A Compound of Geeta Distribution with Generalized Beta Distribution

Similar documents
Decision Science Letters

8 Laplace s Method and Local Limit Theorems

Estimation of Parameters in Weighted Generalized Beta Distributions of the Second Kind

Travelling Profile Solutions For Nonlinear Degenerate Parabolic Equation And Contour Enhancement In Image Processing

New Expansion and Infinite Series

Continuous Random Variables

A REVIEW OF CALCULUS CONCEPTS FOR JDEP 384H. Thomas Shores Department of Mathematics University of Nebraska Spring 2007

Solutions of Klein - Gordan equations, using Finite Fourier Sine Transform

Research Article Moment Inequalities and Complete Moment Convergence

Jim Lambers MAT 169 Fall Semester Lecture 4 Notes

Journal of Inequalities in Pure and Applied Mathematics

Hybrid Group Acceptance Sampling Plan Based on Size Biased Lomax Model

Time Truncated Two Stage Group Sampling Plan For Various Distributions

NOTE ON TRACES OF MATRIX PRODUCTS INVOLVING INVERSES OF POSITIVE DEFINITE ONES

A SHORT NOTE ON THE MONOTONICITY OF THE ERLANG C FORMULA IN THE HALFIN-WHITT REGIME. Bernardo D Auria 1

FRACTIONAL INTEGRALS AND

Improvement of Ostrowski Integral Type Inequalities with Application

Chapter 5 : Continuous Random Variables

The use of a so called graphing calculator or programmable calculator is not permitted. Simple scientific calculators are allowed.

Estimation of Binomial Distribution in the Light of Future Data

Research Article Harmonic Deformation of Planar Curves

Research Article On Hermite-Hadamard Type Inequalities for Functions Whose Second Derivatives Absolute Values Are s-convex

MIXED MODELS (Sections ) I) In the unrestricted model, interactions are treated as in the random effects model:

Reversals of Signal-Posterior Monotonicity for Any Bounded Prior

1.9 C 2 inner variations

Hermite-Hadamard type inequalities for harmonically convex functions

Application of Exp-Function Method to. a Huxley Equation with Variable Coefficient *

Songklanakarin Journal of Science and Technology SJST R1 Thongchan. A Modified Hyperbolic Secant Distribution

The Shortest Confidence Interval for the Mean of a Normal Distribution

Normal Distribution. Lecture 6: More Binomial Distribution. Properties of the Unit Normal Distribution. Unit Normal Distribution

Math 113 Fall Final Exam Review. 2. Applications of Integration Chapter 6 including sections and section 6.8

Population Dynamics Definition Model A model is defined as a physical representation of any natural phenomena Example: 1. A miniature building model.

Definite integral. Mathematics FRDIS MENDELU

DUNKL WAVELETS AND APPLICATIONS TO INVERSION OF THE DUNKL INTERTWINING OPERATOR AND ITS DUAL

OBSERVATIONS ON TERNARY QUADRATIC EQUATION z 82 x

1 Probability Density Functions

Construction and Selection of Single Sampling Quick Switching Variables System for given Control Limits Involving Minimum Sum of Risks

1 2-D Second Order Equations: Separation of Variables

Discrete Least-squares Approximations

Edexcel GCE Core Mathematics (C2) Required Knowledge Information Sheet. Daniel Hammocks

Definite integral. Mathematics FRDIS MENDELU. Simona Fišnarová (Mendel University) Definite integral MENDELU 1 / 30

Section 6.1 INTRO to LAPLACE TRANSFORMS

Journal of Inequalities in Pure and Applied Mathematics

ON A CONVEXITY PROPERTY. 1. Introduction Most general class of convex functions is defined by the inequality

Some estimates on the Hermite-Hadamard inequality through quasi-convex functions

Characterizations of the Weibull-X and Burr XII Negative Binomial Families of Distributions

Thomas Whitham Sixth Form

INVESTIGATION OF MATHEMATICAL MODEL OF COMMUNICATION NETWORK WITH UNSTEADY FLOW OF REQUESTS

WHEN IS A FUNCTION NOT FLAT? 1. Introduction. {e 1 0, x = 0. f(x) =

Taylor Polynomial Inequalities

The Existence of the Moments of the Cauchy Distribution under a Simple Transformation of Dividing with a Constant

