new time series package available

[Adrian Trapletti]

Fritz just put the first version of a new time series package to the
contrib section at CRAN.
The package is called "tseries.tgz" and provides a library for time
series analysis. It contains

acf                      Autocorrelation Function
adf.test                 Augmented Dickey-Fuller Test
amif                     Auto Mutual Information Function
bds.test                 BDS Test
box.test                 Box-Pierce and Box-Ljung Test
ccf                      Crosscorrelation Function
cross spectra            Cross Spectra Estimation (cross spectrum,
                         cospectrum, quadrature spectrum, amplitude
spectrum,
                         phase spectrum, and absolute coherency
estimation)
cumulative.periodogram   Cumulative Periodogram
embed                    Embedding a Time Series
finance                  Daily Closing Prices of Major European Stock
                         Indices, 1991-1998.
intgrt                   Discrete Integrals
is.univariate.ts         Test for Univariate Time Series
kernel                   Smoothing Kernel Objects
pacf                     Partial Autocorrelation Function
portfolio.optim          Portfolio Optimization
pp.test                  Phillips-Perron Unit Root Test
print.bdstest            Print BDS Test
quadmap                  Quadratic Map (Logistic Equation)
read.matrix              Read Matrix Data
read.ts                  Read Time Series Data
runs.test                Runs Test
sales                    Sales Data with Leading Indicator.
spectrum                 Spectrum Estimation
sunspot                  Yearly Sunspot Data, 1700-1988.   Monthly
                         Sunspot Data, 1749-1997.
surrogate                Generate Surrogate Data
toeplitz                 Form Symmetric Toeplitz Matrix
treering                 Yearly Treering Data, -6000-1979.
tsparam                  Time Series Paramater Object

and should be more or less well documented. The library is a port of a
part of my
octave time series library, and, at the moment it does not contain
routines for
estimating particular time series models. However, I plan to port my VAR
routines (Johansen
MLE methodology) and to implement MLE of ARMA models within the next few
months. Finally,
thanks to Ross: I used some of his ideas to implement the "tsparam" and
the "kernel" classes.

Testing, suggestions, and comments are welcome!

Adrian

--
Adrian Trapletti, Vienna University of Economics and Business
Administration, Augasse 2-6, A-1090 Vienna, Austria
Phone: ++43 1 31336 4561, Fax: ++43 1 31336 708,
Email: adrian.trapletti at wu-wien.ac.at



-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-announce mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-announce-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._