Higher degree stop-loss transforms and stochastic orders — (I) Theory

ZusammenfassungDie Stop-Loss Transformierten eines höheren Grades und ihre logarithmische Ableitungen, genaant Stop-Loss Raten eines höheren Grades, werden untersucht, um Einsicht in die Hierarchie der Stop-Loss Ordnungen und verwandte stochastische Ordnungen zu erlangen. Mit Hilfe von Differential und Integral rekursive Relationen werden zwei Charakterisierungen von Gupta und Gupta (1983) auf einfache Weise hergeleitet. Diese Resultate zeigen, daß eine Verteilungsfunktion eindeutig durch eine Stop-Loss Transformierte oder Stop-Loss Rate eines höheren Grades definiert ist. Klassen ISLR (n) von Verteilungen mit einer wachsenden Stop-Loss Rate des Grades n werden betrachtet. Es wird gezeigt, daß die Eigenschaft ISLR (n) die Eigenschaft ISLR (n+1) zur Folge hat, was das wohlbekannte Resultat von Bryson and Siddiqui (1969) für den Fall n=0 verallgemeinert. Hinreichende Bedingungen für eine Stop-Loss Ordnung eines höheren Grades werden anhand von Stop-Loss Raten Ordnungen und Stop-Loss Raten Gefährlichkeitsordnungen formuliert. Zwei neue Charakterisierungen der Stop-Loss Ordnungen eines höheren Grades, welche die Vorzeichenänderungen der Stop-Loss Transformierten und der Stop-Loss Raten berücksichtigt, werden aufgestellt. Anwendungen in Versicherungsmathematik folgen in Teil (II) dieser Abhandlung.SummaryThe higher degree stop-loss transforms and their logarithmic derivatives, called higher degree stop-loss rate functions, are studied to get insight into the hierarchical theory of the higher degree stop-loss orders and related stochastic orders. Based on differential-integral recursive relationships, we derive in a simple way two characterization results by Gupta and Gupta (1983), which state that the higher degree stop-loss transforms and the higher degree stop-loss rate functions uniquely determine a distribution function. Classes ISLR (n) of distributions with an increasing stop-loss rate function of degree n are considered, and it is shown that ISLR (n) implies ISLR (n+1). This result generalizes the well-known fact by Bryson and Siddiqui (1969) that a distribution with an increasing failure rate has necessarily a decreasing mean residual life. Necessary and sufficient conditions, which guarantee that ISLR (n+1) implies ISLR (n), are formulated. Using notions of higher degree stop-loss rate order and higher degree stop-loss rate dangerousness order, sufficient conditions for a higher degree stop-loss order relation are established. Two new sign change characterizations of the higher degree stop-loss order by means of higher degree stop-loss transforms and higher degree stop-loss rate functions are derived. Applications in actuarial mathematics follow in part (II) of the present work.

[1]  R. Szekli Stochastic Ordering and Dependence in Applied Probability , 1995 .

[2]  On Characterization of Distributions by Conditional Expectations , 1975 .

[3]  Harshinder Singh,et al.  The Reversed Hazard Rate Function , 1998, Probability in the Engineering and Informational Sciences.

[4]  Marc Goovaerts,et al.  Ordering of actuarial risks , 1994 .

[5]  Hans U. Gerber,et al.  An introduction to mathematical risk theory , 1982 .

[6]  Tomasz Rolski,et al.  Order relations in the set of probability distribution functions and their applications in queueing theory , 1976 .

[7]  W. Hürlimann Higher degree stop-loss transforms and stochastic orders — (II) Applications , 2000 .

[8]  M. C. Bhattacharjee The Class of Mean Residual Lives and Some Consequences , 1982 .

[9]  J. Laffont,et al.  A Theory of Incentives in Procurement and Regulation , 1993 .

[10]  On characterization of distribution by conditional expectation , 1975 .

[11]  Richard E. Barlow,et al.  Statistical Analysis of Reliability and Life Testing Models , 1975 .

[12]  Ward Whitt,et al.  The effect of variability in the GI/G/s queue , 1980, Journal of Applied Probability.

[13]  M. Rothschild,et al.  Increasing risk: I. A definition , 1970 .

[14]  M. M. Siddiqui,et al.  Some Criteria for Aging , 1969 .

[15]  F. Proschan,et al.  The Mathematical Theory of Reliability. , 1966 .

[16]  Peter C. Fishburn,et al.  Stochastic Dominance and Moments of Distributions , 1980, Math. Oper. Res..

[17]  Rob Kaas,et al.  Ordering claim size distributions and mixed Poisson probabilities , 1995 .

[18]  William H. Jean The Geometric Mean and Stochastic Dominance , 1980 .

[19]  L. Eeckhoudt,et al.  Demand for risky assets and the monotone probability ratio order , 1995 .

[20]  O. L. Smith,et al.  ON THE CUMULANTS OF RENEWAL PROCESSES , 1959 .

[21]  M. Rothschild,et al.  Increasing risk II: Its economic consequences , 1971 .

[22]  Richard E. Barlow,et al.  Statistical Theory of Reliability and Life Testing: Probability Models , 1976 .

[23]  G. Whitmore,et al.  Third-Degree Stochastic Dominance , 1970 .

[24]  Moshe Shaked,et al.  Stochastic orders and their applications , 1994 .

[25]  A. Müller Orderings of risks: A comparative study via stop-loss transforms , 1996 .

[26]  Dietrich Stoyan,et al.  Qualitative Eigenschaften und Abschätzungen stochastischer Modelle , 1977 .

[27]  H. Gerber,et al.  Some Inequalities for Stop-Loss Premiums , 1977, ASTIN Bulletin.

[28]  J. Keilson,et al.  Uniform stochastic ordering and related inequalities , 1982 .

[29]  Karl Hinderer Grundbegriffe der Wahrscheinlichkeitstheorie , 1972 .

[30]  A unification of some order relations , 1996 .

[31]  Pushpa L. Gupta,et al.  On the moments of residual life in reliability and some characterization results , 1983 .

[32]  W. Hürlimann On Stop-Loss Order and the Distortion Pricing Principle , 1998 .

[33]  W. Heilmann Charakterisierungen von Lebensdauer- und Schadenhöhenverteilungen , 1984 .

[34]  Samuel Karlin,et al.  Generalized convex inequalities , 1963 .

[35]  Fonctions extrémales et gain financier , 1997 .

[36]  Ole Hesselager Ordering of risks. Theory and actuarial applications. : van Heerwaarden Angela, Tinbergen Institute, Research Series, Amsterdam, 1991, 159 pp. , 1994 .

[37]  Peter C. Fishburn,et al.  Optimal Portfolios with One Safe and One Risky Asset: Effects of Changes in Rate of Return and Risk , 1976 .

[38]  Mukhtar M. Ali Stochastic Ordering and Kurtosis Measure , 1974 .

[39]  G. L. O'Brien Stochastic Dominance and Moment Inequalities , 1984, Math. Oper. Res..

[40]  William S. Jewell,et al.  Gerber Hans U.: An Introduction to Mathematical Risk Theory Huebner Foundation Monograph No. 8. Homewood, Ill.: Richard D. Irwin Inc., 1980, xv + 164, paperbound, $ 15.95 , 1980, ASTIN Bulletin.