Prior distributions. July 29, 2002

Similar documents
Taylor Polynomials. The Tangent Line. (a, f (a)) and has the same slope as the curve y = f (x) at that point. It is the best

SM2H. Unit 2 Polynomials, Exponents, Radicals & Complex Numbers Notes. 3.1 Number Theory

10.5 Power Series. In this section, we are going to start talking about power series. A power series is a series of the form

INTEGRATION TECHNIQUES (TRIG, LOG, EXP FUNCTIONS)

Surds, Indices, and Logarithms Radical

PROGRESSIONS AND SERIES

 n. A Very Interesting Example + + = d. + x3. + 5x4. math 131 power series, part ii 7. One of the first power series we examined was. 2!

Chapter 7 Infinite Series

Students must always use correct mathematical notation, not calculator notation. the set of positive integers and zero, {0,1, 2, 3,...

Unit 1. Extending the Number System. 2 Jordan School District

Chapter 2 Infinite Series Page 1 of 9

Double Sums of Binomial Coefficients

Inference on One Population Mean Hypothesis Testing

Infinite Series Sequences: terms nth term Listing Terms of a Sequence 2 n recursively defined n+1 Pattern Recognition for Sequences Ex:

1.3 Continuous Functions and Riemann Sums

1. (25 points) Use the limit definition of the definite integral and the sum formulas to compute. [1 x + x2

Math 3B Midterm Review

Week 13 Notes: 1) Riemann Sum. Aim: Compute Area Under a Graph. Suppose we want to find out the area of a graph, like the one on the right:

Limit of a function:

Chapter System of Equations

1 Tangent Line Problem

Introduction to mathematical Statistics

Discrete Mathematics and Probability Theory Spring 2016 Rao and Walrand Lecture 17

Linear Programming. Preliminaries

FOURIER SERIES PART I: DEFINITIONS AND EXAMPLES. To a 2π-periodic function f(x) we will associate a trigonometric series. a n cos(nx) + b n sin(nx),

Review of Sections

Lesson 4 Linear Algebra

( ) k ( ) 1 T n 1 x = xk. Geometric series obtained directly from the definition. = 1 1 x. See also Scalars 9.1 ADV-1: lim n.

INFINITE SERIES. ,... having infinite number of terms is called infinite sequence and its indicated sum, i.e., a 1

The Exponential Function

Convergence rates of approximate sums of Riemann integrals

Approximate Integration

Frequency-domain Characteristics of Discrete-time LTI Systems

Why study large deviations? The problem of estimating buer overow frequency The performance of many systems is limited by events which have a small pr

POWER SERIES R. E. SHOWALTER

0 otherwise. sin( nx)sin( kx) 0 otherwise. cos( nx) sin( kx) dx 0 for all integers n, k.

: : 8.2. Test About a Population Mean. STT 351 Hypotheses Testing Case I: A Normal Population with Known. - null hypothesis states 0

Algebra II, Chapter 7. Homework 12/5/2016. Harding Charter Prep Dr. Michael T. Lewchuk. Section 7.1 nth roots and Rational Exponents

Lecture 38 (Trapped Particles) Physics Spring 2018 Douglas Fields

Background 1. Cramer-Rao inequality

f(bx) dx = f dx = dx l dx f(0) log b x a + l log b a 2ɛ log b a.

Chapter 5. The Riemann Integral. 5.1 The Riemann integral Partitions and lower and upper integrals. Note: 1.5 lectures

Schrödinger Equation Via Laplace-Beltrami Operator

334 MATHS SERIES DSE MATHS PREVIEW VERSION B SAMPLE TEST & FULL SOLUTION

We will begin by supplying the proof to (a).

King Fahd University of Petroleum & Minerals

Vectors. Vectors in Plane ( 2

The total number of permutations of S is n!. We denote the set of all permutations of S by

In an algebraic expression of the form (1), like terms are terms with the same power of the variables (in this case

[ 20 ] 1. Inequality exists only between two real numbers (not complex numbers). 2. If a be any real number then one and only one of there hold.

Avd. Matematisk statistik

Probability and Stochastic Processes: A Friendly Introduction for Electrical and Computer Engineers Roy D. Yates and David J.

2017/2018 SEMESTER 1 COMMON TEST

y udv uv y v du 7.1 INTEGRATION BY PARTS

Statistics for Financial Engineering Session 1: Linear Algebra Review March 18 th, 2006

A general theory of minimal increments for Hirsch-type indices and applications to the mathematical characterization of Kosmulski-indices

Solutions to Problem Set 7

lecture 16: Introduction to Least Squares Approximation

Important Facts You Need To Know/Review:

Certain sufficient conditions on N, p n, q n k summability of orthogonal series

Convergence rates of approximate sums of Riemann integrals

8.3 Sequences & Series: Convergence & Divergence

Name: A2RCC Midterm Review Unit 1: Functions and Relations Know your parent functions!

