Mathematical Statistics

Similar documents
Summary: Binomial Expansion...! r. where

PROGRESSION AND SERIES

SOLUTIONS ( ) ( )! ( ) ( ) ( ) ( )! ( ) ( ) ( ) ( ) n r. r ( Pascal s equation ). n 1. Stepanov Dalpiaz

For this purpose, we need the following result:

«A first lesson on Mathematical Induction»

Graphing Review Part 3: Polynomials

Approximations of Definite Integrals

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

Lecture 18: Sampling distributions

BINOMIAL THEOREM OBJECTIVE PROBLEMS in the expansion of ( 3 +kx ) are equal. Then k =

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

42. (20 pts) Use Fermat s Principle to prove the law of reflection. 0 x c

Linford 1. Kyle Linford. Math 211. Honors Project. Theorems to Analyze: Theorem 2.4 The Limit of a Function Involving a Radical (A4)

Lecture 24: Observability and Constructibility

POWER SERIES R. E. SHOWALTER

We show that every analytic function can be expanded into a power series, called the Taylor series of the function.

Lecture 7: Properties of Random Samples

MATH 104 FINAL SOLUTIONS. 1. (2 points each) Mark each of the following as True or False. No justification is required. y n = x 1 + x x n n

FACULTY OF MATHEMATICAL STUDIES MATHEMATICS FOR PART I ENGINEERING. Lectures

Applied Mathematical Sciences, Vol. 2, 2008, no. 9, Parameter Estimation of Burr Type X Distribution for Grouped Data

Chapter 25 Sturm-Liouville problem (II)

PROGRESSIONS AND SERIES

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:

UNIT V: Z-TRANSFORMS AND DIFFERENCE EQUATIONS. Dr. V. Valliammal Department of Applied Mathematics Sri Venkateswara College of Engineering

On Certain Classes of Analytic and Univalent Functions Based on Al-Oboudi Operator

ME 501A Seminar in Engineering Analysis Page 1

lecture 16: Introduction to Least Squares Approximation

Eigenfunction Expansion. For a given function on the internal a x b the eigenfunction expansion of f(x):

Definite Integral. The Left and Right Sums

ENGINEERING PROBABILITY AND STATISTICS

SOME REMARKS ON HORIZONTAL, SLANT, PARABOLIC AND POLYNOMIAL ASYMPTOTE

BINOMIAL THEOREM SOLUTION. 1. (D) n. = (C 0 + C 1 x +C 2 x C n x n ) (1+ x+ x 2 +.)

LEVEL I. ,... if it is known that a 1

Numbers (Part I) -- Solutions

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

B. Examples 1. Finite Sums finite sums are an example of Riemann Sums in which each subinterval has the same length and the same x i

9.4 The response of equilibrium to temperature (continued)

MATH Midterm Solutions

Math 7409 Homework 2 Fall from which we can calculate the cycle index of the action of S 5 on pairs of vertices as

Induction. Induction and Recursion. Induction is a very useful proof technique

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

[ 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.

ANSWER KEY PHYSICS. Workdone X

8.1 Arc Length. What is the length of a curve? How can we approximate it? We could do it following the pattern we ve used before

1.3 Continuous Functions and Riemann Sums

Chapter Linear Regression

Review of Sections

Parametric Methods. Autoregressive (AR) Moving Average (MA) Autoregressive - Moving Average (ARMA) LO-2.5, P-13.3 to 13.4 (skip

Limit of a function:

Fast Fourier Transform 1) Legendre s Interpolation 2) Vandermonde Matrix 3) Roots of Unity 4) Polynomial Evaluation

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

(a) Counter-Clockwise (b) Clockwise ()N (c) No rotation (d) Not enough information

Previously. Extensions to backstepping controller designs. Tracking using backstepping Suppose we consider the general system

MATH 118 HW 7 KELLY DOUGAN, ANDREW KOMAR, MARIA SIMBIRSKY, BRANDEN LASKE

( a n ) converges or diverges.

