profile_ML: Grid search for the mean length estimator

In quang-huynh/MLZ: Mean Length-Based Estimators of Mortality using TMB

Grid search for the mean length estimator

Description

A grid search is performed over the time series, which can be used to identify local and global minima. A plot of the likelihood surface is also created similar to Figure 6 of Gedamke and Hoenig (2006) or Figure 3 of Huynh et al. (2017).

Usage

profile_ML(MLZ_data, ncp, startZ = rep(0.5, ncp + 1), min.time = 3,
  parallel = ifelse(ncp > 2, TRUE, FALSE), figure = TRUE,
  color = TRUE)

Arguments

MLZ_data	An object of class MLZ_data.
ncp	The number of change points.
startZ	A vector of length ncp+1 as the starting value of total mortality rate used in the grid search.
min.time	The minimum number of years between change points. Only used if ncp > 1.
parallel	Whether grid search is performed using parallel processing.
figure	If TRUE, creates a plot of the likelihood over the grid search. Only used if ncp = 1 or 2.
color	If TRUE, creates a color plot for the likelihood surface. Only used if ncp = 2.

Value

A matrix of change points with the negative log-likelihood values.

References

Gedamke, T. and Hoenig, J.M. 2006. Estimating mortality from mean length data in nonequilibrium situations, with application to the assessment of goosefish. Transactions of the American Fisheries Society 135:476-487.

Huynh, Q.C, Gedamke, T., Hoenig, J.M, and Porch C. 2017. Multispecies Extensions to a Nonequilibrium Length-Based Mortality Estimator. Marine and Coastal Fisheries 9:68-78.

Examples

## Not run: 
data(Goosefish)
profile_ML(Goosefish, ncp = 1)
profile_ML(Goosefish, ncp = 2)

## End(Not run)

quang-huynh/MLZ documentation built on April 10, 2022, 7:39 p.m.