tsPI: Improved Prediction Intervals for ARIMA Processes and Structural Time Series

Prediction intervals for ARIMA and structural time series models using importance sampling approach with uninformative priors for model parameters, leading to more accurate coverage probabilities in frequentist sense. Instead of sampling the future observations and hidden states of the state space representation of the model, only model parameters are sampled, and the method is based solving the equations corresponding to the conditional coverage probability of the prediction intervals. This makes method relatively fast compared to for example MCMC methods, and standard errors of prediction limits can also be computed straightforwardly.

Version: 1.0.3
Imports: KFAS
Suggests: testthat
Published: 2019-12-05
Author: Jouni Helske
Maintainer: Jouni Helske <jouni.helske at iki.fi>
BugReports: https://github.com/helske/tsPI/issues
License: GPL-3
NeedsCompilation: yes
Citation: tsPI citation info
Materials: ChangeLog
In views: TimeSeries
CRAN checks: tsPI results

Documentation:

Reference manual: tsPI.pdf

Downloads:

Package source: tsPI_1.0.3.tar.gz
Windows binaries: r-devel: tsPI_1.0.3.zip, r-release: tsPI_1.0.3.zip, r-oldrel: tsPI_1.0.3.zip
macOS binaries: r-release (arm64): tsPI_1.0.3.tgz, r-oldrel (arm64): tsPI_1.0.3.tgz, r-release (x86_64): tsPI_1.0.3.tgz, r-oldrel (x86_64): tsPI_1.0.3.tgz
Old sources: tsPI archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=tsPI to link to this page.