Dear All, Currently I'm using the "segmented" package. While using the package, (i.e segmented - version 0.2-4) to investigate a possible change point (around X = 2) in my data, I had the following error message:
dat00<-read.table("data.txt",header=T) library(segmented) glm.Y<-glm(Y~X,data=dat00) seg.Y<-segmented.glm(glm.Y,seg.Z=~X,psi=2) Error in segmented.glm(glm.Y, seg.Z = ~X, psi = 2) (Some) estimated psi out of its range The used data are attached in this mail for your reference. I have tried my best using many modifications to avoid this error, but it couldn't be. However, data seems to have a breakpoint around 2. I'm requesting you to give me some advice to avoid the error. Thanks in advance, Yuichi Iwasaki -------------------------------------------------- Yuichi IWASAKI Graduate School of Environment and Information Sciences, Yokohama National University
Y X 8 3.03 9 2.94 8 2.69 26 0.48 17 0.48 27 0.48 21 0.48 23 0.48 8 2.65 9 2.58 25 2.13 25 2.18 23 2.1 28 1.8 25 0.69 27 0.81 37 0.78 16 2.32 30 2.04 34 1.87 30 0.38 32 0.28 34 0.06 7 3.26 7 3.17 21 1.99 23 2.79 26 0.32 30 0.27 28 0.42
______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.