CHAPTER 5. p(x,y) x

Σχετικά έγγραφα
Pairs of Random Variables

Homework #6. A circular cylinder of radius R rotates about the long axis with angular velocity

Statistics 104: Quantitative Methods for Economics Formula and Theorem Review

Math 6 SL Probability Distributions Practice Test Mark Scheme

α A G C T 國立交通大學生物資訊及系統生物研究所林勇欣老師

SOLUTIONS TO MATH38181 EXTREME VALUES AND FINANCIAL RISK EXAM

Solution Series 9. i=1 x i and i=1 x i.

SOLUTIONS TO MATH38181 EXTREME VALUES AND FINANCIAL RISK EXAM

Matrices and Determinants

16 Electromagnetic induction

Section 8.3 Trigonometric Equations

CHAPTER 25 SOLVING EQUATIONS BY ITERATIVE METHODS

ΚΥΠΡΙΑΚΗ ΕΤΑΙΡΕΙΑ ΠΛΗΡΟΦΟΡΙΚΗΣ CYPRUS COMPUTER SOCIETY ΠΑΓΚΥΠΡΙΟΣ ΜΑΘΗΤΙΚΟΣ ΔΙΑΓΩΝΙΣΜΟΣ ΠΛΗΡΟΦΟΡΙΚΗΣ 19/5/2007

HOMEWORK#1. t E(x) = 1 λ = (b) Find the median lifetime of a randomly selected light bulb. Answer:

Aquinas College. Edexcel Mathematical formulae and statistics tables DO NOT WRITE ON THIS BOOKLET

ST5224: Advanced Statistical Theory II

19. ATOMS, MOLECULES AND NUCLEI HOMEWORK SOLUTIONS

2 Composition. Invertible Mappings

Calculus and Differential Equations page 1 of 17 CALCULUS and DIFFERENTIAL EQUATIONS

Areas and Lengths in Polar Coordinates

Other Test Constructions: Likelihood Ratio & Bayes Tests

Statistical Inference I Locally most powerful tests

Exercises 10. Find a fundamental matrix of the given system of equations. Also find the fundamental matrix Φ(t) satisfying Φ(0) = I. 1.

Chapter 6: Systems of Linear Differential. be continuous functions on the interval

Fourier Series. MATH 211, Calculus II. J. Robert Buchanan. Spring Department of Mathematics

3.4 SUM AND DIFFERENCE FORMULAS. NOTE: cos(α+β) cos α + cos β cos(α-β) cos α -cos β

b. Use the parametrization from (a) to compute the area of S a as S a ds. Be sure to substitute for ds!

SCHOOL OF MATHEMATICAL SCIENCES G11LMA Linear Mathematics Examination Solutions

k A = [k, k]( )[a 1, a 2 ] = [ka 1,ka 2 ] 4For the division of two intervals of confidence in R +

Homework 8 Model Solution Section

ANSWERSHEET (TOPIC = DIFFERENTIAL CALCULUS) COLLECTION #2. h 0 h h 0 h h 0 ( ) g k = g 0 + g 1 + g g 2009 =?

4.6 Autoregressive Moving Average Model ARMA(1,1)

EE512: Error Control Coding

Areas and Lengths in Polar Coordinates

Finite Field Problems: Solutions

PULLEYS 1. GROOVE SPECIFICATIONS FOR V-BELT PULLEYS. Groove dimensions and tolerances for Hi-Power PowerBand according to RMA engineering standards

1. A fully continuous 20-payment years, 30-year term life insurance of 2000 is issued to (35). You are given n A 1

General theorems of Optical Imaging systems

derivation of the Laplacian from rectangular to spherical coordinates

The challenges of non-stable predicates

Similarly, we may define hyperbolic functions cosh α and sinh α from the unit hyperbola

