mcap function

Monte Carlo adjusted profile

Given a collection of points maximizing the likelihood over a range of fixed values of a focal parameter, this function constructs a profile likelihood confidence interval accommodating both Monte Carlo error in the profile and statistical uncertainty present in the likelihood function.

mcap(logLik, parameter, level = 0.95, span = 0.75, Ngrid = 1000)

Arguments

• logLik: numeric; a vector of profile log likelihood evaluations.
• parameter: numeric; the corresponding values of the focal parameter.
• level: numeric; the confidence level required.
• span: numeric; the loess smoothing parameter.
• Ngrid: integer; the number of points to evaluate the smoothed profile.

Returns

mcap returns a list including the loess-smoothed profile, a quadratic approximation, and the constructed confidence interval.

References

E. L. Ionides, C. Bretó, J. Park, R. A. Smith, and A. A. King. Monte Carlo profile confidence intervals for dynamic systems. Journal of the Royal Society, Interface 14 , 20170126, 2017. tools:::Rd_expr_doi("10.1098/rsif.2017.0126") .

Author(s)

Edward L. Ionides