Solution interface
ProfileLikelihoodSolution type is designed to contain the results of a profile likelihood analysis.
LikelihoodProfiler.ProfileLikelihoodSolution — TypeProfileLikelihoodSolution{probType,P}Contains the results of a profile likelihood analysis.
Fields
prob::probType: The profile likelihood problemProfileLikelihoodProblem.profiles::P: The computed profile curves.elapsed_time::Float64: The time elapsed during the computation.
Selectors
A number of selectors are available to extract information from the sol::ProfileLikelihoodSolution object. These can be applied to each computed profile sol[i]:
endpoints(sol[i]): Returns the confidence interval (CI) endpoints, marking the intersection of the profile with thethreshold.retcodes(sol[i]): Returns the retcodes of the CI endpoints estimation.stats(sol[i]): Returns the statistics of the profile computation.
Retcodes
sol::ProfileLikelihoodSolution outputs the following retcodes, which are accessible with retcodes(sol[i]) function:
:Identifiable- the profile has intersection with the predefinedthreshold.:NonIdentifiable- the profile doesn't intersect the predefinedthreshold.:MaxIters- maximum number of iterations reached while computing the profile. Seemaxitersargument to thesolve.:Failure- the solver (optimizer or integrator) reported failure status, profiling was interrupted.
Endpoints (confidence-interval estimates)
endpoints(sol[i]) returns the estimated crossing points of the profile with the chosen likelihood threshold for the i-th profile.
Visualization and tabular representation
The recipes are defined to visualize profiles saved in sol::ProfileLikelihoodSolution with Plots.jl package: plot(sol), plot(sol[i]). The following keyword arguments can be used in plot function:
steps::Bool- whether to scatter steps performed by the profiler. Defaults totrue.threshold::Bool- whether to plotthresholddefined inProfileLikelihoodProblem. Defaults toisfinite(threshold)
Also each profile contained in the sol::ProfileLikelihoodSolution can be represented as a DataFrame with DataFrame(sol[i]).