fit_length_weight: Fit length weight relationship to species data from SVDBS

In NOAA-EDAB/neusCatch: Multispecies length expansion of commercial catch

Fit length weight relationship to species data from SVDBS

Description

Fits a length weight relationship for use in catch expansion

Usage

fit_length_weight(
  lengthWeightData,
  speciesName,
  speciesRules,
  outputDir = NULL,
  logfile = NULL,
  suppressMessages = F
)

Arguments

lengthWeightData	Data frame. length-weight pairs. Each row represents an individual fish
speciesName	Character string. Common name for species
speciesRules	List. Obtained from get_species_object
outputDir	Character string. Path to output directory (Default = NULL, no output written)
logfile	Character string. Specify the name for the log file generated describing all decisions made. (Default = NULL, no output written)
suppressMessages	Boolean. Suppress all messages

Value

List of model fit objects

commonSlope	lm object. Fit for single slope (beta)
seasonalSlope	lm object. Fit for seasonal slopes

Notes on model fitting

The Weight-Length relationship is defined as

W_{ij} = \alpha L_{ij}^{\beta_j} e^{z_{ij}}

where,

W_{ij} = Weight of fish i in season j, i = 1, ..., n, j = 1, ... J

L_{ij} = Length of fish i in season j,

z_{ij} ~ N(0,\sigma^2),

and \beta_j is effect of season j

On the more familiar log scale the model is

log(W_{ij}) = log(\alpha) + \beta_j log(L_{ij}) + {z_{ij}}

To test for a seasonal effect, we test the Null hypothesis:

{H_0}: \beta_j = \beta

against the alternative,

{H_1}: \beta_j \neq \beta

The test statistic is the standard F statistic

F = \frac{(RSS_{H_0}-RSS_{H_1})/(J-1)}{RSS_{H_1}/(n-J-1)}

which will have an F distribution with (J-1, n-J-1) degrees of freedom

where RSS= Residual Sum of Square s

NOAA-EDAB/neusCatch documentation built on Oct. 17, 2023, 7:07 a.m.