plotMCMC (version 2.0-0)

xpar: MCMC Results for Model Parameters

Description

Markov chain Monte Carlo results from stock assessment of cod (Gadus morhua) in Icelandic waters, showing estimated model parameters.

Usage

xpar

Format

Data frame containing 1000 rows and 8 columns:

R0	average virgin recruitment
Rinit	initial recruitment scaler
uinit	initial harvest rate
cSleft	left-side slope of commercial selectivity curve
cSfull	age at full commercial selectivity
sSleft	left-side slope of survey selectivity curve
sSfull	age at full survey selectivity

Details

Each column contains the results of 1 million MCMC iterations, after thinning to every 1000th iteration.

The MCMC analysis started at the best fit, so no burn-in period was discarded.

References

Fournier, D. A., Skaug, H. J., Ancheta, J., Ianelli, J., Magnusson, A., Maunder, M. N., Nielsen, A., and Sibert, J. (2012) AD Model Builder: using automatic differentiation for statistical inference of highly parameterized complex nonlinear models. Optimization Methods and Software 27, 233--249.

Magnusson, A., Punt, A. E., and Hilborn, R. (2013) Measuring uncertainty in fisheries stock assessment: the delta method, bootstrap, and MCMC. Fish and Fisheries 14, 325--342.

See Also

xpar (parameters), xrec (recruitment), xbio (biomass), and xpro (projected future biomass) are MCMC data frames to explore.

plotMCMC-package gives an overview of the package.

Examples

# NOT RUN {
plotTrace(xpar, xlab="Iterations", ylab="Parameter value",
          layout=c(2,4))
plotTrace(xpar$R0, axes=TRUE, div=1000)

plotAuto(xpar$R0)
plotAuto(xpar$R0, thin=10)
plotAuto(xpar, lag.max=50, ann=FALSE, axes=FALSE)

plotCumu(xpar$R0, main="R0")
plotCumu(xpar$cSfull, main="cSfull")
plotCumu(xpar, probs=c(0.25,0.75), ann=FALSE, axes=FALSE)

plotSplom(xpar, pch=".")

plotDens(xpar, xlab="Parameter value", ylab="Posterior density\n")
# }