Mathematics 426 Robert Gross Homework 9 Answers

Similar documents
HW4 : Bivariate Distributions (1) Solutions

Continuous Random Variables

Bivariate distributions

MULTIVARIATE PROBABILITY DISTRIBUTIONS

Perhaps the simplest way of modeling two (discrete) random variables is by means of a joint PMF, defined as follows.

2 Functions of random variables

Chapter 2. Some Basic Probability Concepts. 2.1 Experiments, Outcomes and Random Variables

Notes for Math 324, Part 19

Multivariate distributions

Chapter 3 sections. SKIP: 3.10 Markov Chains. SKIP: pages Chapter 3 - continued

Chapter 4. Chapter 4 sections

2 (Statistics) Random variables

Math 3215 Intro. Probability & Statistics Summer 14. Homework 5: Due 7/3/14

STAT/MA 416 Answers Homework 6 November 15, 2007 Solutions by Mark Daniel Ward PROBLEMS

18.440: Lecture 19 Normal random variables

MASSACHUSETTS INSTITUTE OF TECHNOLOGY 6.436J/15.085J Fall 2008 Lecture 8 10/1/2008 CONTINUOUS RANDOM VARIABLES

Chapter 3 sections. SKIP: 3.10 Markov Chains. SKIP: pages Chapter 3 - continued

Recitation 2: Probability

Homework 5 Solutions

Joint Probability Distributions and Random Samples (Devore Chapter Five)

Review: mostly probability and some statistics

Random Variables. Saravanan Vijayakumaran Department of Electrical Engineering Indian Institute of Technology Bombay

STAT 430/510 Probability Lecture 7: Random Variable and Expectation

Probability and Distributions

Stat 5101 Notes: Algorithms (thru 2nd midterm)

Random Variables. Cumulative Distribution Function (CDF) Amappingthattransformstheeventstotherealline.

STT 441 Final Exam Fall 2013

Random Variables. Random variables. A numerically valued map X of an outcome ω from a sample space Ω to the real line R

Conditional densities, mass functions, and expectations

Class 8 Review Problems solutions, 18.05, Spring 2014

3 Multiple Discrete Random Variables

Chapter 4. Continuous Random Variables 4.1 PDF

STAT/MATH 395 PROBABILITY II

SDS 321: Introduction to Probability and Statistics

Random Signals and Systems. Chapter 3. Jitendra K Tugnait. Department of Electrical & Computer Engineering. Auburn University.

ENGG2430A-Homework 2

Random Variables and Their Distributions

Stat 5101 Notes: Algorithms

MA/ST 810 Mathematical-Statistical Modeling and Analysis of Complex Systems

Review of Statistics I

Functions of two random variables. Conditional pairs

18.440: Lecture 28 Lectures Review

1 Random Variable: Topics

Homework 10 (due December 2, 2009)

ECE 302 Division 2 Exam 2 Solutions, 11/4/2009.

CMPSCI 240: Reasoning Under Uncertainty

Contents. 2 Partial Derivatives. 2.1 Limits and Continuity. Calculus III (part 2): Partial Derivatives (by Evan Dummit, 2017, v. 2.

Lecture 25: Review. Statistics 104. April 23, Colin Rundel

STA 256: Statistics and Probability I

1 Solution to Problem 2.1

MATHEMATICS 154, SPRING 2009 PROBABILITY THEORY Outline #11 (Tail-Sum Theorem, Conditional distribution and expectation)

CHAPTER 2 POLYNOMIALS KEY POINTS

ACE 562 Fall Lecture 2: Probability, Random Variables and Distributions. by Professor Scott H. Irwin

Final Exam # 3. Sta 230: Probability. December 16, 2012

MATH 151, FINAL EXAM Winter Quarter, 21 March, 2014

MAS223 Statistical Inference and Modelling Exercises

Bell-shaped curves, variance

SDS 321: Introduction to Probability and Statistics

IAM 530 ELEMENTS OF PROBABILITY AND STATISTICS LECTURE 3-RANDOM VARIABLES

(a) x cos 3x dx We apply integration by parts. Take u = x, so that dv = cos 3x dx, v = 1 sin 3x, du = dx. Thus