AQA Further Pure 1. Complex Numbers. Section 1: Introduction to Complex Numbers. The number system

Chapter 1. Basic Concepts

Indefinite Integral. Chapter Integration - reverse of differentiation

P 3 (x) = f(0) + f (0)x + f (0) 2. x 2 + f (0) . In the problem set, you are asked to show, in general, the n th order term is a n = f (n) (0)

ARITHMETIC OPERATIONS. The real numbers have the following properties: a b c ab ac

FUNCTIONS OF α-slow INCREASE

MonotonicBehaviourofRelativeIncrementsofPearsonDistributions

CS 109 Lecture 11 April 20th, 2016

New Integral Inequalities for n-time Differentiable Functions with Applications for pdfs

Lecture 21: Order statistics

Lecture 4: Piecewise Cubic Interpolation

NUMERICAL INTEGRATION. The inverse process to differentiation in calculus is integration. Mathematically, integration is represented by.

ON THE TERNARY QUADRATIC DIOPHANTINE EQUATION

A Companion of Ostrowski Type Integral Inequality Using a 5-Step Kernel with Some Applications

Monte Carlo method in solving numerical integration and differential equation

A basic logarithmic inequality, and the logarithmic mean

Line Integrals. Partitioning the Curve. Estimating the Mass

STEP FUNCTIONS, DELTA FUNCTIONS, AND THE VARIATION OF PARAMETERS FORMULA. 0 if t < 0, 1 if t > 0.

THE INTERVAL LATTICE BOLTZMANN METHOD FOR TRANSIENT HEAT TRANSFER IN A SILICON THIN FILM

University of Texas MD Anderson Cancer Center Department of Biostatistics. Inequality Calculator, Version 3.0 November 25, 2013 User s Guide

Expected Value of Function of Uncertain Variables

A General Dynamic Inequality of Opial Type

Pi evaluation. Monte Carlo integration

1. On some properties of definite integrals. We prove

The logarithmic mean is a mean

Physics 116C Solution of inhomogeneous ordinary differential equations using Green s functions

New Integral Inequalities of the Type of Hermite-Hadamard Through Quasi Convexity

Lesson 1: Quadratic Equations

GENERALIZATIONS OF WEIGHTED TRAPEZOIDAL INEQUALITY FOR MONOTONIC MAPPINGS AND ITS APPLICATIONS. (b a)3 [f(a) + f(b)] f x (a,b)

1.2. Linear Variable Coefficient Equations. y + b "! = a y + b " Remark: The case b = 0 and a non-constant can be solved with the same idea as above.

Exact solutions for nonlinear partial fractional differential equations

INEQUALITIES FOR GENERALIZED WEIGHTED MEAN VALUES OF CONVEX FUNCTION

Mathematic Model of Green Function with Two-Dimensional Free Water Surface *

Tutorial 4. b a. h(f) = a b a ln 1. b a dx = ln(b a) nats = log(b a) bits. = ln λ + 1 nats. = log e λ bits. = ln 1 2 ln λ + 1. nats. = ln 2e. bits.

20 MATHEMATICS POLYNOMIALS

On the degree of regularity of generalized van der Waerden triples

MAC-solutions of the nonexistent solutions of mathematical physics

5 Probability densities

Before we can begin Ch. 3 on Radicals, we need to be familiar with perfect squares, cubes, etc. Try and do as many as you can without a calculator!!!

