REL_mean_CI: Profile a confidence interval for a one-dimensional mean...

In hoangtt1989/BICEP: Bi-linear algorithm for composite empirical likelihood

Description

Profile a confidence interval for a one-dimensional mean using either REL or EL

Usage

REL_mean_CI(data_mat, q = NULL, conf_level = 0.05, test_thresh = "chisq",
  upper_break = NULL, lower_break = 1e-06, upper_divide = 5,
  upper_increase = 0.1, left_algorithm = c("REL", "EL"),
  right_algorithm = c("REL", "EL"), ..., verbose = F)

Arguments

data_mat	a matrix of the data with observations in rows and variables in columns.
q	an integer specifying the number of detected outliers. Default is floor(.1 * n).
conf_level	the confidence level.
test_thresh	a string specifying the calibration type. Only the chi-squared approximation is currently implemented.
upper_break	the initial guess for the upper limit for root finding. Default uses a value based on the magnitude of the MLE.
lower_break	the initial guess for the lower limit for root finding.
upper_divide	divide the MLE by this much for upper_break.
upper_increase	increase the initial guess for the upper limit by this amount.
left_algorithm	the algorithm for the left confidence limit.
right_algorithm	the algorithm for the right confidence limit.
...	additional arguments passed to REL_fixed.
verbose	a boolean to allow console output.

Value

A list with confidence interval attributes.

hoangtt1989/BICEP documentation built on May 28, 2019, 3:37 p.m.