Package: carfima
Version: 1.0.0
Date: 2017-10-21
Title: Continuous-Time Fractionally Integrated ARMA Process for
        Irregularly Spaced Long-Memory Time Series Data
Author: Hyungsuk Tak and Henghsiu Tsai
Maintainer: Hyungsuk Tak <hyungsuk.tak@gmail.com>
Depends: R (>= 2.2.0)
Imports: MASS (>= 7.3-47), DEoptim (>= 2.2-4), numDeriv (>= 2016.8-1),
        truncnorm (>= 1.0-7), invgamma (>= 1.1)
Description: We provide a toolbox to fit a continuous-time fractionally integrated ARMA process (CARFIMA) on univariate and irregularly spaced time series data via frequentist or Bayesian machinery. A general-order CARFIMA(p, H, q) model for p>q is specified in Tsai and Chan (2005)<doi:10.1111/j.1467-9868.2005.00522.x> and it involves p+q+2 unknown model parameters, i.e., p AR parameters, q MA parameters, Hurst parameter H, and process uncertainty (standard deviation) sigma. The package produces their maximum likelihood estimates and asymptotic uncertainties using a global optimizer called the differential evolution algorithm. It also produces their posterior distributions via Metropolis within a Gibbs sampler equipped with adaptive Markov chain Monte Carlo for posterior sampling. These fitting procedures, however, may produce numerical errors if p>2. The toolbox also contains a function to simulate discrete time series data from CARFIMA(p, H, q) process given the model parameters and observation times. 
License: GPL-2
NeedsCompilation: no
Packaged: 2017-10-21 16:47:01 UTC; hyungsuktak
Repository: CRAN
Date/Publication: 2017-10-23 09:05:43 UTC
