simdata_priors: Simulate consumer isotope ratios to evaluate priors
In cbrown5/remixsiar: Post-processing of stable isotope mixing models

Description Usage Arguments Details Value Author(s)

Simulations of consumer isotope ratios are useful to evaluate model fits for bias and precision (variance). This function evaluates simulates data from simmr_input priors to estimate model bias and precision. Estimates can be compared to precision and bias from posteriors. Multiple groups are allowed.

1	simdata_priors(simmr_in, simmr_priors)

`simmr_in`	A `simmr_input` object, the output of simmr_mcmc
`simmr_priors`	A `data.frame` object containing draws of dietary proportions from the prior distributions.

High bias is indicative of a mis-specified model, for instance one that is missing an important source or an inaccurate fractionation. See remix_PI and remix_2DPI for plotting model predictions for 1 and 2 tracers.

A remix_simdata object containing for each tracer:

`bias`	A `data.frame` with estimates of model bias - mean deviation of the consumer data from the mean estimate
`rmse`	Variance of consumer isotope ratio predictions estimated as root-mean-square error.
`xmean`	Mean predicted consumer isotope ratio
`xvar`	Variance in predicted consumer isotope ratios
`xmean_bar`	Mean predicted consumer isotope ratio for the mean dietary proportions
`xvar_bar`	Variance in predicted consumer isotope ratios for the mean predicted dietary proportions