similar to: multivariate markov switching

Dear R community, I am looking for an R package or other software to study hidden Markov models. I need to be able to incorporate multivariate emissions and covariates for the transition probabilities. The msm package seems almost perfect for my purpose, but I do not think it allows multivariate emissions. I will be grateful for your suggestions. All the best, -- Emilio A. Laca One

Dear R-helpers, I made the package depmix for fitting hidden markov models. After updating R to version 2.2.0 on my PC I got the following error when installing the package from a local directory. One of the C files includes the R.h file which apparently causes problems. I call R CMD INSTALL --docs="normal" depmix and I get the following error: make[3]: *** No rule to make target

Dear Users, i have this time series, the tree lines means different level, i would use a Markov switching model with two states to modelling this time series. i would obtain the relative transition matrix (2X2) the first state is above the value of 23.65 (the higher line) the second state is below the value of 23.65 You can ignore the other two lines

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

Dear list, This question is about Hidden Markov Model. Given a transition matrix, an emission matrix and a sequence of observed symbols (actually, nucleotide sequences, A, T, C and G), I hope to predict the sequence of state by Viterbi algorithm. I searched R repository for related packages. msm package has function viterbi.msm (as well as very good document), but it only works for

Dear all, following the thread http://tolstoy.newcastle.edu.au/R/e2/devel/07/09/4338.html regarding the bug in the partial autocorrelation function for multivariate time series. I have prepared a web page with patches and relevant information. http://www2.stat.unibo.it/giannerini/R/pacf.htm Please do not hesitate to contact me for further clarifications regards Simone --

Dear R users, I have been trying to obtain the MLE of the following model state 0: y_t = 2 + 0.5 * y_{t-1} + e_t state 1: y_t = 0.5 + 0.9 * y_{t-1} + e_t where e_t ~ iidN(0,1) transition probability between states is 0.2 I've generated some fake data and tried to estimate the parameters using the constrOptim() function but I can't get sensible answers using it. I've tried using

Dear helpers, is there any possible that transition (in depmixS4) is in scale of two variable, e.g transition=~scale(x1,x2)? If it can be, how transition of two variable (covariate time) can be worked in depmixS4-hidden markov model for time series. Many thanks, nglthu -- View this message in context: http://r.789695.n4.nabble.com/depmixS4-transition-tp4572726p4572726.html Sent from the R help

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

Dear help group, Just fyi a markov chain is a sequence of transitions between states (say A,T,G,C - on a gene) with a given probability for each transition. In this case there'd be 16 different kinds, each with a different weight. Given a transition matrix (4x4) filled with all transition probabilities of course, how can I generate a random sequence of a given length, say 200?

Dear all, I found the following behaviour > rf(5,Inf,Inf) [1] 1 1 1 1 1 but > qf(0.1,Inf,Inf) [1] NaN Warning messages: 1: In qf(0.1, Inf, Inf) : value out of range in 'lgamma' 2: In qf(p, df1, df2, lower.tail, log.p) : NaNs produced incidentally, > pf(1.00000000000001,Inf,Inf) [1] 1 > pf(1.0000000000000001,Inf,Inf) [1] 0.5 Is this the expected behaviour? Thanks

Hi, I am looking for a package to estimate regime switching models (states following a markov chain). I found packages for Hidden Markov Models but I am looking for something a little different: In the HMM the conditional distribution of the observations (give the state) is a known distribution (normal or others), while the package I need should allow to set a conditional distribution (given the

R Community - I am attempting to fit a model as described in Hampton, Bossaerts, and O'doherty (J. Neuroscience) 2006. They use a bayesian hidden markov model to model the Reversal Learning data. I have tried using HMM and depmixS4 with no success. My data is a Reversal Learning Task in which there are 3 sets of patterns over 3 blocks. The participant receives incorrect or correct

Greetings fellow R entusiasts! We have some problems converting a computer routine written initially for Gauss to estimate a Markov Regime Switching analysis with Time Varying Transition Probability. The source code in Gauss is here: http://www.econ.washington.edu/user/cnelson/markov/programs/hmt_tvp.opt We have converted the code to R, and it's running without errors, but we have some

According to ?parCapply: parRapply and parCapply always return a vector. This appears not to be the case in the following minimal reproducible example: > library(parallel) > nslaves <- 2 > cl <- makeCluster(nslaves) > X <- matrix(2,nrow=3,ncol=4) > X <- rbind(c(1,1,0,1),X) > tv <- parCapply(cl,X,FUN=function(x){ +

minimal reproducible example plot(1,1) identify(1,1) # or locator() now, trying to close the window by clicking on the cross of the upper right corner causes Rgui (and Rterm) to crash. I see the same behaviour on 2 different Windows PC (one with Win 8.1 and one with Win 10). I did not see the problem in linux (see below) WINDOWS ************** > sessionInfo() R version 3.3.0 beta

Dear all, it looks like that something is wrong with the /bin/windows/base/rpatched.html page as it seems pointing to the 2.8.1rc version. Also, I do not know if it is relevant but notice the dates of the following files on ftp://ftp.stat.math.ethz.ch/Software/CRAN/bin/windows/base/ R-2.8.1pat-win32.exe 31963 KB 22/12/2008 16.15.00 R-2.8.1rc-win32.exe 31991 KB 25/12/2008 9.30.00 thank

I tried to check or build a package under windows xp but I got the error the package can not be installed (without any details in the install.out file) I work with R-2.5.0, Miktex 2.5.0, and I have installed the unix tools.zip, Perl and Microsoft HTML Workshop. The path environment is ok. Have someone else encountered the same problem? Thank you, Cinzia

Hello, I work under windows xp and I am trying to build a R package with a subroutine written in fortran 90. I have installed all the updated tools and I am working with R-2.4.0 or R-2.5.0. When I check a package with a subroutine in fortran 77 (and extension f) everything is ok. When I try to build the same package with a subroutine in fortran 90 (with extension f90) the following warning

Dear all, there seems to be a problem with displayed legends when a multiple figure environment is used, see the following example: par(mfrow=c(1,2)) curve(dnorm,col=4,from=-4,to=4); legend(-4,0.3,legend="curve",lty=1,col=4) legend(-4,0.2,legend="curve",lty=1,col=4) On my machines the first time the command legend() is issued the legend box stretches over the curve.