SUTCLIFFE S NOTES: CALCULUS 2 SWOKOWSKI S CHAPTER 11

Name: Period: Date: 2.1 Rules of Exponents

M3P14 EXAMPLE SHEET 1 SOLUTIONS

MA123, Chapter 9: Computing some integrals (pp )

Chapter 7 Infinite Series

Introduction to mathematical Statistics

Optimization. x = 22 corresponds to local maximum by second derivative test

DRAFT. Formulae and Statistical Tables for A-level Mathematics SPECIMEN MATERIAL. First Issued September 2017

Introduction to Matrix Algebra

The Reimann Integral is a formal limit definition of a definite integral

2.Decision Theory of Dependence

Notes 17 Sturm-Liouville Theory

7.5-Determinants in Two Variables

SULIT 3472/2. Rumus-rumus berikut boleh membantu anda menjawab soalan. Simbol-simbol yang diberi adalah yang biasa digunakan.

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

Homework 2 solutions

Chapter 7. Kleene s Theorem. 7.1 Kleene s Theorem. The following theorem is the most important and fundamental result in the theory of FA s:

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

f(t)dt 2δ f(x) f(t)dt 0 and b f(t)dt = 0 gives F (b) = 0. Since F is increasing, this means that

Class Summary. be functions and f( D) , we define the composition of f with g, denoted g f by

10 Statistical Distributions Solutions

Physics 235 Final Examination December 4, 2006 Solutions

n 2 + 3n + 1 4n = n2 + 3n + 1 n n 2 = n + 1

5. Solving recurrences

USE OF STATISTICAL TECHNIQUES FOR CRITICAL GAPS ESTIMATION

Crosscorrelation of m-sequences, Exponential sums and Dickson

Interpolation. 1. What is interpolation?

18.01 Calculus Jason Starr Fall 2005

BINOMIAL THEOREM An expression consisting of two terms, connected by + or sign is called a

Chapter 2 Infinite Series Page 1 of 9

CHAPTER 5 : SERIES. 5.2 The Sum of a Series Sum of Power of n Positive Integers Sum of Series of Partial Fraction Difference Method

CH 39 USING THE GCF TO REDUCE FRACTIONS

The Weierstrass Approximation Theorem

BINOMIAL THEOREM NCERT An expression consisting of two terms, connected by + or sign is called a

Lecture 3 : Concentration and Correlation

MTH 146 Class 16 Notes

Convergence rates of approximate sums of Riemann integrals

Different kinds of Mathematical Induction

Review. I will give you these formulas: Sphere: V=frr Circle: A = rr2 Cone: V = I 2rr2h Cube: V = side3

General properties of definite integrals

Prior distributions. July 29, 2002

Simpson s 1/3 rd Rule of Integration

Statistical Signal Processing

1 Using Integration to Find Arc Lengths and Surface Areas

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),

Transcription:

7 75 Ode Sttistics The ode sttistics e the items o the dom smple ed o odeed i mitude om the smllest to the lest Recetl the impotce o ode sttistics hs icesed owi to the moe equet use o opmetic ieeces d obust pocedues Howeve ode sttistics hve lws bee pomiet becuse mo othe this the e eeded to detemie the simple sttistics such s the smple medi the smple e d the empiicl distibutio uctio I most o ou discussio we will ssume tht the dom smple ises om cotiuous-tpe distibutio This mes mo othe thi tht the pobbilit o two smple items bei equl is zeo Tht is the pobbilit is oe tht the items c be odeed om smllest to lest without hvi two equl vlues O couse i pctice we do equetl obseve ties; but i the pobbilit o this is smll the ollowi distibutio theo will hold ppoximtel Thus i the discussio hee we e ssumi tht the pobbilit o tie is zeo I X X L X e obsevtios o dom smple o size om cotiuous-tpe distibutio with distibutio uctio x d pd x we let the dom vibles L deote the ode sttistics o tht smple Tht is smllest o X X L X secod smllest o M lest o X X X X L X L X The pobbilit desit uctios o d c be oud usi the method o distibutio uctios Becuse is the lest o X X L X the evet will occu i d ol i the evet X occu o eve i Tht is i X X X L To detemie the distibutio o the th ode sttistic depeds o the biomil distibutio Suppose tht x o x b d b It is possible tht d/o b The evet tht the th ode sttistic c occu i d ol i t lest o the obsevtios e less th o equl to Tht is hee the pobbilit o success o ech til is x d we must hve t lest successes Thus [ ] [ ] Thus the pd o is

