se.coef.dr {mable} | R Documentation |
Standard errors of coefficients in density ratio model
Description
Bootstrap estimates of standard errors for the regression coefficients which are estimated by maximum approximate Bernstein/Beta likelihood estimation method in a density ratio model based on two-sample raw data.
Usage
se.coef.dr(
obj,
grouped = FALSE,
B = 500L,
parallel = FALSE,
ncore = NULL,
controls = mable.ctrl()
)
Arguments
obj |
Class 'mable_dr' object return by |
grouped |
logical: are data grouped or not. |
B |
number of bootstrap runs. |
parallel |
logical: do parallel or not. |
ncore |
number of cores used for parallel computing. Default is half of availables. |
controls |
Object of class |
Details
Bootstrap method is used based on bootstrap samples generated from
the MABLE's of the densities f0 and f1. The bootstrap samples are fitted by
the Bernstein polynomial model and the glm()
to obtain bootstrap
versions of coefficient estimates.
Value
the estimated standard errors