similar to: two questions about regression models and clustering routines

I would appreciate some help with the followiing error ... what did I do wrong and what is the woraroud. > library(nlme) > glmod <- gls(A ~ T +cosP +cos2P +cos4P +cos5P +sin3P +sin5P +cosP2 +sinP3 +P2, correlation=corAR1(),method="ML") Error: cannot allocate vector of size 491.3 Mb I have a bunch of humans' breathing signals. The recording frequency was 30 samples per

Hi It is preferable to echo your posts to r-help, you usually get more answers and some definitelly superb to mine. It is also better to start a new mail if your question has nothing to do with original subject "Maura E Monville" <maura.monville at gmail.com> napsal dne 01.10.2007 17:44:43: > Unluckily I do not have the privilege of practising with R all day > long. I

Thank you for your prompt answer. The breathing signal observations are the amplitude values as a function of time and phase. According to our model the hidden states are the different breathing types. Subjects, whose respiratiion process is regular, are likely to breathe, keeping the same cycle pattern/type, for many consecutive cycles. therefore dwelling in the same hidden state. The more

I have 316 files storing a number of cycles of the respiratory signal from 316 different patients. Each file record is made up of the following data: amplitude,phase,timestamp,validflag,ttlin,mark,ttlout amplitude: is the position in cm relative to an arbitrary reference (signal amplitude) phase: is the phase value for the current sample (the time point at which the breathing signal was

*I would like to plot some semi-periodic signals as a function of the phase expressed as a value in [0,2PI]* *The problem is that the phase data is reported as the residual of the division by 2PI.* *For instance if the phase is 10.359 rd then:* *15.359 / 6.283185 = 2*6.283185 + 2.79263* *then only the residual 2.79263 is stored. * *In order to plot a number of consecutive cycles I have to add

I am reading the comprehensive on-line documentation about msm. The positive side is that it seems it has been designed for biomedical statistics, like Clinical Trials. The bad side is that it does not seem to model observations sequences that are not independent but instead are autocorrelated, as it is my case. I did not find any mention to correlated observations therefore I assume the authors

Now that I've loaded a file into an R data.frame and played with linear regression until I got a good model, my next step is clustering using the coefficients of the regression model (I have many files) Thanks to some R experts' guidelines I could find plenty of documentation on regression analysis in the "contributed" section. Some touch on the concepts of the underlying

Warning: Sligthly off topic. http://shelleytherepublican.com/2006/04/linux-european-threat-to-our-computers.html Quotes: > And guess what software Osama Bin Laden uses on his laptop? > > If you guessed it was Linux you would be 100% right. > Next time somebody asks you how Al Queda agents pay for their > rifles and rocket launchers, you can tell them that foreign hackers >

We are trying to build a human respiration model. Preliminary analysis of some breathing signals has shown that humans breathe through switching among a finite number of patterns. Hidden Markov seems to be the right approach. Since most of our code is written in R scripting language, finding an R package implementing an HMM that we can use for our prototype would be very helpful. I have been

I have 316 files. Each file represents a patient's breathing track (respiratory signal recorded for a variable number of cycles). All files have the same are made up of a header followed by a variable number of records. Each record contains 7 comma separated fields. The patient ID is recorder in the header which is stripped off when reading the file into a R data.frame. Since I need to keep

I would appreciate some suggestions about nonlinear regression available in R ... possible methods and plenty of worked out examples .... I have a bunch of noisy curves representing breathing amplitude from medical physics experiments recoding patients' breathing tracks in form of Amplitude, Phase, Time, some flags controlling the data validity. A variable number of successive breathing

I have a pretty big similarity matrix (2870x2870). I will produce even bigger ones soon. I am using PAM to generate clusters. The desired number of output clusters is a PAM input parameter. I do not know a-priopri what is the best clusters layout . I resorted to the silhouette test. It takes forever as I have to run PAM with all possible numbers of clusters. I wonder whether there is some faster

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()

I deal with mono-channel breathing signals sampled at 30[Hz] which are non-linear and non-stationary. My goal is to classify the signals according to common breathing patterns Trend remotion is necessary for cluster analysis but quite challenging. In fact, quasi-periodic patterns that span a number of consecutive breathing cycles should not be naively removed as they carry a lot of useful

look at the spectrums before you do the cbind - I would not suggest letting R wrap the data to fill in a data frame. I would suggest using something that you "know how it acts" in the frequency domain like zero. You are probably introducing periodicies that are not real, and I would suggest not to go down this path. As for finding commonalities amongst signals- it all depends on what

Does R implements Pseudo-F-Statistics Clustering ? Vogel and Wong derived a formula to evaluate the best clusters number through such a method. Silhouette metod only provides an average evaluation. Thank you very much. Maura tutti i telefonini TIM! [[alternative HTML version deleted]]

I have a binary vector whose length is known. Such a vector contains an unspecified number of 1s. My goal is 1. to generate as many clusters as the number of 1s 2. to place the 1 as much as possible at the center of its own cluster Example. Say I have the following binary vector: v <- c(0,0,1,0,0,0,0,1,0,1,0,0) Then I have to get 3 clusters. I can generate a matrix containing the distance of

I saw there exists an R version for Mac/OS. I'd like to hear from someone who is running R on a Mac/OS before venturing on getting the following computer system. I am in the process of choosing a powerful laptop 17" MB PRO 2.6GHZ(dual-core) 4GBRAM .... Thank you so much, -- Maura E.M [[alternative HTML version deleted]]

I am going to try out a tentative clustering of some feature vectors. The range of values spanned by the three items making up the features vector is quite different: Item-1 goes roughly from 70 to 525 (integer numbers only) Item-2 is in-between 0 and 1 (all real numbers between 0 and 1) Item-3 goes from 1 to 10 (integer numbers only) In order to spread out Item-2 even further I might try to

I have downloaded the source code for Linux. the ./configure procedure can find gcc but cannot find f77 or f2c I have looked for the above compiler with Test and installed all what pertains to Fortran. Still not even the man pages for f77 anf fc2 work >. Where is f77 and f2c with linux 10.3 ?? Thank you do much -- Maura E.M [[alternative HTML version deleted]]