predict.mbsts {CausalMBSTS}

Predictions for a given multivariate Bayesian structural time series model

Description

Given an object of class 'mbsts' and the number of 'steps.ahead' in the future to be forecasted, this function provides in-sample forecasts and out-of-sample forecasts, both based on drawing from the posterior predictive distribution. If 'mbsts' contains a regression component, then the new matrix of predictors 'newdata' must be provided. Note that NA values are not allowed in the new regressor matrix.

Usage

## S3 method for class 'mbsts'
predict(object, steps.ahead, newdata = NULL, ...)

Arguments

object

An object of class 'mbsts', a result of call to as.mbsts.

steps.ahead

An integer value (S) specifying the number of steps ahead to be forecasted. If 'object' contains a regression component, the argument is disregarded and a prediction is made with the same length of 'newdata'.

newdata

Optional matrix of new data. Only required when 'object' contains a regression component.

...

Arguments passed to other methods (currently unused).

Value

Returns a list with the following components

post.pred.0

t x d x ('niter'- 'burn') array of in-sample forecasts.

post.pred.1

S x d x ('niter'- 'burn') array out-of-sample forecasts, where S is the number of forecasted periods (set to the length of 'steps.ahead' or 'newdata').

post.pred

(t + S) x d x ('niter'- 'burn') array combining in- and out-of-sample forecasts.

Examples

## Note: The following are toy examples, for a proper analysis we recommend to run
##       at least 1000 iterations and check the convergence of the Markov chain

## Example 1 :
y <- cbind(seq(0.5,100,by=0.5)*0.1 + rnorm(200),
           seq(100.25,150,by=0.25)*0.05 + rnorm(200),
           rnorm(200, 5,1))
mbsts.1 <- as.mbsts(y = y, components = c("trend", "seasonal"), seas.period = 7, s0.r = diag(3),
                    s0.eps = diag(3), niter = 50, burn = 5)
pred.1 <- predict(mbsts.1, steps.ahead = 10)

## Example 2
y <- cbind(rnorm(100), rnorm(100, 2, 3))
X <- cbind(rnorm(100, 0.5, 1) + 5, rnorm(100, 0.2, 2) - 2)
mbsts.2 <- as.mbsts(y = y, components = c("trend", "seasonal"),
                    seas.period = 7, X = X, s0.r = diag(2),
                    s0.eps = diag(2), niter = 100, burn = 10)
newdata <- cbind(rnorm(30), rt(30, 2))
pred.2 <- predict(mbsts.2, newdata = newdata)