ΚΥΠΡΙΑΚΗ ΕΤΑΙΡΕΙΑ ΠΛΗΡΟΦΟΡΙΚΗΣ CYPRUS COMPUTER SOCIETY ΠΑΓΚΥΠΡΙΟΣ ΜΑΘΗΤΙΚΟΣ ΔΙΑΓΩΝΙΣΜΟΣ ΠΛΗΡΟΦΟΡΙΚΗΣ 6/5/2006

NONLINEAR FINITE ELEMENT ANALYSIS OF PLATE BENDING

Inverse trigonometric functions & General Solution of Trigonometric Equations

2. THEORY OF EQUATIONS. PREVIOUS EAMCET Bits.

5.4 The Poisson Distribution.

CHAPTER 101 FOURIER SERIES FOR PERIODIC FUNCTIONS OF PERIOD

Jesse Maassen and Mark Lundstrom Purdue University November 25, 2013

Relativsitic Quantum Mechanics. 3.1 Dirac Equation Summary and notation 3.1. DIRAC EQUATION SUMMARY AND NOTATION. April 22, 2015 Lecture XXXIII

DERIVATION OF MILES EQUATION FOR AN APPLIED FORCE Revision C

Second Order RLC Filters

APPENDICES APPENDIX A. STATISTICAL TABLES AND CHARTS 651 APPENDIX B. BIBLIOGRAPHY 677 APPENDIX C. ANSWERS TO SELECTED EXERCISES 679

FORMULAS FOR STATISTICS 1

DESIGN OF MACHINERY SOLUTION MANUAL h in h 4 0.

Probability and Random Processes (Part II)

Potential Dividers. 46 minutes. 46 marks. Page 1 of 11

ΕΙΣΑΓΩΓΗ ΣΤΗ ΣΤΑΤΙΣΤΙΚΗ ΑΝΑΛΥΣΗ

Solutions to Exercise Sheet 5

Homework for 1/27 Due 2/5

Lecture 34 Bootstrap confidence intervals

1 String with massive end-points

C.S. 430 Assignment 6, Sample Solutions

Example Sheet 3 Solutions

Homework 3 Solutions

Modbus basic setup notes for IO-Link AL1xxx Master Block

Differential equations

ΠΟΣΟΤΙΚΕΣ ΜΕΘΟΔΟΙ ΔΕΟ 13 ΤΟΜΟΣ Δ ΣΤΑΤΙΣΤΙΚΗ ΓΙΑ ΤΗ ΔΙΟΙΚΗΣΗ ΕΠΙΧΕΙΡΗΣΕΩΝ

Chapter 4 : Linear Wire Antenna

( y) Partial Differential Equations

An Inventory of Continuous Distributions

Solutions to the Schrodinger equation atomic orbitals. Ψ 1 s Ψ 2 s Ψ 2 px Ψ 2 py Ψ 2 pz

Durbin-Levinson recursive method

Φυγόκεντρος αποθήκευσης Κανονική n 1k Αγωγή n 2k

7 Present PERFECT Simple. 8 Present PERFECT Continuous. 9 Past PERFECT Simple. 10 Past PERFECT Continuous. 11 Future PERFECT Simple

ΠΑΝΕΠΙΣΤΗΜΙΟ ΠΕΙΡΑΙΑ ΤΜΗΜΑ ΝΑΥΤΙΛΙΑΚΩΝ ΣΠΟΥΔΩΝ ΠΡΟΓΡΑΜΜΑ ΜΕΤΑΠΤΥΧΙΑΚΩΝ ΣΠΟΥΔΩΝ ΣΤΗΝ ΝΑΥΤΙΛΙΑ

Second Order Partial Differential Equations

Instruction Execution Times

Risk! " #$%&'() *!'+,'''## -. / # $

Problem Set 3: Solutions

Bit Error Rate in Digital Photoreceivers

ΕΦΑΡΜΟΣΜΕΝΗ ΣΤΑΤΙΣΤΙΚΗ I Παντελής Δημήτριος Τμήμα Μηχανολόγων Μηχανικών

Math221: HW# 1 solutions

Integrals in cylindrical, spherical coordinates (Sect. 15.7)

HOMEWORK 4 = G. In order to plot the stress versus the stretch we define a normalized stretch:

ΠΑΝΔΠΗΣΖΜΗΟ ΠΑΣΡΩΝ ΣΜΖΜΑ ΖΛΔΚΣΡΟΛΟΓΩΝ ΜΖΥΑΝΗΚΩΝ ΚΑΗ ΣΔΥΝΟΛΟΓΗΑ ΤΠΟΛΟΓΗΣΩΝ ΣΟΜΔΑ ΤΣΖΜΑΣΩΝ ΖΛΔΚΣΡΗΚΖ ΔΝΔΡΓΔΗΑ

Section 9.2 Polar Equations and Graphs

Bayesian statistics. DS GA 1002 Probability and Statistics for Data Science.

