lad.fit-methods function

Fit a least absolute deviation (LAD) regression model

Fits a linear model using LAD methods, returning the bare minimum computations.

lad.fit.BR(x, y, tol = 1e-7)
lad.fit.EM(x, y, tol = 1e-7, maxiter = 200)

Arguments

• x, y: numeric vectors or matrices for the predictors and the response in a linear model. Typically, but not necessarily, x will be constructed by one of the fitting functions.
• tol: the relative tolerance for the iterative algorithm. Default is tol = 1e-7.
• maxiter: The maximum number of iterations for the EM method. Default to 200.

Returns

The bare bones of a lad object: the coefficients, residuals, fitted values, and some information used by summary.lad.

See Also

lad, lad.fit, lm

Examples

x <- cbind(1, stack.x)
z <- lad.fit.BR(x, stack.loss)
z