R help - Sep 1997 - R-beta: "Comparison of Mathematical Programs for Analysis"

Hi,
 I have just seen Stefan Steinhaus' web page : 
http://www.uni-franfurt.de/~stst/ncrunch.html

I think it would be nice to include "R" as well. 

I have taken Forrest Young's email on stat-lisp list and changed the
stuff for "R" :) Here it is: (someone please check this so we can
also send it to Stefan Steinhaus.

----------------------------------------------------------------------
The features are the rows of the table.

I have included my (initial) rating of  R  using the testreport's
rating categories of "+", "-", or "m".
 "+" means the feature is supported
 "-" means not supported
 "m" means it is available in an additional module (i.e., in code not
included in the original distribution of R, but available from the
net).

I've added "?" in places I'm not sure about my rating.

I've added a few random comments.

I'd appreciate anyone else's additions/corrections, especially about
whether "-"s should be "m"s. Then I'll send it to Stefan
Steinhaus.



=-=-=-=-=-=-
2.1 Standard Mathematical Functions
Trig functions +
Gamma function +
Poly Gamma -(?)
Log-Gamma functions +
Beta function +

2.2 Linear Algebra
Eigenvalues +
Eigenvectors +
Cholesky Decomposition +
Crout Decomposition -
LU Decomposition +
Singular Value Decomposition +
Upper Hessenberg form -
Toeplitz matrix -
Schur form of quadratic matrix -
Optimization (Unconstr. / Constr.) +/- (?)
Linear equation solver + 
Non-linear equation solver -(?)
Ordinary Differential Equation solver -
Partial Differential Equation solver -
Sparse matrices handling -
Moore-Penrose pseudo-inverse -

2.3 Analysis
Numerical integration (m)
Double integration (m)
Triple integration (m)
Numerical differentiation -
Fourier transf. (1D / 2D /multidim.) +/+/-
Inverse Fourier transformation (1D / 2D / multidim.) +/+/-

2.4 Numerical Mathematics -
Classical Interpolation +
k-Spline Interpolation ?
B-Spline Interpolation ?
Newton method for finding roots +
Bisection -
Runge Kutta method for solving ODE -

2.5 Stochastic
Markov models -
Mean +
Median +
Mode -
Variance +
Beta Distribution + + +
Chi-Squared Distribution + + +
Gamma Distribution + + +
Log-Normal
Normal Distribution + + +
Poisson Distribution + + +
Uniform Distribution + + +
More Distribution

2.6 Statistics
Linear regression +
Polynomial regression m
Nonlinear regression +
Loess regression -
LOGIT regression ?
PROBIT regression ?
PSN regression -
Event count models +
Duration models -
Goodness of fit test +
T-Test +
F-Test +
Q-Test -
Z-Test -
Maximum Likelihood m
ARIMA m
Time series analysis m
GARCH models -
Wavelets m
Cluster analysis m
Survival analysis m

2.7 Other Mathematics - Does anyone know of functions/methods that have
been written for any of these?
Cointegration models
Black Scholes model
Dynamic rational expectation models
Linear rational expectation models
Non-linear rational expectation models
Social network models
Kalman filter
Neuronal networks
Regressive-autoregressive models
Portfolio analysis
State-space models

3.0 Graphics - It seems to me this is a woefully inadequate classification

2D Graphics
Bar charts   +
Other charts +
Error charts +
High-Low-Average plot +
Histograms +
Log Plot +
Log-Log Plot +
Polar Plot ?
XY Plot +

3D Graphics
Charts -
Contour Plot +
Error bars   -?
Height Colors  ?
Surface Plot -
XYZ plot -

Special Graphics
Animations -
Bollinger bands -
Box & Whisker Plots +
Candlestick charts  -
Cluster graphs  m
Dendograms -
Periodograms m
QQ Plot +


4.0 Functionality of the Programming Environment

Editing Features
Built-in Editor -
External Editor Configurable +
Source code formatting ? (depends on the external editor)
Syntax highlighting ? (depending on the editor used)

Debugging
Breakpoints +
Function Tracer + ?
Line Tracing
Profiler
Stack inspection
Variable inspection +

Language Features
API interface -
DDE support  -
GUI programming -
N-dimensional arrays +
Object Oriented programming +
OLE support ?
P code compiling - (If this means Byte-Code compiling)

Language Interfaces
Assembler -
C/C++ +
FORTRAN +
GAUSS -
LISP + ?
Macsyma -
Maple -
Mathematica -
Matlab -
MuPAD -
Q-Matrix -
Ox -
S-Plus -
DLL-Calls -

5.0 Data Import-Export

none except ASCII


6.0 Available Operating Systems

Convex +  (if this means unix)
Cray + (if this means unix)
DEC + + -
HP 9000 + -
IBM RISC +
Intel Dos +
Intel OS/2 +
Intel Win 3.1x/95,NT + +
Intel Linux +
Motorola (Mac OS/Nextstep) + -
SGI-Irix +
SUN (solaris) +

COST        Free
Copyright   GPL
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-r-help
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-help-request at
stat.math.ethz.ch
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=

Some corrections to Stefan Steinhaus'  "Comparison of Mathematical
Programs for Analysis" for R. These also apply for S and Splus.

The following are handled by my DSE library available on statlib and at
http://www.bank-banque-canada.ca/pgilbert. I will try to make the
version for R available shortly after R 0.50 is release as beta.

State-space models (m)
Kalman filter (m)
autoregressive models (m)
(and also autoregressive moving-average models and VAR models)
Numerical differentiation (m)
Cointegration models (m - models yes, but not yet cointegration tests )

The following can be done with an interface from my DSE library which
runs Troll (a commercially available product) from S or R and returns
the results.

Dynamic rational expectation models (m)
Linear rational expectation models (m)
Non-linear rational expectation models (m)

5.0 Data Import-Export
There is also an interface (used by my DSE library) which allows access
to Fame databases and potentially any other database supporting the PADI
protocol explained at the above mentioned web site.



=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-r-help
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-help-request at
stat.math.ethz.ch
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=

U-E59264-Osman Buyukisik writes:
 > Hi, I have just seen Stefan Steinhaus' web page :
 > http://www.uni-franfurt.de/~stst/ncrunch.html
 > 
 > I think it would be nice to include "R" as well. 
 > 
 > ....
 >
 > The features are the rows of the table.

Not having seen the web-page (and unable to do so right now) I am
not about to pan it outright, but I must say I am largely
unimpressed by these comparisons of software on the basis of what
features they do or do not have, simply because they usually
ignore (or at least downgrade the value of) extensibility.

For example R and S+ do lack built-in polygamma functions, but it
is trivial to write very effective polygamma functions and
suddenly they are available.  (See, for example, the digamma and
trigamma functions in the MASS library.)  For other software
systems doing the same thing is a major undertaking or even
actually impossible unless the vendors do it for you.  That's a
major difference that these comparisons usually hide completely.

Bill Venables.
-- 
Bill Venables, Head, Dept of Statistics,    Tel.: +61 8 8303 5418
University of Adelaide,                     Fax.: +61 8 8303 3696
South AUSTRALIA.     5005.   Email: Bill.Venables at adelaide.edu.au
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-r-help
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-help-request at
stat.math.ethz.ch
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=