{"name":"estSigmaR","title":"Estimate Recruitment Sigma","pagetitle":"Estimate Recruitment Sigma — estSigmaR","aliases":"estSigmaR","author":[],"keywords":[],"description":"

Estimate sigma R (recruitment variability), based on the empirical\n standard deviation of recruitment deviates in log space.

","usage":"estSigmaR(model, digits=2)","arguments":[{"name":"model","description":"

fitted scape model containing element Dev.

"},{"name":"digits","description":"

number of decimal places to use when rounding, or\n NULL to suppress rounding.

"}],"has_args":true,"examples":"# NOT RUN {\ngetSigmaR(x.cod) # sigmaR used in assessment 0.5 and 1.0\nestSigmaR(x.cod) # model estimates imply 0.20 and 0.52\n\ngetSigmaR(x.ling) # 0.6, deterministic age distribution in first year\nestSigmaR(x.ling) # model estimates imply 0.36\n\ngetSigmaR(x.sbw)\nestSigmaR(x.sbw) # large deviates in first year\nplotN(x.sbw) # enormous plus group and 1991 cohort\n\n# x.oreo assessment had deterministic recruitment, so no deviates\n# }\n","sections":[],"value":"

Vector of two numbers, estimating recruitment variability based on (1)\n the estimated age composition in the first year, and (2) subsequent\n annual recruitment.

","note":"

This function uses the empirical standard deviation to estimate sigma\n R, which may be appropriate as likelihood penalty (or Bayesian prior\n distribution) for recruitment deviates from the stock-recruitment\n curve. The smaller the estimated recruitment deviates, the smaller the\n estimated sigma R.

estSigmaR can be used iteratively, along with\n estN and estSigmaI to assign likelihood\n weights that are indicated by the model fit to the data. Sigmas and\n sample sizes are then adjusted between model runs, until they\n converge. The iterate function facilitates this procedure.

If \$ss\$ is the sum of squared recruitment deviates in log space\n and \$n\$ is the number of estimated recruitment deviates, then the\n estimated sigma R is:

$$\\sigma_R=\\sqrt{\\frac{ss}{n}}$$

The denominator is neither \$n-\$1 nor \$n-p\$, since \$ss\$ is\n based on deviates from zero and not the mean, and the deviates do not\n converge to zero as the number of model parameters increases.

","seealso":"

getN, getSigmaI, getSigmaR,\n estN, estSigmaI, and estSigmaR\n extract and estimate sample sizes and sigmas.

iterate combines all the get* and est*\n functions in one call.

plotN and plotB(..., what=\"s\") show what\n is behind the sigma R estimation.

scape-package gives an overview of the package.

","package":{"package":"scape","version":"2.3-2"}}

Description

Usage

Arguments

Value

See Also

Examples