Embedding R in Windows applications, and executing R remotely
Embedding R in Windows applications, and executing R remotely
Embedding R in Windows applications, and executing R remotely
You also want an ePaper? Increase the reach of your titles
YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.
Rmetrics<br />
www.rmetrics.org<br />
An Environment for Teach<strong>in</strong>g<br />
F<strong>in</strong>ancial Eng<strong>in</strong>eer<strong>in</strong>g <strong>and</strong> Computational F<strong>in</strong>ance<br />
Diethelm Würtz<br />
Swiss Federal Institute of Technology, Zürich<br />
Institute for Theoretical Physics, Hönggerberg<br />
CH-8093 Zürich, Switzerl<strong>and</strong><br />
February 2004<br />
Rmetrics is a collection of several hundreds of functions which may be useful for teach<strong>in</strong>g<br />
"F<strong>in</strong>ancial Eng<strong>in</strong>eer<strong>in</strong>g" <strong>and</strong> "Computational F<strong>in</strong>ance". This R port was <strong>in</strong>itiated 1999 as an<br />
outcome of my lectures held on topics <strong>in</strong> econophysics at ETH Zürich. The family of the<br />
Rmetrics packages <strong>in</strong>cludes currently four members deal<strong>in</strong>g with the follow<strong>in</strong>g subjects:<br />
fBasics - Markets, Basic Statistics, Date <strong>and</strong> Time, fSeries - The Dynamical Process Beh<strong>in</strong>d<br />
F<strong>in</strong>ancial Markets, fExtremes - Beyond the Sample, Deal<strong>in</strong>g with Extreme Values, <strong>and</strong><br />
fOptions – The Valuation of Options.<br />
The package fBasics covers the management of economic <strong>and</strong> f<strong>in</strong>ancial market data. Included are<br />
functions to download economic <strong>in</strong>dicators <strong>and</strong> f<strong>in</strong>ancial market data from the Internet. Distribution<br />
functions relevant <strong>in</strong> f<strong>in</strong>ance are added like the asymmetric stable, the hyperbolic <strong>and</strong> the <strong>in</strong>verse normal<br />
gaussian distribution function to compute densities, probabilities, quantiles <strong>and</strong> r<strong>and</strong>om deviates. Estimators<br />
to fit the distributional parameters are also available. Some additional hypothesis tests for the<br />
<strong>in</strong>vestigation of correlations, dependencies <strong>and</strong> other stylized facts of f<strong>in</strong>ancial time series can also be<br />
found <strong>in</strong> this package. Furthermore, for date <strong>and</strong> time management a holiday database for all ecclestial<br />
<strong>and</strong> public holidays <strong>in</strong> the G7 countries <strong>and</strong> Switzerl<strong>and</strong> is provided together with a database of daylight<br />
sav<strong>in</strong>g times for f<strong>in</strong>ancial centers around the world. Special calendar management functions were<br />
implemented to create easily bus<strong>in</strong>ess calendars for exchanges. A collection of functions for filter<strong>in</strong>g <strong>and</strong><br />
outlier detection of high frequency foreign exchange data records collected from Reuters’ data feed can<br />
also be found together with functions for de-volatilization <strong>and</strong> de-seasonalization of the data. – A new<br />
additional chapter with synonyme functions for Splus like time, date, <strong>and</strong> time series objects is scheduled<br />
for April 2004.<br />
The package fSeries covers topics from the field of f<strong>in</strong>ancial time series analysis <strong>in</strong>clud<strong>in</strong>g ARIMA,<br />
GARCH, Regression, <strong>and</strong> Feedforward Neural Network modell<strong>in</strong>g. This library tries to br<strong>in</strong>g together the<br />
content of exist<strong>in</strong>g R-packages with additional new functionality on a common platform. The collection<br />
comes with functions for test<strong>in</strong>g various aspects of f<strong>in</strong>ancial time series, <strong>in</strong>clud<strong>in</strong>g unit roots, <strong>in</strong>dependence,<br />
normality of the distribution, trend stationary, co-<strong>in</strong>tegration <strong>and</strong> neglected non-l<strong>in</strong>earities.<br />
Furthermore functions for test<strong>in</strong>g for higher serial correlations, for heteroskedasticity, for autocorrelations<br />
of disturbances, for l<strong>in</strong>earity, <strong>and</strong> functional relations are also provided. Technical analysis <strong>and</strong> benchmark<strong>in</strong>g<br />
is another major issue of this package. The collection offers a set of the most common technical<br />
<strong>in</strong>dicators together with functions for chart<strong>in</strong>g <strong>and</strong> benchmark measurements. For build<strong>in</strong>g trad<strong>in</strong>g models