Statistical estimation and prediction for generalized rayleigh record data

Mohamed T. Madi, Mohammad Z. Raqab

    Research output: Contribution to journalArticlepeer-review

    Abstract

    Statistical estimation and prediction of record values have important practical applications especially, in the prediction of rainfall extremes, highest water levels and air record temperatures. Importance sampling is used to estimate the parameters of the generalized Rayleigh (GR) distribution, on the basis of observed GR records. The Gibbs and Metropolis samplers are implemented to predict the future records. A real data set representing the maximum flood levels for the Susquehanna River in Pennsylvania is used to illustrate the results developed here.

    Original languageEnglish
    Pages (from-to)145-156
    Number of pages12
    JournalJournal of Applied Statistical Science
    Volume21
    Issue number2
    Publication statusPublished - 2013

    Keywords

    • Bayesian estimation
    • Bayesian prediction
    • Generalized rayleigh distribution
    • Gibbs and metropolis sampling
    • Importance sampling
    • Record statistics

    ASJC Scopus subject areas

    • Statistics and Probability

    Fingerprint

    Dive into the research topics of 'Statistical estimation and prediction for generalized rayleigh record data'. Together they form a unique fingerprint.

    Cite this