ENGINEERING PROBABILITY AND STATISTICS

Exponential and Logarithmic Functions (4.1, 4.2, 4.4, 4.6)

EVALUATING DEFINITE INTEGRALS

Graphing Review Part 3: Polynomials

Numbers (Part I) -- Solutions

Numerical Solutions of Fredholm Integral Equations Using Bernstein Polynomials

2015/2016 SEMESTER 2 SEMESTRAL EXAMINATION

Canonical Form and Separability of PPT States on Multiple Quantum Spaces

Content: Essential Calculus, Early Transcendentals, James Stewart, 2007 Chapter 1: Functions and Limits., in a set B.

Review of the Riemann Integral

Basic Limit Theorems

Indices and Logarithms

Orthogonality, orthogonalization, least squares

Approximations of Definite Integrals

Options: Calculus. O C.1 PG #2, 3b, 4, 5ace O C.2 PG.24 #1 O D PG.28 #2, 3, 4, 5, 7 O E PG #1, 3, 4, 5 O F PG.

A GENERAL METHOD FOR SOLVING ORDINARY DIFFERENTIAL EQUATIONS: THE FROBENIUS (OR SERIES) METHOD

Particle in a Box. and the state function is. In this case, the Hermitian operator. The b.c. restrict us to 0 x a. x A sin for 0 x a, and 0 otherwise

Section 6.3: Geometric Sequences

Crushed Notes on MATH132: Calculus

MA123, Chapter 9: Computing some integrals (pp )

Probability for mathematicians INDEPENDENCE TAU

General properties of definite integrals

BC Calculus Review Sheet

Exponential Families and Bayesian Inference

2a a a 2a 4a. 3a/2 f(x) dx a/2 = 6i) Equation of plane OAB is r = λa + µb. Since C lies on the plane OAB, c can be expressed as c = λa +

ELEG 3143 Probability & Stochastic Process Ch. 5 Elements of Statistics

=> PARALLEL INTERCONNECTION. Basic Properties LTI Systems. The Commutative Property. Convolution. The Commutative Property. The Distributive Property

Math 140 Introductory Statistics

Simpson s 1/3 rd Rule of Integration

Reversing the Arithmetic mean Geometric mean inequality

Limits and an Introduction to Calculus

ALGEBRA. Set of Equations. have no solution 1 b1. Dependent system has infinitely many solutions

Sequence and Series of Functions

Similar idea to multiplication in N, C. Divide and conquer approach provides unexpected improvements. Naïve matrix multiplication

Power Series Solutions to Generalized Abel Integral Equations

1 Section 8.1: Sequences. 2 Section 8.2: Innite Series. 1.1 Limit Rules. 1.2 Common Sequence Limits. 2.1 Denition. 2.

* power rule: * fraction raised to negative exponent: * expanded power rule:

Transcription:

Prior distributios Aledre Tchourbov PKI 357, UNOmh, South 67th St. Omh, NE 688-694, USA Phoe: 4554-64 E-mil: tchourb@cse.ul.edu July 9, Abstrct This documet itroduces prior distributios for the purposes of Byesi sttistics. Usig prior beliefs we c sigifictly improve our sttisticl ifereces bsed o observtios. Most of the books o sttistics do ot cover the mteril preseted. Here we try to collect the iformtio vilble o cojugte priors to certi distributios. Itroductio Accordig to the Byesi rule [], we c epress posterior probbility of certi evet H give some dt with the formul P dt HP H P H dt = P dt The probbility of H give the dt is clled the posterior probbility of H. The posterior equls to the likelihood time the prior divided by mrgil probbility of dt. The pper shows wht priors we c hve d how they ffect posterior distributios give likelihood. Prior d posterior distributios Sometimes prior distributio c be pproimted by oe tht is i coveiet fmily of distributios, which combies with the likelihood to produce posterior tht is mgeble. We see tht objective wy of buildig priors for the biomil prmeter ws to use the cojugte fmily distributio tht hs the property tht the updted distributio is i the sme fmily. I geerl, if the prior distributio belogs to fmily G, the dt hve distributio belogig to fmily H, d the posterior distributio lso belogs to G, the we sy tht G is fmily of cojugte priors to H. Thus, the bet distributio is cojugte prior to the biomil, d the orml is self cojugte. Cojugte priors my ot eist; whe they do, selectig member of the cojugte fmily s prior is doe mostly for mthemticl coveiece, sice the posterior c be evluted very simply. More geerlly, umericl methods of itegrtio would hve to be used to evlute the posterior. I would like to thk professors Heshm Ali d Jiteder Deogu for the opportuity to work o this project

