predict_deaths_fn: A function to compute the fitted and forecast number of...

In BayesMoFo: Bayesian Mortality Forecasting

A function to compute the fitted and forecast number of deaths, accompanied by credible intervals, from posterior samples generated for stochastic mortality models

Description

Return the median fitted and forecast number of deaths, accompanied by credible intervals (user-specified level), using posterior samples stored in "fit_result" object.

Usage

predict_deaths_fn(result, expo_forecast = NULL, pred_int = 0.95)

Arguments

result	object of type either "fit_result" or "BayesMoFo".
expo_forecast	An optional 3-dimensional array (of dimensions p \times A \times h) containing exposure data for the forecast period. If not provided, the exposure data from the most recent year will be used for forecasting.
pred_int	A numeric value (between 0 and 1) specifying the credible level of uncertainty bands. Default is pred_int=0.95 (95\% intervals).

Value

An array containing the lower, median, and upper quantiles of the number of deaths for both the fitted and forecast periods.

Examples

#load and prepare data
data("dxt_array_product");data("Ext_array_product")
death<-preparedata_fn(dxt_array_product,strat_name = c("ACI","DB","SCI"),ages=35:65)
expo<-preparedata_fn(Ext_array_product,strat_name = c("ACI","DB","SCI"),ages=35:65)

#fit any mortality model
runBayesMoFo_result<-runBayesMoFo(death=death,expo=expo,models="APCI",n_iter=1000)

#default
predict_deaths_fn(runBayesMoFo_result)

#changing pre-specified arguments 
predict_deaths_fn(runBayesMoFo_result,pred_int=0.8)

BayesMoFo documentation built on Aug. 11, 2025, 1:07 a.m.