NEWS

---

MSGARCH 2.51 (2022-12-05)

• Fix warning: use of bitwise '|' with boolean operands

MSGARCH 2.43

• Doc fixes

MSGARCH 2.5

• Fix for Rcpp change

MSGARCH 2.4

• Fixed issue with Fixed parameter
• Bug fix in the mapping function of gjrGARCH for some parameters configuration

MSGARCH 2.3 (2018-05-16)

• Alexios added as contributor
• run_jss.R file updated
• THANKS updated
• References to package updated

MSGARCH 2.2

• Fix when constraint spec with more than 3 regime and mcmc estimation
• Fix for standard error computation

MSGARCH 2.1 (2018-02-26)

• spec can now be used with predict
• Documentation updated / examples improved
• THANKS updated
• COPYRIGHTS updated
• run_jss.R file updated in GitHub
• run_timing.R file updated in GitHub

MSGARCH 2.0 (2017-11-16)

• Add do.cumulative boolean argument to Risk for aggregated in time risk measures computation.
• Forecasts are now handle through the predict function. The predict function follows the standard stats::predict function. The Forecast method is thus discountinued.
• Simulations are now handle through the simulate function and the Sim function is discountinued. Simulation ahead of a sample can be retreived via the predict function with the argument do.return.draw = TRUE. The simulate function follows the standard stats::simulate function.
• Argument n.sim, n.mcmc, n.thin, n.burn, n.mesh, n.ahead, new.data are now relabeled to nsim, nmcmc, nthin, nburn, nmesh, nahead, newdata for more standard labelling of argument.
• The Pred function is now handle through the PredPDF function to avoid confusion with the function name Pred and predict (Pred was for Predictive Density).
• AIC and BIC now use the stats::AIC and stats::BIC implementation thus removing the MSGARCH::AIC and MSGARCH::BIC function. Usage is unchanged.
• Remove AIC and BIC functionalities for MSGARCH_MCMC_FIT object as it was not useful given the MSGARCH::DIC function. stats::AIC/BIC cannot handle the MSGARCH_MCMC_FIT version of AIC and BIC.
• do.sort can now be configure in the FitMCMC ctr argument. do.sort indicate if the each paramater draw of the MCMC change should be sorted conditional on the unconditional variance of each state (from low to high). This serve as to resolve label switching issue encountered in Markov-switching and mixture models bayesian estimation. Previous version of MSGARCH had this parameter set at TRUE at all time. The unsorted chain can now be outputted by setting do.sort = FALSE
• Support for zoo and ts timeseries. When using MSGARCH functionality, if a ts or zoo object is passed as data, the date or index now appear in the output as well. For forecast, the date are continued from the last data of the time series with inrcement of 1 day.
• do.cumulative is now available for PredPdf, PIT, and predict.

MSGARCH 1.3 (2017-10-26)

• Fix CRAN valgrind error
• Solaris error fix
• inst/test removed and moved to GitHub Examples folder
• Added test

MSGARCH 1.2 (2017-10-19)

• Small improvements
• Robustification of Hessian
• Robustification of MCMC with Rcpp
• Speedup examples

MSGARCH 1.1 (2017-09-14)

• New release on CRAN

MSGARCH 1.00.1

• Vignette updated

MSGARCH 1.00.0

• Vignette finalized
• Packages new release
• Several fixes and improvements

MSGARCH 0.21.1

• Vignette updated

MSGARCH 0.21.0

• Update vignetet
• Fix sorting

MSGARCH 0.20.7

• Update vignette
• Update doc
• Simplification of various outputs

MSGARCH 0.20.6

• S3 names changes
• improvements and fixes

MSGARCH 0.20.5

• Several small fixes

MSGARCH 0.20.1

• Doc improved
• Ineq removed
• Prior std to 10

MSGARCH 0.19.7

• Fixes by KB
• Merging of R files

MSGARCH 0.19.5

• New naming
• GAS removed
• Sigma0 removed

MSGARCH 0.19.4

• New input parameters with control lists

MSGARCH 0.19.2

• Fix bug related to object instantiation. No more random error on specification creation.

MSGARCH 0.19.1

• Fix bug in MCMC estimation n-step ahead simulation

MSGARCH 0.19

• Remove pdf and cdf since they were the same as pred and pit
• Change how pdf and cdf function works: See example run_test_v0.19.R
• Speed up risk measure calculation

MSGARCH 0.18.3

• unconditional probabilities

MSGARCH 0.18.2

• fix EM starting value

MSGARCH 0.18.1

• added wrapper arround standardize distribution

MSGARCH 0.18

• fix CRPS to be compatible with spec object

MSGARCH 0.17.9

• add an option to modify the accptance rate of the adaptive sampler

MSGARCH 0.17.8

• doc updated

MSGARCH 0.17.7 (2017-01-09)

• info updated

MSGARCH 0.17.6

• additional checks for create.spec when failing to properly instanciate it

MSGARCH 0.17.5

• fix ctr.deoptim in mle.R
• unify of defaults inputs for the various classes

MSGARCH 0.17.3

• fix bound problem

MSGARCH 0.17.2

• crps function added
• control parameters added to speedup for VaR calculation
• vignette removed and cited in the documentation with appropriate reference
• CITATION file modified
• check for input of check.enhance.theta
• change of optimization in do.enhance.theta

MSGARCH 0.17 (2016-10-30)

• fixed many bugs when the number of states were above 2.
• changed MLE estimation scheme
• function ht now output the conditional variance and not the conditional volatility
• do.init is now FALSE by default
• do.enhance.theta0 is now TRUE by default Known bugs in version 0.17
• sometimes do.enhance.theta0 gives an error concerning uniroot

MSGARCH 0.16 (2016-08-26)

• first release