Observtios Prior Posterior Beroulli Bet Bet Poisso Gmm Gmm Biomil Bet Bet Norml Norml Norml Norml Gmm Gmm Tble : Cojugte priors 3 Bet priors From Byes 763: A white billird bll W is rolled log lie d we look t where it stops, scle the tble from to. We suppose tht it hs uiform probbility of fllig ywhere o the lie. It stops t poit p. A red billird bll R is the rolled times uder the sme uiform ssumptio. X the deotes the umber of times R goes o further th W wet. Give X, wht iferece c we mke bout p? Here we re lookig for the posterior distributio of p give X. The prior distributio of p is uiform gp = Uiform, = Bet, =. Give p, X hs biomil distributio P X = p = p p The overll distributio of the umber of successes is the sum of probbilities for ll possible p s P < p < b, X = = p p dp P X = = p p dp Suppose we throw ll + blls o the tble, d choose the red oe. The the probbility tht the red oe hs whites to the left of it is. So we hve + P X = = p p dp = p p dp = + p p dp =!! +! ccordig to defiitio formul for bet fuctio Br, s = we hve X B, p p r p s dp = r!s! r + s! = ΓrΓs Γr + s

P X = = p p dp = B +, + P < p < b X = = p p dp B +, + P < p < b X = = p p dp B +, + which is bet distributio of p with prmeters + d +. The desity fuctio f of the bet distributio is fp = Γ + b ΓΓb p p b, p Emple Suppose tht the prior distributio of p is Bet, b, i.e. gp = p p b B, b Likelihood hs biomil distributio f p = p p The posterior distributio of p give is hp = f pgp f = B, b p p p p b p + p +b dp B, b = p+ p +b B +, + b = Bet +, + b This distributio is thus bet s well with prmeters = + d b = b +. 4 Norml prior Here we follow emple o pge 589 [], which proves the Norml cojugte prior for Norml distributio. The cojugte for Norml likelihood is the Norml distributio. Emple We cosider iferece cocerig ukow me with kow vrice. 3

First, suppose tht the prior distributio of µ is Nµ, σ. Nµ, σ is tke. The posterior distributio of µ is hµ = f µgµ = f µgµ f µgµ f µgµdµ A sigle observtio X µ µ σ π ep µ ep σ σ π σ µ ep µ µ σ σ ep µ σ + µ σ σ + µ + σ σ + µ σ Let, b d c be the coefficiets i the qudrtic polyomil i µ tht is the lst epressio. The my the be writte hµ = ep µ b µ + c To simplify this further, we use the techique of completig the squre d rewrite the epressio s hµ = ep ep µ b ep µ b c We see tht posterior distributio of µ is orml with me µ = + µ σ σ + σ σ b For prcticl resos, we defie the precisio s the iverse of the vrice: we deote by ξ = d d ξ σ = σ Theorem Suppose tht µ Nµ, σ. The the posterior distributio of µ is orml with me µ = σ µ + ξ ξ + ξ d precisio ξ = ξ + ξ The posterior me is weighted verge of the prior me d the dt, weights beig proportiol to the respective precisios. With very getle prior we would hve very low precisio ξ, very t prior d mostly the posterior is Norml with s its me. Of course wht we re usully iterested i is the posterior give iid smple of size, wht you could epect hppes it is equivlet to ddig oe observtio from distributio tht hs vrice σ. 4

5 Multiomil Dirichlet priors Dirichlet prior Dirichlet prior is cojugte to multiomil distributio. This is probbility distributio o o the simple. = { p = p, p,..., p, p +... + p =, p i } The Dirichlet distributio c be writte s DΘ α = Γ K i= α i K i= Γα i K i= Θ α i i where α = α,..., α K, with α i > re costts specifyig the Dirichlet distributio Θ i stisfy Θ i d K i= Θ i = The multiomil distributio correspodig to k blls dropped ito boes with fied probbility p,..., p, with ith bo cotiig k i blls is k k,..., k p k p k For two vribles K = the Dirichlet distributio reduces to Bet distributio, d ormlizig costt becomes Bet fuctio. The Dirichlet is coveiet prior becuse the posterior p hvig observed k,..., k is Dirichlet with probbility α +k,..., α +k. A importt chrcteriztio of the Dirichlet: it is the oly prior tht predicts outcomes lierly i the pst. Oe frequetly used specil cse is the symmetric Dirichlet whe ll α i = c >. We deote this prior s D c. Dirichlet priors re importt becuse They re turl cojugte priors for multiomil distributios, i.e. posterior prmeter distributio, fter hvig observed some dt from multiomil distributio with Dirichlet prior, lso hve form of Dirichlet distributio The Dirichlet distributio c be see s multivrite geerliztio of the bet distributio, over the spce of distributios P, with costt o the verge distce reltive etropy to referece distributio determied by Θ d α. Refereces [] Rev. Thoms Byes, A essy towrds solvig problem i the doctrie of chces, Philosophicl Trsctios of the Royl Society of Lodo 763. [] Joh. A. Rice, Mthemticl sttistics d dt lysis, Dubury Press, 995. 5