factorstochvol (version 0.8.1)

predloglik: Evaluates the predictive log likelihood using the predicted covariance matrix

Description

predloglik approximates the predictive log likelihood by simulating from the predictive distribution of the covariance matrix and evaluating the corresponding multivariate normal distribution.

Usage

predloglik(y, x, ahead = 1, each = 1)

Arguments

y

Matrix of dimension length(ahead) times m where the predictive density should be evaluated.

x

Object of class 'fsvdraws', usually resulting from a call to fsvsample.

ahead

Vector of timepoints, indicating how many steps to predict ahead.

each

Single integer (or coercible to such) indicating how often should be drawn from the posterior predictive distribution for each draw that has been stored during MCMC sampling.

Value

Vector of length length(ahead) with log predictive likelihoods.

See Also

Uses predcov. If m is large but only few factors are used, consider also using predloglikWB.

Other predictors: predcond, predcor, predcov, predh, predloglikWB, predprecision

Examples

## Not run: 
# set.seed(1)
# 
# # Simulate a time series of length 1100:
# sim <- fsvsim(n = 1100, series = 3, factors = 1)
# y <- sim$y
# 
# # Estimate using only 1000 days:
# res <- fsvsample(y[seq_len(1000),], factors = 1)
# 
# # Evaluate the 1, 10, and 100 days ahead predictive log
# # likelihood:
# ahead <- c(1, 10, 100)
# scores <- predloglik(y[1000+ahead,], res, ahead = ahead, each = 10)
# print(scores)
# ## End(Not run)