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.

AuthorJouni Helske
Date of publication2016-03-17 13:14:01
MaintainerJouni Helske <jouni.helske@jyu.fi>
LicenseGPL-3
Version1.0.1

View on CRAN

Files

tsPI
tsPI/inst
tsPI/inst/CITATION
tsPI/tests
tsPI/tests/testthat
tsPI/tests/testthat/test_acv_armaR.R
tsPI/tests/testthat/test-arima_pi.R
tsPI/tests/testthat/test_information_arma.R
tsPI/tests/testthat/test-struct_pi.R
tsPI/tests/test-all.R
tsPI/src
tsPI/src/Makevars
tsPI/src/arcov.f95
tsPI/src/declarations.h
tsPI/src/approxinfmat.f95
tsPI/src/init.c
tsPI/NAMESPACE
tsPI/R
tsPI/R/struct_pi.R tsPI/R/acv_arma.R tsPI/R/avg_coverage_struct.R tsPI/R/priors.R tsPI/R/information_arma.R tsPI/R/tsPI-package.R tsPI/R/arima_pi.R tsPI/R/avg_coverage.R
tsPI/MD5
tsPI/DESCRIPTION
tsPI/ChangeLog
tsPI/man
tsPI/man/acv_arma.Rd tsPI/man/struct_pi.Rd tsPI/man/avg_coverage_struct.Rd tsPI/man/dacv_arma.Rd tsPI/man/avg_coverage_arima.Rd tsPI/man/priors.Rd tsPI/man/arima_pi.Rd tsPI/man/information_arma.Rd tsPI/man/tsPI.Rd

Questions? Problems? Suggestions? or email at ian@mutexlabs.com.

Please suggest features or report bugs with the GitHub issue tracker.

All documentation is copyright its authors; we didn't write any of that.