I uploaded the package "multilm_0.1.tar.gz", which implements multivariate linear models and test procedures (T^2 and stabilized multivariate procedures by Laeuter et. al.). The function "multilm" allows the specification of multivariate linear models Y = X B + E, parameter restrictions Z B = 0 and linear hypotheses K B = 0. The Hotelling T^2 test ist computed and also p-values are available (an approximation of the null distribution by Laeuter is used). The summary method "summary.multilm" offers the computation of stabilized multivariate tests: SS, PC-1, PC-q and CS. Unlike "lm" this package uses the Moore-Penrose inverse for least square fitting (see the MP, QR, lm, anova discussion in June). I'm not sure if those basic methods fit most users needs, maybe wrappers for special models (MANOVA) are required. I'm very grateful for any hint and discussion, mails of common interest please to the R-list, others to my email address. Torsten -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- 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 _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
Package installed at CRAN. fritz>>>>> On Fri, 24 Sep 1999 18:07:04 +0200 (MET DST), >>>>> Torsten Hothorn (TH) wrote:TH> I uploaded the package "multilm_0.1.tar.gz", which implements multivariate TH> linear models and test procedures (T^2 and stabilized multivariate procedures TH> by Laeuter et. al.). TH> The function "multilm" allows the specification of multivariate linear TH> models Y = X B + E, parameter restrictions Z B = 0 and linear hypotheses TH> K B = 0. The Hotelling T^2 test ist computed and also p-values are TH> available (an approximation of the null distribution by Laeuter is used). TH> The summary method "summary.multilm" offers the computation of stabilized TH> multivariate tests: SS, PC-1, PC-q and CS. TH> Unlike "lm" this package uses the Moore-Penrose inverse for least square TH> fitting (see the MP, QR, lm, anova discussion in June). TH> I'm not sure if those basic methods fit most users needs, maybe wrappers for TH> special models (MANOVA) are required. I'm very grateful for any hint and TH> discussion, mails of common interest please to the R-list, others to my TH> email address. TH> Torsten -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- 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 _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
Torsten Hothorn <hothorn at statistik.uni-dortmund.de> writes:> I'm not sure if those basic methods fit most users needs, maybe wrappers for > special models (MANOVA) are required. I'm very grateful for any hint and > discussion, mails of common interest please to the R-list, others to my > email address.Now I didn't actually try this (yet), but one thing that reduces the practical value of these models is missing values. Is there any provision to handle these? Someone mentioned code to handle multivariate normals with missings earlier today, how do the two packages get along? I did some special cases of this for a project a couple of years back where I did polynomial curve fits to repeated measurements of bone metabolism data. In those data, an overall rate of 10% missing data would result in losing half the data set for complete-case analyses. -- O__ ---- Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk) FAX: (+45) 35327907 -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- 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 _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._