Computing confidence intervals for the mipfp estimates
This function computes the (asymptotic) Wald confidence intervals at a given
significance level for the estimates of an mipfp object generated by
Estimate.
## S3 method for class 'mipfp' confint(object, parm, level = 0.95, prop = FALSE, ...)
object |
The |
parm |
A specification of which estimates are to be given confidence intervals, either a vector of numbers or a vector of names. If missing, all estimates are considered. |
level |
The confidence level required. |
prop |
A boolean indicating if the results should be using counts ( |
... |
Further arguments passed to or from other methods (for instance
|
The confidence interval of the estimates X.hat, at significance level α is given by
X.hat +/- z(1-α/2) * σ.hat
where σ.hat is the standart deviations of X.hat, z and α = 1 - level is the inverse of the cumulative distribution function of the standard normal distribution.
A matrix containing the upper and lower bounds for the estimated
counts/probabilities (depending on the value of the prop argument).
Johan Barthelemy.
Maintainer: Johan Barthelemy johan@uow.edu.au.
Smithson, M. (2002). Confidence intervals. Sage Publications.
confint for the default method to compute
confidence intervals for model parameters.
Estimate, Ipfp and
ObtainModelEstimates to generate the
mipfp objects for this function.
# true contingency (2-way) table true.table <- array(c(43, 44, 9, 4), dim = c(2, 2)) # generation of sample, i.e. the seed to be updated seed <- ceiling(true.table / 10) # desired targets (margins) target.row <- apply(true.table, 2, sum) target.col <- apply(true.table, 1, sum) # storing the margins in a list target.data <- list(target.col, target.row) # list of dimensions of each marginal constrain target.list <- list(1, 2) # using ipfp res <- Estimate(seed, target.list, target.data) # computing and printing the confidence intervals print(confint(res))
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.