update_rm: Perform one update using Robbins-Monro search process

View source: R/utils.R

update_rmR Documentation

Perform one update using Robbins-Monro search process

Description

update_rm performs one update using Robbins-Monro search process

Usage

update_rm(method, init, thetahat, t, tstar, alpha, i, m, k, Ps, bound)

Arguments

method

if method = 'G' (default), then search is carried out as described in Garthwaite (1996). For longer searches (nperm >= 200,000), method = 'GJ' is recommended and carried out as outlined in Garthwaite and Jones (2009).

init

initial (or most recent) estimate (e.g. L_i or U_i)

thetahat

point estimate of theta (parameter of interest) based on original data

t

test statistic for new permutation

tstar

test statistic for original permutation

alpha

corresponds to 100(1 - alpha)% CI

i

iteration of the search process

m

an optional initial magnitude of the steps; if left unspecified, m defaults to recommended value proposed in Garthwaite and Buckland (1992)

k

step length multiplier

Ps

if method = 'GJ', vector of search lengths for each phase (if unspecified, defaults to recommended values in Garthwaite and Jones (2009))

bound

"lower" or "upper"; i.e. which confidence bound you want

Details

This function inputs values necessary to perform one update using the Robbins-Monro search procedure specific to confidence intervals proposed by Garthwaite (1996) (for method = 'G') and Garthwaite and Jones (2009) (for method = 'GJ'). This is a general utility function called within the confidence interval functions (e.g permci_glm()).


djrabideau/permuter documentation built on Jan. 9, 2025, 11:45 p.m.