Conducting Ellipsoid and Circular Disk

A Convergence Theorem for the Improper Riemann Integral of Banach Space-valued Functions

63. Representation of functions as power series Consider a power series. ( 1) n x 2n for all 1 < x < 1

A New Statistic Feature of the Short-Time Amplitude Spectrum Values for Human s Unvoiced Pronunciation

Harmonic Mean Derivative - Based Closed Newton Cotes Quadrature

Research Article Fejér and Hermite-Hadamard Type Inequalities for Harmonically Convex Functions

Orthogonal Polynomials and Least-Squares Approximations to Functions

A new algorithm for generating Pythagorean triples 1

Physics 201 Lab 3: Measurement of Earth s local gravitational field I Data Acquisition and Preliminary Analysis Dr. Timothy C. Black Summer I, 2018

Research Article On New Inequalities via Riemann-Liouville Fractional Integration

Transcription:

Journl of Modern Applied Sttisticl Methods Volume 3 Issue Article 8 5--204 A Compound of Geet Distribution ith Generlized Bet Distribution Adil Rshid University of Kshmir, Sringr, Indi, dilstt@gmil.com T R. Jn University of Kshmir, Sringr, Indi, drtrjn@gmil.com Follo this nd dditionl ors t: http://digitlcommons.yne.edu/jmsm Prt of the Applied Sttistics Commons, Socil nd Behviorl Sciences Commons, nd the Sttisticl Theory Commons Recommended Cittion Rshid, Adil nd Jn, T R. (204) "A Compound of Geet Distribution ith Generlized Bet Distribution," Journl of Modern Applied Sttisticl Methods: Vol. 3 : Iss., Article 8. DOI: 0.22237/jmsm/39897820 Avilble t: http://digitlcommons.yne.edu/jmsm/vol3/iss/8 This Regulr Article is brought to you for free nd open ccess by the Open Access Journls t DigitlCommons@WyneStte. It hs been ccepted for inclusion in Journl of Modern Applied Sttisticl Methods by n uthorized editor of DigitlCommons@WyneStte.

Journl of Modern Applied Sttisticl Methods My 204, Vol. 3, No., 278-286. Copyright 204 JMASM, Inc. ISSN 538 9472 A Compound of Geet Distribution ith Generlized Bet Distribution Adil Rshid University of Kshmir Sringr, Indi T. R. Jn University of Kshmir Sringr, Indi A compound of Geet distribution ith Generlized Bet distribution (GBD) is obtined nd the compound is specilized for different vlues of β. The first order fctoril moments of some specil compound distributions re lso obtined. A chronologicl overvie of recent developments in the compounding of distributions is provided in the introduction. Keyords: Compound distribution, Geet distribution, Generlized Bet Distribution (GBD), fctoril moments Introduction Regrding the problem of the compounding of the probbility distributions, or hs been conducted in this re since 920. It is ell non tht the prmeter in Poisson distribution is considered to be gmm vrite in the fmous rticle by Greenood nd ule (920). Sellm (948) derived probbility distribution from the binomil distribution by regrding the probbility of success s bet vrible beteen sets of trils. The interreltionships mong compound nd generlized distributions ere first explored by Gurlnd (957) fter hich, Molenr (965) discussed some importnt remrs on mixtures of distributions. Dubey (970) derived compound gmm, bet nd F distributions by compounding gmm distribution ith nother gmm distribution nd reducing it to the bet st nd 2 nd ind nd to the F distribution vi suitble trnsformtions. The ppliction of compounding of distributions to clculte moments s explored by Dycz (973). The problem of compounding of distributions s further ddressed by Gerstenorn (993, 996) ho proposed severl compound distributions; Gerstenorn obtined compound of gmm Adil Rshid is PhD Scholr in the Deprtment of Sttistics. Emil t: dilstt@gmil.com. T. R. Jn is Fculty member in the Deprtment of Sttistics. Emil t: drtrjn@gmil.com. 278