= λ 1 1 e. = λ 1 =12. has the properties e 1. e 3,V(Y

ΕΝΙΣΧΥΣΗ ΠΛΑΚΩΝ ΚΑΙ ΔΟΚΩΝ ΣΕ ΚΑΜΨΗ ΜΕ ΜΑΝΔΥΕΣ Η ΕΛΑΣΜΑΤΑ ΣΥΝΘΕΤΩΝ ΥΛΙΚΩΝ.

Answers - Worksheet A ALGEBRA PMT. 1 a = 7 b = 11 c = 1 3. e = 0.1 f = 0.3 g = 2 h = 10 i = 3 j = d = k = 3 1. = 1 or 0.5 l =

Web-based supplementary materials for Bayesian Quantile Regression for Ordinal Longitudinal Data

Srednicki Chapter 55

Section 7.6 Double and Half Angle Formulas

Strain gauge and rosettes

Additional Results for the Pareto/NBD Model

ss rt çã r s t Pr r Pós r çã ê t çã st t t ê s 1 t s r s r s r s r q s t r r t çã r str ê t çã r t r r r t r s

Module 5. February 14, h 0min

Notes on the Open Economy

Biostatistics for Health Sciences Review Sheet

Practice Exam 2. Conceptual Questions. 1. State a Basic identity and then verify it. (a) Identity: Solution: One identity is csc(θ) = 1

Transcript:

CHAPTER 5 Sction 5.. a. P(X, Y p(,. b. P(X and Y p(, + p(, + p(, + p(,.4 c. At last on hos is in us at both islands. P(X and Y p(, + p(, + p(, + p(,.7 d. B summing row probabilitis, p (.6,.4,.5 for,,, and b summing column probabilitis, p (.4,.8,.8 for,,. P(X p ( + p (.5. P(,., but p ( p ( (.6(.4.84., so X and Y ar not indpndnt.. a. p(, 4..5.5.5..5.8..5.5.6......4..6..5.5. b. P(X and Y p(, + p(, + p(, + p(,.56 (.8(.7 P(X P(Y c. P( X + Y P(X and Y p(,. d. P(X + Y p(, + p(, + p(,.5. a. p(,.5, th ntr in th st row and st column of th joint probabilit tabl. b. P( X X p(, + p(, + p(, + p(,.8+.5+.+.7.4 c. A { (, : + } { (, : + } P(A p(, + p(, + p(4, + p(, + p(4, + p(4, + p(, + p(, + p(,. d. P( actl 4 p(, + p(, + p(, + p(4,.7 P(at last 4 P(actl 4 + p(4, + p(4, + p(4, + p(, + p(, + p(,.46 75

Chaptr 5: Joint Probabilit Distributions and Random Sampls 4. a. P ( P(X p(, + p(, + p(, + p(,.9 P ( P(X p(, + p(, + p(, + p(,., tc. 4 p (.9..5.4. b. P ( P(X p(, + p(, + p(, + p(, + p(4,.9, tc p (.9..8. c. p(4,, t p (4. > and p (.9 >, so p(, p ( p ( for vr (,, and th two variabls ar not indpndnt. 5. a. P(X, Y P( customrs, ach with packag P( ach has packag customrs P( customrs (.6 (.5.54 b. P(X 4, Y P(total of packags 4 customrs P(4 customrs Givn that thr ar 4 customrs, thr ar 4 diffrnt was to hav a total of packags:,,, or,,, or,,, or,,,. Each wa has probabilit (. (., so p(4, 4(. (.(.5.8 6. 4 a. p(4, P( Y X 4 P(X 4 (.6 (.4 (.5. 58 b. P(X Y p(, + p(, + p(, + p(, + p(4,4.+(.(.6 + (.(.6 + (.5(.6 + (.5(.6 4.44 76

