move.HMM-package: Fit hidden Markov models and hidden semi-Markov...

In benaug/move.HMM: Fit HMM and HSMM animal movement models

Description

move.HMM is used to fit hidden Markov models and hidden semi-Markov approximations, allowing for multiple observation variables with different distributions. Models can be compared via AICc and fit can be assessed by plotting the fitted models, ordinary normal pseudoresiduals, and goodness-of-fit plots introduced by Altman (2004). Conditional state probabilities can be calculated and global decoding can be performed via the Viterbi algorithm. Support for Rcpp is included which can significantly speed up fitting HMMs to longer time series and HSMMs generally. The package was developed for inferring behavioral states from animal movement and sensor data, but is more widely applicable.

Details

Package:	move.HMM
Type:	Package
Version:	1.1
Date:	2013-10-08
License:	GPL(>=2)
See move.HMM.mle and move.HSMM.mle for details about how to use the package.

Author(s)

Ben Augustine and Roland Langrock

Maintainer: Ben Augustine <[e-mail]>

References

Langrock, R., King, R., Matthiopoulos, J., Thomas, L., Fortin, D., & Morales, J. M. (2012). Flexible and practical modeling of animal telemetry data: hidden Markov models and extensions. Ecology, 93(11), 2336-2342.

MacKay Altman, R. (2004). Assessing the Goodness-of-Fit of Hidden Markov Models. Biometrics, 60(2), 444-450.

Zucchini, W., & MacDonald, I. L. (2009). Hidden Markov models for time series: an introduction using R. CRC Press.

benaug/move.HMM documentation built on Jan. 23, 2022, 4:29 a.m.