hi, hi, good morning everyone. I have a time series with binary outputs like : 0001011110100.................etc. Now I want to forecast the future values of that. Can anyone please tell me whether there is any tools exist in literature for dealing with this kind of binary observation? If possible please provide me some good references in net as well. rgd, Megh __________________________________________________ [[alternative HTML version deleted]]
Hi Megh, One good reference for your problem could be Harvey(1989), "Forecasting, Structural Time Series Models and the Kalman Filter", Cambridge University Press. In section 6.6.2, he includes the treatment of binomial and multinomial observations using state space models. Hope it helps, Leonardo Trujillo ____________________________________________ Leonardo Trujillo Division of Social Statistics University of Southampton trujillo at soton.ac.uk -------------------------------------------- -----Original Message----- From: r-help-bounces at stat.math.ethz.ch [mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of Megh Dal Sent: 04 May 2007 08:12 To: r-help at stat.math.ethz.ch Subject: [R] Analysis for Binary time series hi, hi, good morning everyone. I have a time series with binary outputs like : 0001011110100.................etc. Now I want to forecast the future values of that. Can anyone please tell me whether there is any tools exist in literature for dealing with this kind of binary observation? If possible please provide me some good references in net as well. rgd, Megh __________________________________________________ [[alternative HTML version deleted]] ______________________________________________ R-help at stat.math.ethz.ch 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.
>>>>> "Megh" == Megh Dal <megh700004 at yahoo.com> >>>>> on Fri, 4 May 2007 00:12:25 -0700 (PDT) writes:Megh> hi, good morning everyone. I have a time series with Megh> binary outputs like : Megh> 0001011110100.................etc. Now I want to Megh> forecast the future values of that. Can anyone please Megh> tell me whether there is any tools exist in literature Megh> for dealing with this kind of binary observation? If Megh> possible please provide me some good references in net Megh> as well. Since you're asking on R-help : The R package "VLMC" (variable length markov chains) works with such "finite alphabet" time-series and has been applied to such successfully in the past. Do install.packages("VLMC") library(VLMC) ?vlmc It contains the following References Buhlmann P. and Wyner A. (1998) Variable Length Markov Chains. Annals of Statistics 27, 480--513. M?chler M. and B?hlmann P. (2004) Variable Length Markov Chains: Methodology, Computing, and Software. J. Computational and Graphical Statistics 2, 435--455. -- Martin Maechler, ETH Zurich
Seemingly Similar Threads
- fitting Markov chains
- A matrix automation problem
- vlmc - "In vlmc(traffic.clusters.stationary, cutoff = i) : alphabet with >1-letter strings; trying to abbreviate"
- R 2.3.0: Use of NULL as an environment is deprecated
- R 2.3.0: Use of NULL as an environment is deprecated