Chaptr 5: Joint Probabilit Distributions and Random Sampls c. p(, unlss,,, ;,,,, 4. For an such pair, p(, P(Y X P(X (. 6 (.4 p ( p (4 p( 4 p( 4, 4 p(4,4 (.6 4 (.5.94 4 p ( p(, + p(4, (.6 (.5 + (.6 (.4(.5. 58 p ( p(, + p(, + p(4, (.6 (. + (.6 (.4(.5 4 + (.6 (.4 (.5.678 p ( p(, + p(, + p(, + p(4, (. 6(. + (.6(.4(. 4 (.6(.4 (.5 + (.6(.4 (.5.59 p ( [.59+.678+.58+.94].48 7. a. p(,. b. P(X and Y p(, + p(, + p(, + p(,. c. P(X p(, + p(, + p(,.; P(Y p(, + + p(5,. d. P(ovrflow P(X + Y > 5 P(X + Y 5 P[(X,Y(, or or (5, or (, or (, or (,] -.6.8. Th marginal probabilitis for X (row sums from th joint probabilit tabl ar p (.5, p (., p (.5, p (., p (4., p (5.; thos for Y (column sums ar p (.5, p (., p (.. It is now asil vrifid that for vr (,, p(, p ( p (, so X and Y ar indpndnt. 77

Chaptr 5: Joint Probabilit Distributions and Random Sampls 8. 8 59, 6 a. numrator ( 56( 45(, 4,4 59,775 dnominator 775 ; p(,. 59 b. p(, 8 6 6 ( +, _ ar _ non ngativ int grs _ such _ that + 6 othrwis 9. dd a. f (, dd K( + K K d dd + K dd K d + 9, K K 8, 6 6 ( d b. P(X < 6 and Y < 6 K + dd K c. 6 4K 6 8,4K.4 I + III II P( X Y rgion III f (, dd (, dd f f (, dd I 8 + II f (, dd (aftr much algbra.59 f (, dd 78

Chaptr 5: Joint Probabilit Distributions and Random Sampls d. f ( f (, d K ( + d K + K +.5, K. f ( is obtaind b substituting for in (d; clarl f(, f ( f (, so X and Y ar not indpndnt.. a. f(, 5 6,5 6 othrwis sinc f (, f ( for 5 6, 5 6 b. P(5.5 X 5.75, 5.5 Y 5.75 P(5.5 X 5.75 P(5.5 Y 5.75 (b indpndnc (.5(.5.5 c. 6 I +/6 / 6 5 II P((X,Y A A dd ara of A (ara of I + ara of II 5. 6 6 6 5 6. a. p(, µ µ!! for,,, ;,,, µ b. p(, + p(, + p(, [ + + µ ] c. P( X+Ym P( X k, Y m k m! ( + µ m m k m k µ k k k! ( m k m ( + µ m m k mk ( + µ k! µ k m! +. Poisson distribution with paramtr µ µ, so th total # of rrors X+Y also has a 79

Chaptr 5: Joint Probabilit Distributions and Random Sampls. (+ a. P(X> dd d. 5 b. Th marginal pdf of X is ( + d ( + (+ d th marginal pdf s, so th two r.v s ar not indpndnt. c. P( at last on cds P(X and Y d (+ dd for ; that of Y is for. It is now clar that f(, is not th product of ( d +.5.5.. a. f(, f ( f (, othrwis b. P(X and Y P(X P(Y ( - ( -.4 ( c. P(X + Y dd [ ] d ( d. 594 ( d. P(X + Y [ ] d. 64 so P( X + Y P(X + Y P(X + Y.594 -.64., 4. a. P(X < t, X < t,, X < t P(X < t P( X < t ( t b. If succss {fail bfor t}, thn p P(succss t, and P(k succsss among trials ( k k t t k c. P(actl 5 fail P( 5 of l s fail and othr 5 don t + P(4 of l s fail, m fails, and othr 5 9 5 9 4 t 5 ( + 4 t t 4 µ t t µ t 5 don t ( ( ( ( ( 8

