surveillance (version 1.12.1)

twinSIR_profile: Profile Likelihood Computation and Confidence Intervals

Description

Function to compute estimated and profile likelihood based confidence intervals. Computations might be cumbersome!

Usage

## S3 method for class 'twinSIR':
profile(fitted, profile, alpha = 0.05,
        control = list(fnscale = -1, factr = 10, maxit = 100), ...)

Arguments

fitted

an object of class "twinSIR".

profile

a list with elements being numeric vectors of length 4. These vectors must have the form c(index, lower, upper, gridsize). [object Object],[object Object],[object Object]

alpha

$(1-\alpha) 100%$ profile likelihood based confidence intervals are computed. If alpha <= 0<="" code="">, then no confidence intervals are computed.

control

control object to use in optim for the profile log-likelihood computations.

...

unused (argument of the generic).

Value

• list with profile log-likelihood evaluations on the grid and highest likelihood and Wald confidence intervals. The argument profile is also returned.

encoding

latin1

Examples

if (surveillance.options("allExamples")) {
  data("foofit")
  prof <- profile(foofit, list(c(1,NA,NA,5), c(3,NA,NA,0), c(4, 0.5, 1.1, 10)))
  prof

  ## there is also a plot-method for "profile.twinSIR"
  plot(prof)
}