similar to: Comparing switchpoints from segmented

Hello all I'm trying to do a simulation that involves identifying the minimum point between two peaks of a (usually) bimodal distribution. I can do this easily if there are only two peaks: CnBdens<-density(Ys/Xs) #probability density function for ratio of Ys to Xs for(p in 1:512) ifelse(CnBdens$y[p]>CnBdens$y[p-1],peak1<-p,break) #identifies first peak in probability

Hi folks I wonder if anyone can help me. I want to run some simulations to see how big a sample size might be necessary to distinguish a curved bivariate relationship (e.g. something that might be best described by a quadratic model) from a relationship that is two straight lines with a sudden change in slope (e.g. something best described by a breakpoint regression). I am using

People I apologise for asking a general stats question, but I'm at a bit of a loss as to what to do following some hostile referees' comments. If I have a fully randomised blocked design, with only three blocks, should I treat block as a random or fixed effect? I have read comments about not treating block as a random effect if the number of blocks is less than 6 or 7: is this

Hello people I am doing some thinking about how to analyse data on dimorphic animals - where different individuals of the same species have rather different morphology. An example of this is that some male beetles have large horns and small wings, and rely on beating the other guys up to get access to mates, whereas others have smaller horns and larger wings, and rely on mobility to

Hi there The default option for saving graphics from R (1.9.1) on my Mac is as a pdf file. If I open the file in Acrobat reader it looks really good and crisp, and is obviously saved as vector graphics, since I can zoom in as much as I like and it continues to look really nice. If I import it into MS Word (from office 2000), or Textedit, however, it imports it as a bitmap and unless I save

Hello Can anyone let me know how I might change the size of the numbers on the axes in a pairs plot? The normal cex.axis call doesn't do anything, cex.labels only seems to change the font size in the diagonal labels. Using R 1.8.0 on a Mac with OS X.3. Thanks Rob Knell

Dear R-helpers Can anyone direct me to a method for plotting what you might call a partial wireframe plot? I have two explanatory variables in a dataset which give me a significant interaction term when I fit a model. The two variables are correlated with each other to a moderate degree, and if I plot the predicted values from the model as a surface in a 3D wireframe plot there are some

Hi folks Can anyone direct me to a guide to analysing mixed models in R that is understandable by mere mortals (or worse, mere biologists)? I have read MASS and also Mick Crawley's book on the subject, have thrashed my way through the various help files from the NLME package and I'm afraid I remain baffled :-(. Particularly confusing is exactly what groupedData does, how I should use

Hi All, For the past few months I've been running a SUSE 9.2 server here (mostly as an app server) which was a member of an AD domain (w2k3 domain controller.) I used winbind to enable domain members to log into the box, all was well. This week the w2k3 server had some MS security patches applied and suddenly logins became impossible, because winbind was unable to retrieve user info from the

I am faced with a network that needs to autoswitch to isdn should T-1 go down. After a shorewall search it looks to be quite a deal with routing config with linux. Like scripts written to deal with knowing the T-1 is down. I looked into a cisco router that does this. around $3000 This network has used shorewall as the gateway for 4 years now. Currently Fedora as op. system. It appears to me

Hi- I'm gettting the following error message when trying to use the segmented function to look for breakpoints in my data. Error in segmented.glm(glm, seg.Z = ~segmentdist, psi = 2, control = seg.control(display = F), : (Some) estimated psi out of its range Here are some real data and the models I'm calling which gives the error above. > segmentdist [1] 0.000000 8.547576

I tried to install "segmented" from three different repositories but I keep getting the following message on R window: ... Please, advice where to find this package. Thank you in advance. Maura > utils:::menuInstallPkgs() --- Please select a CRAN mirror for use in this session --- Warning: package 'segmented' is in use and will not be installed > utils:::menuInstallPkgs()

Hi everyone. I'm trying to use the segmented function with the following data: For instance, I use segmented package as follow: myreg2 = lm(xy$y ~ xy$x) mysegmented = segmented(myreg2, seg.Z=~x, psi=c(245000), control = seg.control(display=FALSE)) Which get me to the following error : As a break point, a starting guess of 245000 seems fair. Anyone has an idea why I'm getting such

Hi everyone. I'm using segmented package to find break point in a bi-linear relationship. In a particular case, I find 1 pointcut (so 2 slopes). I would like to know if it is possible to retrieve information in the segmented object that could let me to plot 1 particular segment with a different color. For example, in that folowing example, I would like to plot the second segment in red.

Hi, I appreciate your help with the segmented function. I am relatively new to R. I followed the introduction of the 'segmented'-package by Vito Muggeo, but still it does not work. Here are the lines I wrote: data_test<-data.frame(x=c(1:10),y=c(1,1,1,1,1,2,3,4,5,6)) lr_test<-lm(y~x,data_test) seg_test<-segmented(lr_test,seg.Z~x,psi=1) /error in segmented.lm(lr_test, seg.Z ~ x,

Most of the data sets I'm dealing with exhibit a time trend. We would like to get rid of the time trend. The plot shows in some cases a monotonic increase of the dependent variable with time. This is the easiest case. In some other cases the plot shows a time trend where the dependent variable changes slope 4-5 times along the observations measurement period. I've attempted a segmented

Hello all, I'm trying to find out how to perform a 'segmented regression'. I have some data and the 'classical' model used is: y(t) = a + bx(t) + cx(t)^2 + u(t) for x(t) < x(0) y(t) = a + bx(0) + cx(0)^2 + d(x(t) - x(0)) + u(t) for x(t) > x(0) and u(t) = rho.u(t-1) + eps (It's a model using an ARIMA-model, in this case AR(1)-process) The parameters to estimate here

Hello, I'm currently using the segmented package of M.R. Muggeo to fit a two-slope segmented regression. I would like to constrain a null-left-slope, but I cannot make it. I followed the explanations of the package (http://dssm.unipa.it/vmuggeo/segmentedRnews.pdf) to write the following code : fit.glm <- glm(y~x) fit.seg <- segmented(fit.glm, seg.Z=~x,psi=0.3) fit.glm

Hi all, I am using the package ?Segmented? to estimate logistic regression models with unknown breakpoints (see Muggeo 2003 Statistics in Medicine 22:3055-3071). In the documentation it suggests that it might be possible to include several variables with breakpoints in the same model: ?Z = a vector or a matrix meaning the (continuous) explanatory variable(s) having segmented relationships with

Hello, I have produced some segmented regressions with the segmented package by Viggo Mutteo. I have some example data and code below. I want to annotate the individual segments with the slope parameter (actually it would be nicer to annotate with 1000*slope and add some small amount of text as well). How can I do it? Reading the docs for segmented I can access all of the slope parameters via a