Skip to main content

Research Repository

Advanced Search

Multinomial logistic regression on Markov chains for crop rotation modelling

Paton, Lewis; Troffaes, Matthias C.M.; Boatman, Nigel; Hussein, Mohamud; Hart, Andy

Authors

Lewis Paton

Nigel Boatman

Mohamud Hussein

Andy Hart



Abstract

Often, in dynamical systems such as farmer’s crop choices, the dynamics are driven by external non-stationary factors, such as rainfall, temperature and agricultural input and output prices. Such dynamics can be modelled by a non-stationary Markov chain, where the transition probabilities are multinomial logistic functions of such external factors. We extend previous work to investigate the problem of estimating the parameters of the multinomial logistic model from data. We use conjugate analysis with a fairly broad class of priors, to accommodate scarcity of data and lack of strong prior expert opinion. We discuss the computation of bounds for the posterior transition probabilities. We use the model to analyse some scenarios for future crop growth.

Citation

Paton, L., Troffaes, M. C., Boatman, N., Hussein, M., & Hart, A. (2014). Multinomial logistic regression on Markov chains for crop rotation modelling. In Information processing and management of uncertainty in knowledge-based systems : 15th International Conference, IPMU 2014, Montpellier, France, July 15-19, 2014 ; proceedings, part III (476-485). https://doi.org/10.1007/978-3-319-08852-5_49

Conference Name Information Processing and Management of Uncertainty in Knowledge-Based Systems
Conference Location Montpellier, France
Publication Date Jul 19, 2014
Deposit Date Sep 15, 2014
Pages 476-485
Series Title Communications in computer and information science
Series Number 444
Series ISSN 1865-0929
Book Title Information processing and management of uncertainty in knowledge-based systems : 15th International Conference, IPMU 2014, Montpellier, France, July 15-19, 2014 ; proceedings, part III.
ISBN 9783319088518
DOI https://doi.org/10.1007/978-3-319-08852-5_49

You might also like



Downloadable Citations