bootStat-methods: Bootstrap statistics functions
In complmrob: Robust Linear Regression with Compositional Data as Covariates

Description Usage Arguments Details References See Also

Functions to calculate the coefficient(s) of the robust linear regression model from a bootstrapped sample

bootStatResiduals(residData, inds, coefind, intercept = TRUE,
  maxTries = 4L, control)

bootStatCases(origData, inds, coefind, formula, maxTries = 4L, control)

bootStatFastControl(model)

bootStatFast(origData, inds, control, coefind)

`residData`	the original data set with the columns fit, resid and the predictor variables instead of the response variable.
`inds`	the resampled indices.
`coefind`	the index of the coefficient to extract.
`intercept`	if the model includes an intercept term.
`maxTries`	the maximum number of tries to increase the maxit control arguments for the S estimator.
`control`	either the control object as returned by `bootStatFastControl` (for 'bootStatFast') or the control object used to fit the model(s) with 'lmrob'.
`origData`	the original data set.
`formula`	the formula to fit the model
`model`	The lmrob model

Different approaches for bootstrapping have been implemented. The default "fast and robust bootstrap" (FRB) proposed by M. Salibian-Barrera, et al. (2002), implemented with bootStatFast is the fastest and most resistant to outliers, while the other two bootStatResiduals and bootStatCases are standard bootstrap methods, where the residuals resp. the cases are resampled and the model is fit to this data.

M. Salibian-Barrera, S. Aelst, and G. Willems. Fast and robust bootstrap. Statistical Methods and Applications, 17(1):41-71, 2008.

bootcoefs

complmrob documentation built on Sept. 18, 2019, 1:02 a.m.