Fits hierarchical Bayesian survival model using Nimble.
bb_fit_survival(
data,
min_random_year = 5,
year_trend = FALSE,
include_uncertain_morts = TRUE,
year_start = 4L,
nthin = 10,
niters = 1000,
priors = NULL,
quiet = FALSE
)The data.frame.
A whole number of the minimum number of years required to fit year as a random effect (as opposed to a fixed effect).
A flag indicating whether to fit a year trend effect. Year trend cannot be fit if there is also a fixed year effect (as opposed to random effect).
A flag indicating whether to include uncertain mortalities in total mortalities.
A whole number between 1 and 12 indicating the start of the caribou (i.e., biological) year. By default, April is set as the start of the caribou year.
A whole number of the thinning rate.
A whole number of the number of iterations per chain after thinning and burn-in.
A named vector of the parameter prior distribution values.
Any missing values are assigned their default values in priors_survival() and priors_recruitment().
If NULL, all parameters are assigned their default priors.
A flag indicating whether to suppress messages and progress bars.
A list of the Nimble model object, data and mcmcr samples.
If the number of years is > min_random_year, a fixed-effects model is fit.
Otherwise, a mixed-effects model is fit with random intercept for each year.
If year_trend is TRUE and the number of years is > min_random_year, the model
will be fit with year as a continuous effect (i.e. trend) and no fixed effect of year.
If year_trend is TRUE and the number of years is <= min_random_year, the model
will be fit with year as a continuous effect and a random intercept for each year.
The model is always fit with random intercept for each month.
The start month of the Caribou year can be adjusted with year_start.
Other model:
bb_fit_recruitment(),
bb_fit_recruitment_ml(),
bb_fit_survival_ml()
if (interactive()) {
fit <- bb_fit_survival(bboudata::bbousurv_a)
}