ltsbase: Ridge and Liu Estimates based on LTS Method

In ltsbase: Ridge and Liu Estimates based on LTS (Least Trimmed Squares) Method

Description

Returns the estimates of the Ridge and Liu parameters based on LTS Method.

Usage

ltsbase(xdata, y, print = FALSE, plot = FALSE, alpha = 0.5, by = 0.001)

Arguments

xdata	a data frame of predictors.
y	response variable.
print	if TRUE then the user may see all the calculation results.
plot	if TRUE then the lines of all MSE values versus biasing parameters are plotted.
alpha	the percentage of squared residuals whose sum will be minimized.
by	the increment of the sequence with default 0.001.

Value

list.mse	a list of the minimum MSE values. The MSE values are computed in the sequence of the biasing parameter for each regression model.
list.bias.par	list of the biasing parameters at the minimum MSE values obtained by list.mse.
list.coef.all	coefficients of the models at the corresponding biasing parameters obtained by list.bias.par and the coefficients of the OLS and LTS as well.

Source

B. Kan, O. Alpu, B. Yazici (2013) Robust ridge and Liu estimator for regression based on the LTS estimator. Journal of Applied Statistics. 40(3), 644-655.

References

G. Pison, S. Van Aelst, and G. Willems (2002) Small sample corrections for LTS and MCD, Metrika, 55, 111-123.

P.J. Rousseeuw (1983) Multivariate estimation with high breakdown point, The Fourth Pannonian Symposium on Mathematical Statistics and Probability, Bad Tatzmannsdorf, Austria.

P.J. Rousseeuw and A. M. Leroy (1987) Robust Regression and Outlier Detection, Wiley, New York.

P.J. Rousseeuw and K. Van Driessen (1999) Computing LTS regression for large data sets, Tech. Rep., Statistics Group, University of Antwerp, Antwerp, Belgium.

See Also

ltsbaseSummary, ltsbaseDefault

Examples

data(hbk)
y=hbk[,4]
xdata=data.frame(hbk[,1:3])
model=ltsbase(xdata, y, print=FALSE, plot=TRUE, alpha=0.875, by=0.001)

ltsbase documentation built on May 2, 2019, 8:31 a.m.