speed_boot_par {hmmr} | R Documentation |
speed boot par
Description
Example of a parametric bootstrap for paraneter inference
Usage
data("speed_boot_par")
Format
A boot
object
Details
The bootstrap sample was generated by the following code:
require(depmixS4) require(hmmr) require(boot) data(speed1) set.seed(5) spmix2 <- mix(RT~1, data=speed1, nstates=2) fspmix2 <- fit(spmix2,verbose=FALSE) # define a function to produce a bootstrap sample speed.rg <- function(data,mle) { simulate(data) } # define what to do with a sample (i.e. estimate parameters) speed.fun <- function(data) { getpars(fit(data,verbose=FALSE,emcontrol= em.control(random.start=FALSE))) } # produce 1000 bootstrap samples (may take some time!) speed_boot_par <- boot(fspmix2,speed.fun,R=1000,sim="parametric", ran.gen = speed.rg)
Examples
data(speed_boot_par)
# confidence intervals
confint <- apply(speed_boot_par$t,2,quantile,probs=c(.025,.975))
colnames(confint) <- c("p1","p2","m1","sd1","m2","sd2")
confint
[Package hmmr version 1.0-0 Index]