forecast_tvp_primiceri: Forecast using TVP a la Primiceri model

In bdemeshev/torro:

Description

forecast_tvp_primiceri forecasts time series using TVP model

Usage

forecast_tvp_primiceri(y, h = 1, model = NULL, level = c(80, 95), ...)

Arguments

y	multivariate time series
h	forecast horizon
model	estimated TVP models. If missing will be estimated automatically.
level	vector of confidence levels
...	further arguments passed to bvar.sv.tvp function

Details

One dimensional forecasts are obtained from future MCMC draws. Mean and interval forecasts are calculated from the draws. ACHTUNG: probably we need to scale series for this model!

Value

forecasts from TVP model as mforecast object

Examples

data(rus_macro)
y_small <- rus_macro[, c("cpi", "employment", "m2")]
y_small_scaled <- scale_to(y_small)
tvp_forecast <- forecast_tvp_primiceri(y_small_scaled, h = 2, p = 1)

bdemeshev/torro documentation built on May 21, 2019, 8:36 a.m.