ci.bisection: Bisection method for constructing confidence intervals
In conroylau/lpinfer: An R Package for Inference in Linear Programs

ci.bisection

R Documentation

Bisection method for constructing confidence intervals

This function constructs the two-sided confidence interval of a given testing procedure using the bisection method.

ci.bisection(
  f,
  farg,
  alpha,
  b0,
  b1,
  tol,
  max.iter,
  pvals,
  progress,
  type,
  dp,
  rngstate,
  para.match
)

`f`	The function that represents a testing procedure.
`farg`	The list of arguments to be passed to the function of testing procedure.
`alpha`	The significance level(s). This can be a vector.
`b0`	The lower bound of the initial bracket.
`b1`	The upper bound of the initial bracket.
`tol`	The tolerance level in the bisection method.
`max.iter`	The maximum number of iterations in the bisection method.
`pvals`	The data frame that consists the points and the corresponding p-values that have been tested in the previous iterations.
`progress`	The boolean variable for whether the result messages should be displayed in the procedure of constructing confidence interval. If it is set as `TRUE`, the messages are displayed throughout the procedure. Otherwise, the messages will not be displayed.
`type`	The type of the confidence interval. Set `type` as 1 for the upper bound of the confidence interval and set `type` as -1 for the lower bound of the confidence interval.
`dp`	The number of decimal places to be displayed for the p-values and confidence intervals in the messages if `progress` is set as `TRUE`.
`rngstate`	The current RNG state obtained from `.Random.seed`.
`para.match`	The list of parameters to be matched.

Return the solution of the bisection method and the updated data frame.

`pt`	The last test point.
`iter`	The number of iterations.
`pvals`	The data frame that consists of the points and the corresponding p-values that have been tested in constructing the confidence intervals.
`df_bis`	The data frame storing the information for the bisection method in each iteration.
`last_iter_msg`	The message for the last iteration. This refers to whether why the bisection method stops.