methods), Diblasi
and Bowman (1997) , Dufour, Khalaf,
Bernard, and Genest (2004) , Evans and
King (1985) and Evans and King (1988)
, Glejser (1969)
as formulated by
Mittelhammer, Judge and Miller (2000, ISBN: 0-521-62394-4), Godfrey and
Orme (1999) , Goldfeld and Quandt
(1965) , Harvey (1976)
, Honda (1989)
, Horn (1981)
, Li and Yao (2019)
with and without the modification of
Bai, Pan, and Yin (2016) , Rackauskas and
Zuokas (2007) , Simonoff and Tsai (1994)
with and without the modification of Ferrari,
Cysneiros, and Cribari-Neto (2004) ,
Szroeter (1978) , Verbyla (1993)
, White (1980)
, Wilcox and Keselman (2006)
, and Zhou, Song, and Thompson (2015)
. Besides these heteroskedasticity tests, there are
supporting functions that compute the BLUS residuals of Theil (1965)
, the conditional two-sided p-values of
Kulinskaya (2008) , and probabilities for the
nonparametric trend statistic of Lehmann (1975, ISBN: 0-816-24996-1).
Homoskedasticity refers to the assumption of constant variance that is
imposed on the model errors (disturbances); heteroskedasticity is the
violation of this assumption.