EXPAR: Fitting of Exponential Autoregressive (EXPAR) Model

The amplitude-dependent exponential autoregressive (EXPAR) time series model, initially proposed by Haggan and Ozaki (1981) <doi:10.2307/2335819> has been implemented in this package. Throughout various studies, the model has been found to adequately capture the cyclical nature of datasets. Parameter estimation of such family of models has been tackled by the approach of minimizing the residual sum of squares (RSS). Model selection among various candidate orders has been implemented using various information criteria, viz., Akaike information criteria (AIC), corrected Akaike information criteria (AICc) and Bayesian information criteria (BIC). An illustration utilizing data of egg price indices has also been provided.

Version: 0.1.0
Imports: forecast, stats
Published: 2024-05-10
DOI: 10.32614/CRAN.package.EXPAR
Author: Saikath Das [aut, cre], Bishal Gurung [aut], Achal Lama [aut], KN Singh [aut]
Maintainer: Saikath Das <saikathdas007 at gmail.com>
License: GPL-3
NeedsCompilation: no
In views: TimeSeries
CRAN checks: EXPAR results


Reference manual: EXPAR.pdf


Package source: EXPAR_0.1.0.tar.gz
Windows binaries: r-devel: EXPAR_0.1.0.zip, r-release: EXPAR_0.1.0.zip, r-oldrel: EXPAR_0.1.0.zip
macOS binaries: r-release (arm64): EXPAR_0.1.0.tgz, r-oldrel (arm64): EXPAR_0.1.0.tgz, r-release (x86_64): EXPAR_0.1.0.tgz, r-oldrel (x86_64): EXPAR_0.1.0.tgz


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