Profile Likelihood Computation and Confidence Intervals

Function to compute estimated and profile likelihood based confidence intervals. Computations might be cumbersome! There is a simple plot-method for the result.

Usage

# S3 method for 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).

index:

index of the parameter to be profiled in the vector coef(fitted).

lower, upper:

lower/upper limit of the grid on which the profile log-likelihood is evaluated. Can also be NA in which case lower/upper equals the lower/upper bound of the respective 0.3 % Wald confidence interval (+-3*se).

gridsize:

grid size of the equally spaced grid between lower and upper. Can also be 0 in which case the profile log-likelihood for this parameter is not evaluated on a grid.

alpha

\((1-\alpha) 100\%\) profile likelihood based confidence intervals are computed. If alpha <= 0, 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

a list with profile log-likelihood evaluations on the grid and highest likelihood and Wald confidence intervals. The argument profile is also returned. The result has class "profile.twinSIR", for which a simple (undocumented) plot-method is available.

Author

Michael Höhle and Sebastian Meyer

Examples

data("hagelloch")
fit <- twinSIR(~ household, data = hagelloch)
gridsize <- if (interactive()) 35 else 5  # for fast tests
prof <- profile(fit, list(c(1, NA, NA, gridsize)))
prof$ci.hl
plot(prof)