similar to: New CRAN package dyn

I now have versions of code that is destined (I believe) for 0.63 which is in a suitable state for comment. The files are at ftp://ftp.stats.ox.ac.uk/pub/R (Our www server is being moved, so may be intermittently down, but this ftp server should be stable.) All are R packages, for the moment for personal use only (no re-distribution). Use with 0.62.3 or 0.63 (although I am aware of some

None of Andy's comments) are inconsistent with the point that rlm() and lqs(), if they disagree with lm(), likely offer better places to start than does lm(), in identifying points that should be examined as in some sense outliers. All such methods are to be used, not as crutches, but as sources of insight. Incidentally, the "rlm" class inherits from "lm", and plot.lm()

Hi, trying to do a robudt regression of a two-way linear model, I keep getting the following error: > lqs(obs ~ y + s -1,method="lms", contrasts=list(s=("contr.sum"))) Error: lqs failed: all the samples were singular Robust regression with M-estimators works (also regular least square fits, of course): rlm.formula(formula = obs ~ y + s - 1, method = "M",

Dear R-users & developers, i'd like to know your opinion on the following suggestion. In short: Wouldn't it be possible to combine the properties of local regression (loess) and resistant regression (lqs) in order to cope with fitting of partially continuous data? I think the lqs-fitting could detect and eliminate the 2 outliers but perserve the discontinuity at t1 in case of the

> 3x4 Error: unexpected symbol in "3x4" R has no idea that you equate "x" as multiplication.. use an astrix > 3*4 [1] 12 dominic wrote > > This is basically my code: > > library(MASS) > lmsreg(formula = b0 ~ b1 + b3 + b1xb2, data=mydata) > > b1xb2 is an interaction but it was the centered value for a continuous > variable times a

Hi, I have been trying to dyn.load a library (rq.obj), which will allow me to run a quantile regression function, but so far unsuccessfully. I have tried under windows 98 and R 6.24: 1) dyn.load("d:\\...\\rq.obj") 2) dyn.load("d:\...\rq.obj") 3) 1 and 2 accounting for case sensitivity. 4) dyn.load("d:/.../rq.obj") 5) Place the files in the directory where from I

The package cxxPack builds without problems at CRAN under all OS's except Windows 64bit, and in the case of Windows 64bit there is a problem in a call to dyn.load(). This call happens while processing the package vignette, and the odd thing about this is that there are several calls to dyn.load() that work fine before the one that fails. This seems to suggest that Windows 64bit is imposing

hi guys and gals ... How are you all ... i have to do something in robust regression by R programm , and i have some problems as following: *the first :* suppose w(r) =1/(1 r^2) and r <- c(7.01,2.07,7.061,5.607,8.502,54.909,12.222) and i want to exclude some values from r so that (abs(r)>4.9 )... after ,i want to used (w) to get on coefficients beta0 and beta1 (B1 <-

After long but intermittent discussion (it was mentioned at DSC99, for example), we have reorganized the standard packages, with base graphics stats utils methods normally loaded, mle splines stepfun tcltk tools available for loading, and ctest eda lqs modreg mva nls ts as stub packages which ensure back-compatibility. (These have all been merged into stats except lqs which rejoins

I am using "nls" to fit dose-response curves but am not sure how to approach more robust regression in R to get around the problem of the my error showing increased variance with increasing dose. My understanding is that "rlm" or "lqs" would not be a good idea here. 'Fairly new to regression work, so apologies if I'm missing something obvious.

Hi, i. After estimating some coefficients using robust regression with rlm() or lqs(), I wonder if there exist some measures of the goodness-of-fit as those for standard linear model(R2)... or evenly if it's a statistics non-sense to look for since I do not find any mention of that in differents chapters on robust and resistant regression or in severals R documentation (Fox, Ripley and

Hi all and thanks for your time in advance, I can't figure out why summary.lmrob complains when lmrob is used on a zooreg object. If the zooreg object is converted to vector before calling lmrob, no problems appear. Let me clarify this with an example: >library(robustbase) >library(zoo) >dad<-c(801.4625,527.2062,545.2250,608.2313,633.8875,575.9500,797.0500,706.4188,

Hi all, I?m trying to plot confidence intervals for the fitted values I get with my lme model in R. Is there any way I can plot this in the form of a shaded band, like the output of geom_smooth() in ggplot2 package. ggplot2 seems to use only lm, glm, gam, loess and rlm as smoothing methods. Any advice on the functions I should use to accomplish this will be very helpful. Thank you very much.

Your understanding isn't similar to mine. Mine says robust/resistant methods are for data with heavy tails, not heteroscedasticity. The common ways to approach heteroscedasticity are transformation and weighting. The first is easy and usually quite effective for dose-response data. The second is not much harder. Both can be done in R with nls(). Andy From: Quin Wills > > I am

Hello, Can anyone explain the following behaviour? To me it seems a bug, but maybe it is intentional. It seems that a diff on a zooreg class that is not _strictly_ regular only considers those entries that are 'deltat' apart. In the following, diff on the zooreg class only returns values where the index was one second apart. The example replicates by dev code, but I've also tested

> Date: Mon, 11 Jan 1999 15:23:10 +0100 > From: Kjetil Halvorsen <khal at alumni.uv.es> > To: "Morris, Jeffrey (JCD-RL)" <JMorris at OCDUS.JNJ.COM> > CC: "'R-Help'" <r-help at stat.math.ethz.ch> > Subject: [R] R: Regression with t errors? > > Has anybody implemented/knows about ways to do in R regression > based on

Hi All, I have a data set of daily measurements of river flow. I would like to create a "ts" object from this data. Here's a sample data set: date <- as.Date(c(1:300), format="%Y") year=as.numeric(format(date, format = "%Y")) month=as.numeric(format(date, format = "%m")) julianday=as.numeric(format(date, format = "%j"))

After having browsed the documentation for a while without discovering what I am looking for, maybe one of you would know ... What I want to do: I have two fortran files MC.f and ESCA.f. In MC.f there is a call to a routine called lpost. This routine (lpost) is defined (among other things) in ESCA.f. Under linux, I can do the following: R CMD SHLIB MC.f and R CMD SHLIB ESCA.f followed by

Hello: I am having some difficulty with a DLL, using > version _ platform i386-pc-mingw32 arch x86 os Win32 system x86, Win32 status major 1 minor 2.1 year 2001 month 01 day 15 language R I have a library called

Dear R-experts, I am trying to do cross-validation for different models using the cvTools package. I can't get the CV for the "FastTau" and "hbrfit". I guess I have to write my own functions at least for hbrfit. What is going wrong with FastTau ? Here below the reproducible example. It is a simple toy example (not my real dataset) with many warnings, what is important to