fit_length_weight: Fit a length-weight model

Description Usage Arguments Examples

Description

For use with data for a single species.

Usage

1
2
3
4
fit_length_weight(dat, sex = c("female", "male", "all"),
  downsample = Inf, min_samples = 50L, method = c("tmb", "rlm",
  "lm"), df = 3, too_high_quantile = 1, usability_codes = c(0, 1, 2,
  6), scale_weight = 1/1000)

Arguments

dat

Input data frame. Should be from get_survey_samples() or get_commercial_samples().

sex

Either "male" or "female".

downsample

If not Inf this represents a number of fish specimens to sample prior to model fitting. Can be useful for large data sets that you want to fit with MCMC for testing purposes.

min_samples

The minimum number of fish before a model will be fit.

method

"rlm" for MASS::rlm() or "lm" for stats::lm(). "tmb" for a regression fit with TMB that uses Student-t errors with a degrees of freedom defined by the argument df.

df

The fixed degrees of freedom to use if method = "tmb". Large values (say over 100) are effectively the normal distribution. Small values make the distribution more robust to outliers. The model may become unstable if df < 2.

too_high_quantile

A quantile above which to discard weights and lengths. Can be useful for outliers. Defaults to including all data.

usability_codes

An optional vector of usability codes. All usability codes not in this vector will be omitted. Set to NULL to include all samples.

scale_weight

A value to multiply all weights by. Useful for changing units.

Examples

1
2
3
4
5
6
7
## Not run: 
d <- get_survey_samples("pacific ocean perch")
model_f <- fit_length_weight(d, sex = "female")
model_m <- fit_length_weight(d, sex = "male")
plot_length_weight(object_female = model_f, object_male = model_m)

## End(Not run)

pbs-assess/gfplot documentation built on June 6, 2019, 11:05 p.m.