Draws observations from the posterior predictive distribution over the
fitted period and, if horizon is positive, forecasts beyond it. The
forecast extends the latent process with fresh innovations for each
posterior draw.
# S3 method for class 'cidm_fit'
predict(object, horizon = 0, seed = NULL, ...)An cidm_fit object from fit().
Integer. Number of time points to forecast.
Optional integer seed for the Julia random number generator, used for the forecast. In-sample predictions are drawn when fitting.
Unused.
A matrix with one row per posterior draw and one column per time point, covering the fitted period followed by the forecast horizon.
Forecasting uses the Julia session in which the model was fitted.
Other inference:
fit(),
nuts(),
plot.cidm_fit(),
simulate.julia_spec(),
summary.cidm_fit()
if (FALSE) { # \dontrun{
forecasts <- predict(fitted, horizon = 14)
} # }