More on Distribution Function


MATH 307: Problem Set #3 Solutions

SUMMARY OF PROBABILITY CONCEPTS SO FAR (SUPPLEMENT FOR MA416)

M378K In-Class Assignment #1

THE ROYAL STATISTICAL SOCIETY GRADUATE DIPLOMA

f X, Y (x, y)dx (x), where f(x,y) is the joint pdf of X and Y. (x) dx

MAS113 Introduction to Probability and Statistics. Proofs of theorems

Probability Foundation for Electrical Engineers Prof. Krishna Jagannathan Department of Electrical Engineering Indian Institute of Technology, Madras

Formulas for probability theory and linear models SF2941

Problem Y is an exponential random variable with parameter λ = 0.2. Given the event A = {Y < 2},

LESSON 23: EXTREMA OF FUNCTIONS OF 2 VARIABLES OCTOBER 25, 2017

Elementary ODE Review

SDS 321: Introduction to Probability and Statistics

Practice Examination # 3

Notes 12 Autumn 2005

P (x). all other X j =x j. If X is a continuous random vector (see p.172), then the marginal distributions of X i are: f(x)dx 1 dx n

6.041/6.431 Fall 2010 Quiz 2 Solutions

CMPSCI 240: Reasoning Under Uncertainty

MAT 122 Homework 7 Solutions

ISyE 3044 Fall 2017 Test #1a Solutions

2. Suppose (X, Y ) is a pair of random variables uniformly distributed over the triangle with vertices (0, 0), (2, 0), (2, 1).

STA 4321/5325 Solution to Homework 5 March 3, 2017

Lecture 2: Review of Probability

Solution to Assignment 3

Bivariate Distributions

Prelim 1 Solutions V2 Math 1120

1 Review of Probability and Distributions

Cheng Soon Ong & Christian Walder. Canberra February June 2018

Constructing Approximations to Functions

Formulas that must be memorized:

Conditional distributions (discrete case)

Some Probability and Statistics

Integration of Rational Functions by Partial Fractions

PCMI Introduction to Random Matrix Theory Handout # REVIEW OF PROBABILITY THEORY. Chapter 1 - Events and Their Probabilities

MATH Solutions to Probability Exercises

Multivariate Distributions (Hogg Chapter Two)

18.440: Lecture 28 Lectures Review

Bivariate Distributions

MA : Introductory Probability

Transcription:

Mathematics 4 Robert Gross Homework 9 Answers. Suppose that X is a normal random variable with mean µ and standard deviation σ. Suppose that PX > 9 PX <.. Compute µ and σ as accurately as possible. Answer : Fortunately, symmetry helps out in this situation: we can determine immediately that µ. If PX > 9 PX <, then the problem would be trickier. After that, we can use Φ.8.. We conclude that µ/σ.8, or σ.48.. Suppose that X is a random variable with probability density function { e ax x < fx e bx x > where a and b are positive constants. a Show that a + b. b Compute Fx, the cumulative distribution function for X. c Compute E[X]. d Compute VarX. Answer : a Because fx dx, we see that b If y <, then If y >, then Fy c We have E[X] e ax dx + e ax dx + Fy y xfx dx ] ] e bx dx a e ax b e bx y e ax dx a e ax] y e ay /a. e bx dx a + b e bx ] y xe ax dx + xe bx dx a b. a + b b e by. d We have E[X ] ] ] a xe ax a e ax b xe bx b e bx b a b a b + a b a. x fx dx x e ax dx + x e bx dx a + b

] ] a x e ax a xe ax + a e ax b x e bx b xe bx b e bx a + b b + a b + a b ab + a b ab + a VarX E[X ] E[X] b ab + a b + ab a b + a.. The joint probability density function of the continuous random variables X and Y is given by x + xy < x <, < y < fx, y otherwise. a Verify that this is indeed a probability density function. b Compute the density function for X. c Compute P{X > Y}. d Compute P{Y > X < }. e Compute E[X]. f Compute E[Y]. Answer : a We have x + xy dy dx ] x y + xy dx x + x dx 4 ] x + x +. b If x < or x >, then f X x. For < x <, we have f X x fx, y dy x + xy dy ] x y + xy 4 x + x. c You need to be a bit careful about specifying the bounds of integration; drawing a graph is helpful. The region is < y < x <. We have x PX > Y x + xy dy dx ] x x y + xy dx 4 x + x dx 5 ] 4 4 x4 5 4 5. d We know that P{Y > X < } PY >, X < /PX <. Because we computed f X x, the denominator is straightforward: PX < f X x dx x + x dx x + x ] + 5 8 8.

