Hazard Rates Based on Isoprobability Contours
A new “scalar” definition of a (contour) multivariate hazard rate based on variation of probability distribution across the isoprobability contours is motivated and described. Several examples involving specific multivariate distributions justifying the usefulness of this definition are presented. General structures of “constant” contour multivariate hazard rates as well as increasing contour multivariate hazard rates are described.
Key Wordshazard rates isoprobability contours logarithmic transform power transform multivariate distributions exponential distribution characterizations
Unable to display preview. Download preview PDF.
- Block, H.W. (1973). Monotone hazard and failure rates for absolutely continuous multivariate distributions. Department of Mathematics Research Report #73–20, University of Pittsburgh. Also Naval Research Logistics Quarterly, 24, 1977, 627–638.Google Scholar
- Fraser, D.A.S. (1963). The Structure of Inference. Wiley, New York.Google Scholar
- Fréchet, M. (1951). Sur les tableaux de correlation dont les marges sont données. Annales de l’Universite de Lyon, Section A, Ser. 3, 14, 53–77.Google Scholar
- Simoni, de S. (1968). Su una estensione delle curve normali di ordina r alle variabili doppie. Statistica (Bologna), 28, 151–170.Google Scholar
- Styen, H. S. (1960). On regression properties of multivariate probability functions of Pearson’s type. Proceedings of the Royal Academy of Science, Amsterdam, 63, 302–311.Google Scholar
- Uven, M. J. van. (1947–1948). Extension of Pearson’s probability distributions to two variables, I-IV. Proceedings of the Royal Academy of Sciences, Amsterdam, 50, 1063–1070, 1252–1264; 51, 41–52, 191–196.Google Scholar