7 Hece we hve tht the pd o is b It is woth oti tht the pd o the smllest ode sttistic is b d the pd o the lest ode sttistic is b REMARK: Thee is oe ve stiscto w bsed o the multiomil pobbilit to costuct heuisticll the expessio o the pd o Accodi to the deiitio o deivtive we hve - - - Aothe iteesti heuistic umet c be ive bsed o the otio tht the lielihood o obsevtio is ssied b the pd To hve oe must hve obsevtios less th oe t d obsevtios ete th whee d the lielihood o obsevtio t is Thee e

7 [ ] possible odeis o the idepedet obsevtios d is ive b the bove multiomil expessio This is illustted i iue 7 64 44 7444 8 } 6 44 748 4 L L iue 7 The th ode obsevtio A simil umet c be used to esil ive the joit pd o set o ode sttistics o exmple coside pi o ode sttistics i d j whee i j To hve i i d j j oe must hve i obsevtios less th i oe t j oe t o i d j d j s i j i betwee i d j ete th j Appli the multiomil om ives the joit pd i ji j ij i j [ i ] i [ j i ] [ j ] j i j i j i i j b d zeo othewise This is illustted b iue 7 uthemoe the joit pd o L is ive b i L L L b d zeo othewise i 64748 4 ji } 644 7448 } L L i i i j j j j 644 748 4 L iue 7 The ith d jth ode obsevtios Exmple 75-: Coside dom smple o size om distibutio with pd d CD ive b x x d x x ; x The smllest d lest ode sttistics e d E d Let u d du u u u Deie the e o the smple s R The joit pd o d is du

74 Mi the tsomtio R S ields the ivese tsomtio s s d J Thus the joit pd o R d S is h s 4s s s s The mil desit o the e the is ive b h h s ds o exmple o the cse we hve h 8s s ds 4 Exmple 75-: Let L 7 be the ode sttistics o dom smple o size 7 om distibutio with pd x x x Compute the pobbilit tht the smple medi is less th 6 We could id the pd o ; tht is id 4 6 4 Howeve ote tht the pobbilit o sile obsevtio bei less th 6 is Thus 6 [ x ] 6 4 6 x dx 7 7 7 6 4 6 7 898 4 4 Exmple 75-: I X hs distibutio uctio x o the cotiuous tpe the x hs uiom distibutio o the itevl zeo to oe I L e the ode sttistics o dom smple X X L X o size the L sice is odecesi uctio d the pobbilit o equlit is i zeo Note tht the lst displ could be looed o s odei o the mutull idepedet dom vibles L U Tht is ech o which is W W L W c be thouht o s the ode sttistics o dom smple o size om tht uiom distibutio Sice the distibutio uctio o sttistic W is U is w w w the pd o the th ode h w w w w The me E W E[ ] o E W W is ive b the itel w w w dw w w w dw

75 L is the cumulted pobbilit up to d icludi o equivletl the e ude x x but less th Hece c be teted s dom e Sice is lso dom e is the dom e ude x betwee d The expected vlue o the dom e betwee two djcet ode sttistics is the E[ ] Also it is es to show tht E [ ] d E[ ] Tht is the ode sttistics L ptitio the suppot o X ito pts d thus cete e ude x d bove the x-xis O the vee ech o the es Thee is extemel iteesti itepettio o W Note tht equl I we ecll tht the pth pecetile π is such tht the e ude x to the let o p π p is p the pecedi discussio suests tht we let be estimto o π p whee p o this eso we deie the pth pecetile o the smple s whee p I cse p is ot itee; we use weihted vee o vee o the two djcet ode sttistics d whee is the etest itee i p I pticul the smple medi is whe is odd M whe is eve