The numerator comes from the denition: PY >, X < x + xy x + 5x Therefore, P{Y > X < } 9/448 9.85. 5/8 8 e We have f We have x x + xy E[X] dy dx ] x y + x y dx 4 ] x 4 + x 5. E[Y] y x + xy dy dx ] x y + xy dx ] x + x 8. dy dx dx x ] x y + xy dx 4 + 5x ] 9 448. x + x y dy dx x + x dx x y + xy dy dx x + 4x dx 4. Let fx, y /x if < y < x < and otherwise. Let fx, y be the joint density function for random variables X and Y. a Show that fx, y is a joint density function. b Compute the marginal density of X. c Compute the marginal density of Y. d Compute E[X]. e Compute E[Y]. Answer : a We have b We have fx, y dy dx f X x for < x <, and f X x otherwise. x x x dy dx /x dy dx.

c We have f Y y y ] /x dx log x log y y for < y <, and f Y y otherwise. Note that log y is positive for y between and. d We have e We have E[Y] E[X] yf Y y dy xf X x dx y log y dy x dx. y 4 y log y 5. Suppose that the joint density function for X and Y is given by { xe xy+ x >, y > fx, y otherwise. ] 4. a Verify that this is indeed a probability density function. b Find the conditional density function for X, given that Y y, and the conditional density function for Y, given that X x. c Find the density function for Z XY. Answer : a We have fx, y dy dx xe xy+ dy dx ] y e x e xy dx y xe x e xy dy dx e x dx. b The formul are f X Y x y fx, y/f Y y and f Y X y x fx, y/f X x, so really all we are being asked to compute here are the marginal density functions f X x and f Y y. We have f X x f Y X y x xe xy+ f Y y xe xy+ dy e x xe x e xy e x ] y xe x e xy dy e x e xy e x xe xy xe xy+ dx xe xy+ y + f X Y x y xe xy+ /y + y + xe xy+ ] x e xy+ y + x y y + c The usual approach works. First, compute the cumulative distribution function F Z a. Then dierentiate to get the probability density function f Z z. Because X and Y

are both positive, we know that F Z a if a < and f Z z if z <. For a >, we have F Z a PZ < a PXY < a PY < a/x a/x Therefore, f Z z F Z z e z. xe x e xy dy dx e x e a + e x dx e a. In class, we proved that if gx, y, then E[gX, Y] ] ya/x e x e xy dx y gx, yfx, y dx dy e x dx e a. Follow the argument in a previous homework to show that this formula is still correct for an arbitrary function gx, y. Answer : We have E[gX, Y] gx,y>t PgX, Y > t dt PgX, Y < t dt fx, y dx dy dt fx, y dx dy dt gx,y< t Set t u, u t, du dt in the second integral: fx, y dx dy dt x,y:gx,y>t Interchange the order of integration: gx,y dt fx, y dx dy x,y:gx,y> x,y:gx,y< x,y:gx,y> x,y:gx,y> gx,y du fx, y dx dy gx, yfx, y dx dy gx, yfx, y dx dy + x,y:gx,y<u x,y:gx,y< x,y:gx,y< fx, y dx dy du gx, yfx, y dx dy gx, yfx, y dx dy Adding in the x, y-region where gx, y contributes nothing to the sum: gx, yfx, y dx dy + x,y:gx,y> x,y:gx,y gx, yfx, y dx dy + x,y:gx,y< gx, yfx, y dx dy

gx, yfx, y dx dy x,y. Consider the experiment of rolling cubical dice, and recording the larger of the two numbers as a random variable X. What is the probability distribution for this random variable? What is E[X]? Answer : This can be done by counting all elements in the sample space. We get and E[X] 4.4. k PX k 5 4 5 9