Skip to content

two new packages

3 messages · Bliese, Paul D MAJ WRAIR-Wash DC, Kjetil Halvorsen, John Fox

#
John,

Thanks for making these available!  I'm very interested in your sem package
in particular.  Do you have versions that run in S-PLUS too?  I'll send
comments as I work through the materials.

Paul

**********************************************************************
MAJ Paul D. Bliese, Ph.D.
Chief, Dept. Operational Stress Research
Walter Reed Army Institute of Research
Washington, DC 20307
Voice:  (301) 319-9873
Fax:     (301) 319-9484
paul.bliese at na.amedd.army.mil


-----Original Message-----
From: John Fox [mailto:jfox at mcmaster.ca]
Sent: Friday, April 27, 2001 10:52 PM
To: R-announce at r-project.org
Subject: two new packages



I've prepared preliminary versions of two packages that I plan eventually 
to contribute to CRAN:

car (for "Companion to Applied Regression") is a package that provides a 
variety of functions in support of linear and generalized linear models, 
including regression diagnostics (e.g., studentized residuals, hat-values, 
Cook's distances, dfbeta, dfbetas, added-variable plots, component+residual 
plots, ceres plots, Durbin-Watson statistics); some tools for graphing and 
exploring data (e.g., enhanced quantile-comparison plots -- with simulated 
envelopes for studentized residuals from linear models, scatterplot, and 
scatterplot-matrix functions); some utilities (e.g., for recoding 
variables); some functions for transformations of data (e.g., multivariate 
unconditional Box-Cox transformation); an enhanced Anova function; and many 
datasets. The object is to make tasks that are commonly employed in 
regression modeling more convenient, particularly for students with limited 
programming skills. I've tried largely to avoid duplicating capabilities in 
existing packages.

sem is a package for fitting "structural-equation models." The package 
supports general structural equation models with latent varibles, fit by 
maximum likelihood assuming multinormality, and single-equation estimation 
for observed-variable models by two-stage least squares.

For the present, I'm making these packages available on my web site, at 
<http://www.socsci.mcmaster.ca/jfox/Misc/car/> and 
<http://socserv.socsci.mcmaster.ca/jfox/Misc/sem/>.

I'm particularly interested in suggestions and comments.

John


________________________________
  John Fox
  Department of Sociology
  McMaster University
  email: jfox at McMaster.ca
  web: www.socsci.mcmaster.ca/jfox
________________________________

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.
-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._.
_._
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
1 day later
#
Hola!

I have a package i will soon contribute to CRAN, SenSrivastava,
containing the datasets for exampples and exercises in the book:
Sen/Srivastava: "Regression Analysis, Theory, Methods, and
Applications."
(Springer Verlag, 1990)
What I haven? found in R, needed for teaching from the book, is 
diagnostics for multicollinearity. (VIF?s) Is this somewhere in R I
havent searched, or have anyboduyu coded it up?

Thanks very much, 

Kjetil Halvorsen.
"Bliese, Paul D MAJ WRAIR-Wash DC" wrote:
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
#
Dear Kjetil,

The vif function in the car package calculates vif's for 
one-degree-of-freedom terms in a linear model object and generalized vif's 
for terms with more than one df (the latter are described in Fox, J. and 
Monette, G. (1992) Generalized collinearity diagnostics. JASA, 87, 
178?183). Beyond this, other tools are readily available in R, such as 
eigenvalues/vectors, singular-value decompositions, and 
principal-components analysis.

I hope that this helps,
  John
At 01:43 PM 02/05/2001 -0400, kjetil halvorsen wrote:
________________________________
  John Fox
  Department of Sociology
  McMaster University
  email: jfox at McMaster.ca
  web: www.socsci.mcmaster.ca/jfox
________________________________

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._