RASHID & JAN distribution ith exponentil distribution by treting the prmeter of gmm distribution s n exponentil vrite nd obtined compound of poly ith bet. Gerstenorn (2004) lso found compound of generlized negtive binomil distribution ith generlized bet distribution by treting the prmeter of generlized negtive binomil distribution s generlized bet distribution. Ali, Aslm nd Kzmi (20) improved the informtive prior for the mixture of Lplce distribution under different loss functions. Rshid nd Jn (203) recently obtined compound of zero truncted generlized negtive binomil distribution ith tht of generlized bet distribution. A brod rnge of relevnt references cn be found in studies by Johnson, Kotz nd Kemp (992). The compounding of probbility distributions The folloing definition nd reltions re needed for compounding probbility distributions. A certin compound distribution rises hen ll (or some) prmeters of distribution vry ccording to some probbility distribution, clled the compounding distribution. Suppose Xy is rndom vrible ith distribution function F(x y) tht depends on prmeter y. If prmeter y is considered to be rndom vrible ith distribution function G(y), then the distribution tht hs the distribution function of X is defined by F x cydg y H x () hich is clled compound, here c is n rbitrry constnt or constnt bounded on some intervl (Gurlnd, 957). The occurrence of the constnt c in () hs prcticl justifiction insmuch s the distribution of rndom vrible, in describing phenomenon, often depends on prmeter tht is itself reliztion of nother rndom vrible multiplied by certin constnt. A vrible tht hs distribution function () ill be symbolized by X nd ill be clled compound of the vrible X ith respect to the compounding. Reltion () is symbolized s follos: H x F x cy G y (2) 279

COMPOUND GEETA AND GENERALIZED BETA DISTRIBUTION Consider the cse hen one vrible is discrete ith probbility function P X x cy, if prmeter y is rndom vrible ith density g(y), then () is expressed by i ( ) ( ) ( ) h x P X x g y P X x cy dy (3) i i i Compounding the Geet Distribution ith the Generlized Bet distribution Suppose X is discrete rndom vrible defined over positive integers. The rndom vrible X is sid to hve Geet distribution ith prmeters nd if x x xx ; x,2,... P x; x x 0 ; otherise (4) here 0 nd. The upper limit on hs been imposed for the existence of the men. When, the Geet distribution degenertes nd its probbility mss is concentrted t point x (Consul, 990). The Generlized Bet Distribution (GBD) is distribution given by the density function r y y ;0 y 0; y 0 or y r ;,,, Br /, GB y b r (5) here,,, 0 b r nd ( /, B r ) is bet function. Distribution (5) is specil limit cse of the Bessel distribution (Srod, 973; Seeryn, 986) tht hs been pplied in relibility theory (Oginsi, 979). Consider Geet distribution (4) tht depends on cy : 280

RASHID & JAN x x xx P x; cy cy cy, x,2,3... x x (6) here 0cy, nd is rndom vrible ith GBD (5). Theorem The probbility function of the compound of Geet distribution ith GBD is x x / x r P GB x D c B, K 0 (7) here D x c x x B r /, x x nd x,2,3,,, b,, r 0, 0 cy nd cy Proof: From (3), (5) nd (6) xr2 y xx P GB x D y cy dy 0 K x x xr 2 y K 0 0 D c y dy here D x x c x x. r Br /, Substituting, y t, results in 28

COMPOUND GEETA AND GENERALIZED BETA DISTRIBUTION xr x x P GB x D c t t dt K 0 0 (8) here, x,2,3,,, b,, r 0, nd 0 c. Using the definition of bet function, (7) is obtined. Specil Cses Cse I: When 2 in (4), Hight s distribution results nd compound of the Hight distribution ith generlized bet follos from (8): * x x r P2GB x D 2 c B, 0 (9) here 2x x x c * 2x x D2 ; x,2,3...,, b,, r 0, 0 cy. B r /, Cse II: If b = / nd =, in (5), the bet distribution nd compound of Geet distribution ith bet distribution follo from (8): x c x x here = B r, * x x P Bx D 3 c Bx r, 0 (0) x. Cse III: When β = 2 nd b = /, = in (4) nd (5), respectively obtined re the Hight nd bet distributions nd compound of the Hight distribution ith bet distribution follos from (8): 282

RASHID & JAN here D * 4 x * x P2B x D4 c Bx r, () 0 2x c 2x x B r, x Fctoril moments of the Compound of Geet distribution ith Generlized Bet distribution nd some specil cses Let X y nd X be rndom vrible ith distribution function F ( x y) nd H(X), respectively (see ()), nd let prmeter y hve distribution G(y). Keeping in mind the formul for the so-clled fctoril polynomil l. x x x x x l l l l y m E X E X dg y (2) is clled fctoril moment of order l of the vrible X ith compound distribution (). Reltion (2) is symbolized s l ^ y E X G y. (3) Theorem 2 The first order fctoril moments of the compound of Geet distribution ith GBD is given by m cy GB y b r ; ;,,, 0 c /, B r / r r B, c B, (4) 283

