sglr (version 0.8)

computeBoundary: A function to compute the boundary of the decision region in terms of the number of adverse events (AEs) of interest, such as vaccine AEs.

Description

This function computes the boundary of the decision region in a manner that can be employed in the field, as a table, for example. See section 4.2 of the reference below.

Usage

computeBoundary(b1, b0, p, glrTables = NULL, tol=1e-7)

Arguments

b1

The acceptance boundary value (corresponds to the boundary \(b_1\) in the appendix of reference)

b0

The rejection boundary value (corresponds to the boundary \(b_0\) in the appendix of reference)

p

The vector of probabilities, \((p_0, p_1)\) with \(p_0 < p_1\).

glrTables

A previously computed set of likelihood functions, to speed up computation for the same hypothesis testing problem. Otherwise, it is computed ab initio, resulting in a longer running time.

tol

A numerical tolerance, defaults to 1e-7

Value

upper

The upper boundary that indicates rejection of the null hypothesis

lower

The upper boundary that indicates acceptance of the null hypothesis

estimate

The estimated \(\alpha\) and \(\beta\) values corresponding to the two boundaries

Details

This essentially computes the probabilities of hitting the boundaries using a recursion.

References

``Sequential Generalized Likelihood Ratio Tests for Vaccine Safety Evaluation'' 10.1002/sim.4036.

See Also

See Also glrSearch

Examples

# NOT RUN {
computeBoundary(b1=2.8, b0=3.3, p=c(.5, .75))
# }