pimeta (version 1.0.1)

bootPI: A parametric bootstrap prediction interval (Nagashima et al., 2018)

Description

A parametric bootstrap prediction interval (Nagashima et al., 2018)

Usage

bootPI(y, sigma, alpha = 0.05, B = 25000, maxit1 = 1e+05,
  eps = 10^(-10), lower = 0, upper = 1000, maxit2 = 1000,
  tol = .Machine$double.eps^0.25)

Arguments

y

the effect size estimates vector

sigma

the within studies variances vector

alpha

the alpha level of the prediction interval

B

the number of bootstrap samples

maxit1

the maximum number of iteration for the exact distribution function of \(Q\)

eps

the desired level of accuracy for the exact distribution function of \(Q\)

lower

the lower limit of random numbers of \(\tau^2\)

upper

the lower upper of random numbers of \(\tau^2\)

maxit2

the maximum number of iteration for numerical inversions

tol

the desired level of accuracy for numerical inversions

Value

The average treatment effect estimate \(\hat{\mu}\) (muhat), and the lower and upper prediction limits \(\hat{c}_l\) (lbpi) and \(\hat{c}_u\) (ubpi).

References

Nagashima, K., Noma, H., and Furukawa, T. A. (2018). Prediction intervals for random-effects meta-analysis: a confidence distribution approach. Stat Methods Med Res. In press. https://arxiv.org/abs/1804.01054.

Examples

# NOT RUN {
data(sbp, package = "pimeta")
set.seed(20161102)
# }
# NOT RUN {
pimeta::bootPI(sbp$y, sbp$sigmak, B = 50000)
# }
# NOT RUN {
# $muhat
# [1] -0.3340597
# $lbpi
# [1] -0.8768976
# $ubpi
# [1] 0.2248231
# }