ArfimaOxInterface {fSeries} | R Documentation |
A collection and description of functions to
fit the parameters of an univariate time
series to ARFIMA models interfacing the ARFIMA
Ox Package.
The ARFIMA time series models include the following functiona:
1 | arfimaOxFit | Fits parameters of ARFIMA models, |
2 | S3 print method for ARFIMA models, | |
3 | plot | S3 plot method for ARFIMA models, |
4 | summary | S3 summary method for ARFIMA models, |
5 | fitted | S3 method to extract the fitted values, |
6 | residuals | S3 method to extract the resaidual values, |
7 | predict | S3 method to predict from an ARFIMA model, |
8 | predictPlot | S3 method to plot ARFIMA predictions. |
arfimaOxFit(formula, data, method = c("mle", "nls", "mpl"), trace = TRUE, title = NULL, description = NULL)
data |
an optional timeSeries or data frame object containing the variables
in the model. If not found in data , the variables are taken
from environment(formula) , typically the environment from which
armaFit is called. If data is an univariate series, then
the series is converted into a numeric vector and the name of the
response in the formula will be neglected.
|
description |
a character string which allows for a brief description. |
formula |
a formula object which specifies the ARFIMA process. |
method |
a character string denoting the method used for parameter estimation. |
title |
a character string which allows for a project title. |
trace |
a logical flag. Should the estimation process be ttraced? By default TRUE. |
Ox Interface:
The function garchOxFit
interfaces a subset of the
functionality of the ARFIMA 1.01 Package written in Ox.
ARFIMA is one of the most sophisticated packages for modelling
univariate ARFIMA processes.
About Ox:
Ox (tm) is an object-oriented matrix language with a comprehensive
mathematical and statistical function library. Many packages were
written for Ox including software mainly for econometric modelling.
The Ox packages for time series analysis and forecasting, Arfima,
Doornik and Ooms [2003], Garch, Laurent and Peters [2005], and State
Space Modelling, Koopman, Shepard and Doornik [1998], are especially worth
to note. Since most of the R-users wan't to change to another Statistical
Computing environment, we made selected parts of the ARFIMA Ox software
available for them through an R-Interface. What you have to do, is
to read carefully the "Ox citation and copyright" rules and if you
agree and fullfill the conditions, then download the OxConsole Software
together with the "Arfima" Package, currently implemented Arfima 1.01.
If you are not qualified for a free license, order your copy from
Timberlake Consultants. We recommend to install the "Setup.exe"
for "Ox3" under the path "C:\Ox\Ox3" and to unzip the "Arfima" Package
in the directory "C:\Ox\Ox3\Packages".
Distribution:
Ox and Arfima are distributed by Timberlake Consultants Ltd. Timberlake
Consultants can be contacted through the following web site:
www.timberlake.co.uk.
Installation of the Interface:
In addition you have to copy the files "ArfimaOxFit.ox" and
"ArfimaOxPredict.ox" (which is the interface written especially
for Rmetrics) from the "fSeries/data/" directory to the Ox library
directory "C:\Ox\Ox3\lib".
Ox Citation and Copyright Rules:
Ox and all its components are copyright of Jurgen A. Doornik. The
Console (command line) versions may be used freely for academic
research and teaching purposes only. Commercial users and others
who do not qualify for the free version must purchase the Windows
version of Ox and GiveWin with documentation, regardless of which
version they use (so even when only using Ox on Linux or Unix).
Ox should be cited whenever it is used. Refer to the two references
given below. Note, failure to cite the use of Ox in published work
may result in loss of the right to use the free version, and an
invoice at the full commercial price. Ox is available from Timberlake
Consultants. The Ox syntax is public, and you may do with your own
Ox code whatever you wish, including the files "ArfimaOx*.ox".
Work to do:
Note, only a small part of the functionalities are interfaced until
now to Rmetrics. But, principally it would be possible to interface
also other functionalities offered by the Ox Arfima Package. This
work is left to the Rmetrics/Ox user.
arfimaOxFit
returns an S4 object of class "fARMA"
, with the following
slots:
call |
the matched function call. |
data |
the input data in form of a data.frame. |
description |
allows for a brief project description. |
fit |
the results as a list returned from the underlying time series model function. |
method |
a character string naming the selected ARFIMA model.
Implemented are
the exact max-likelihood estimation method, "mle" ,
the non-linear least-square method, "nls" , and
the "mplik"
|
formula |
the formula expression describing the model. |
parameters |
named parameters or coefficients of the fitted model. |
title |
a title string. |
For further details please consult help(ArmaModelling)
.
The R functions were tested only under MS Windows XP. Please report your experience with other operating systems to info@metrics.org. The functions should also run under the newer version "Ox4".
Jurgen A. Doornik for the Ox Environment, www.doornik.com,
Jurgen A. Doornik and Marius Ooms for the Arfima Ox package, www.doornik.com,
Diethelm Wuertz for R's Ox Arfima interface.
Doornik J.A. (2002), Object-Oriented Matrix Programming Using Ox, London, 3rd ed.: Timberlake Consultants Press and Oxford: www.doornik.com.
Doornik J.A., Ooms M. (2001), A Package for Estimating, Forecasting and Simulating Arfima Models, Arfima Package 1.01 for Ox, pp. 32.
Doornik J.A., Ooms M. (2003), Computational Aspects of Maximum Likelihood Estimation of Autoregressive Fractionally Integrated Moving Average Models, Computational Statistics and Data Analysis 42, 333–348.
Koopman J.S., Shepard N., Doornik J.A. (1999), Statistical Algorithms for Models in State Space using SsfPack 2.2, Econometrics Journal 2, 113–166.
Laurent S., Peters J.P., [2005], G@RCH 4.0, Estimating and Forecasting ARCH Models, Timberlake Consultants, www.timberlake.co.uk
ArmaModelling
.
## Not run: ## SOURCE("fSeries1.1B-ArfimaOxInterface") ## arfimaOxFit - x = armaSim(model = list(ar = c(0.5, - 0.5), d = 0.3, ma = 0.1), n = 500) fit = arfimaOxFit(formula = x ~ arfima(2,1)) print(fit) plot(fit, which = "all:) summary(fit, doplot = FALSE) fitted(fit)[1:10] residuals(fit)[1:10] predict(object) ## End(Not run)