Format

Send to

Choose Destination
Water Sci Technol. 2013;67(8):1786-92. doi: 10.2166/wst.2013.056.

Markov modulated Poisson process models incorporating covariates for rainfall intensity.

Author information

1
School of Computing and Mathematical Sciences, University of Greenwich, Old Royal Naval College, Park Row, Greenwich, London SE10 9LS, United Kingdom. R.Thayakaran@gre.ac.uk

Abstract

Time series of rainfall bucket tip times at the Beaufort Park station, Bracknell, in the UK are modelled by a class of Markov modulated Poisson processes (MMPP) which may be thought of as a generalization of the Poisson process. Our main focus in this paper is to investigate the effects of including covariate information into the MMPP model framework on statistical properties. In particular, we look at three types of time-varying covariates namely temperature, sea level pressure, and relative humidity that are thought to be affecting the rainfall arrival process. Maximum likelihood estimation is used to obtain the parameter estimates, and likelihood ratio tests are employed in model comparison. Simulated data from the fitted model are used to make statistical inferences about the accumulated rainfall in the discrete time interval. Variability of the daily Poisson arrival rates is studied.

PMID:
23579834
DOI:
10.2166/wst.2013.056
[Indexed for MEDLINE]

Supplemental Content

Loading ...
Support Center