COMPOUND GEETA AND GENERALIZED BETA DISTRIBUTION Proof: by The first order fctoril moments of the Geet distribution is given m,. Thus, from (3), the st order fctoril moment of the compound of the Geet distribution ith Generlized bet distribution if cy is r ;,,,, cy 0 cy y m cy GB y b r y r dy B r, c 0 r y r y y dy c y dy. r B r, 0 0 Substituting, y t results in r r c 0 t t dt c t t dt B r, 0 0 r r c 0 t t dt c t t dt B r, 0 0 (5) Using the definition of bet function, (4) is obtined. Specil Cse When b = / nd = in (5), the st order fctoril moment of the compound of Geet distribution ith bet distribution is obtined s c m ; cy B y;,/, r, Br, cb r,. B r 0, 284

RASHID & JAN Theorem 3 First order fctoril moments of the compound of Hight ith generlized bet distribution. m 2; cy GB y;, b, r, 2 c 0 r r (6) B, c B,. B r, Proof: The result follos directly from (5) for 2, m cy GB y b r 2;,,,, 2c /, / r r 0 B r t t dt c t t dt 0 0 (7) hich yields (6). Specil cse When b=/, = in (7) the folloing result is obtined: 2c 0 m 2; cy B y;,/, r, B r, cb r, B r, hich gives the st order fctoril moment of the compound of the Hight distribution ith bet distribution. References Ali, S., Aslm, M., & Kzmi, S. M. (20). Improved informtive prior for the mixture of LPlce distribution under different loss functions. Journl of Relibility nd Sttisticl Studies, 4(2): 57-82. Consul, P. C. (990). Geet distribution nd its properties. Communictions in Sttistics Theory nd Methods, 9: 305-3068. 285

COMPOUND GEETA AND GENERALIZED BETA DISTRIBUTION Dubey, D. S. (970). Compound gmm, bet nd F distributions. Metri, 6(): 27-3. Dycz, W. (973). Appliction of compounding of distribution to determintion of moments in Polish. Mtemty, 3: 205-230. Gerstenorn, T. (993). A compound of the generlized gmm distribution ith the exponentil one. Recherches surles deformtions, 6(): 5-0. Gerstenorn, T. (996). A compound of the Poly distribution ith the bet one. Rndom Opertors nd Stochstic Equtions, 4(2): 03-0. Gerstenorn, T. (2004). A compound of the generlized negtive binomil distribution ith the generlized bet one. Centrl Europen Journl of Mthemtics, 2(4): 527-537. Greenood, M., & ule, G. U. (920). An inquiry into the nture of frequency distribution representtive of multiple hppenings ith prticulr reference to the occurrence of multiple ttcs of disese or of repeted ccidents. Journl of the Royl Sttisticl Society, 83: 255-279. Gurlnd, J. (957). Some interreltions mong compound nd generlized distributions. Biometri, 44: 265-268. Johnson, N. L., nd Kotz, S. (969). Discrete distributions (First Edition). Boston, MA: Houghton Miffin. Molenr, W. (965). Some remrs on mixtures of distributions. In Proceedings of the 35 th Session of the Interntionl Sttisticl Institute, Belgrde (Bulletin de l'institut interntionl de sttistique, 4), pp. 764-765. Oginsi, L. (979). Appliction of distribution of the Bessel type in relibility theory. Mtemty, 2: 3-42, (in Polish). Rshid, A., & Jn, T. R. (203). A compound of zero truncted generlized negtive binomil distribution ith the generlized bet distribution. Journl of Relibility nd Sttisticl Studies, 6(): -9. Seeryn J. G. (986). Some probbilistic properties of Bessel distribution. Mtemty, 9: 69-87. Sellm, J. G. (948). A probbility distribution derived from the binomil distribution by regrding the probbility of success s vrible beteen the sets of trils. Journl of the Royl Sttisticl Society, Series B, 0: 257-26. Srod, T. (973). On some generlized Bessel- type probbility distribution. Mtemty, 4: 5-3. 286