Chaptr 5: Joint Probabilit Distributions and Random Sampls 8 5. a. F( P( Y P [(X ((X (X ] P (X + P[(X (X ] - P[(X (X (X ] ( ( ( + for b. f( F ( ( ( + ( ( 4 for E(Y ( 4 d 6. a. f(, (,, ( d k d f ( ( 7,, + b. P(X + X.5.5.5 ( ( 7 d d (aftr much algbra.55 c. ( ( 7, ( ( d d f f 5 6 6 48 8 + 7. a. (, ( Y X P within a circl of radius A R dd f A P, ( (.5 4.. R A of ara dd πr A π b. π π, R R R Y R R X R P

Chaptr 5: Joint Probabilit Distributions and Random Sampls c. P R X R, R Y R R πr π f f (, d πr d d. ( R R R πr for R R and similarl for f Y (. X and Y ar not indpndnt sinc.g. f (.9R f Y (.9R >, t f(.9r,.9r sinc (.9R,.9R is outsid th circl of radius R. 8. a. P X ( rsults from dividing ach ntr in row of th joint probabilit tabl b p (.4: P P P.8 (.4. (.4.6 (.4.5.588.765 b. P X ( is rqustd; to obtain this divid ach ntr in th row b p (.5: P X (..8.6 c. P( Y P X ( + P X (. +.8.4 d. P X Y ( rsults from dividing ach ntr in th column b p (.8: P (.56.579.7895 8

Chaptr 5: Joint Probabilit Distributions and Random Sampls 9. a. f f (, k( + ( f ( k +.5 Y X X k( + X ( k k +.5 8, f Y b. P( Y 5 X f Y 5 fy X 5 ( d k(( + d.78 5 k( +.5 P( Y 5 ( d (k +.5 d. 75 5 k(( + k( +.5 Y X ( c. E( Y X f d d 5.79 E( Y k(( + X d 65. 864 k( +.5 V(Y X E( Y X [E( Y X ] 8.4976. f (,,, f (, whr f, (, a. f (,, th marginal joint pdf f ( d,, of (X, X b. f (, f (,,, whr f ( f f (,, d ( d. For vr and, f Y X ( f (, sinc thn f(, f Y X ( f X ( f Y ( f X (, as rquird. 8

Chaptr 5: Joint Probabilit Distributions and Random Sampls Sction 5.. a. E( X + Y ( + p(, ( + (. + ( + 5(.6 +... + ( + 5(. 4. b. E[ma (X,Y] ma( + p(, ( (. + (5(.6 +... + (5(. 9.6. E(X X ( 4 p(, ( (.8 + ( (.7 + + (4 (.6.5 (which also quals E(X E(X.7.55 4. Lt h(x,y # of individuals who handl th mssag. h(, 4 5 6-4 - 4-4 4 4-5 4-6 4 - Sinc p(, for ach possibl (,, E[h(X,Y] 84 h,. 8 ( 5. E(XY E(X E(Y L L L 6. Rvnu X + Y, so E (rvnu E (X + Y 5 ( + p(, p(, +... + 5 p(5, 5.4 84

Chaptr 5: Joint Probabilit Distributions and Random Sampls 7. E[h(X,Y] 6 dd ( 6 dd ( dd 5 6 d 8. E(XY p(, p( p ( p( p ( E(X E(Y. (rplac Σ with in th continuous cas µ µ. E(X 75 5 f ( d 4 ( d, so Var (X 6 5 5 5 5 75 5 Similarl, Var(Y, so ρ X, Y. 667 5 75 9. Cov(X,Y and 5 5. a. E(X 5.55, E(Y 8.55, E(XY ((. + ((.6 + + (5(. 44.5, so Cov(X,Y 44.5 (5.55(8.55 -.. X Y, so ρ X, Y. 7 (.45(9.5 b..45, 9. 5. a. E(X f ( d [ K +.5] d 5.9 E( Y E(XY K( + dd 64. 447 Cov ( X, Y 64.447 (5.9., so Var (X Var(Y 649.846 (5.9 8.664 b. E(X [ K +.5] d 649.846 E( Y ρ..4 (8.664(8.664 85

Chaptr 5: Joint Probabilit Distributions and Random Sampls. Thr is a difficult hr. Eistnc of r rquirs that both X and Y hav finit mans and variancs. Yt sinc th marginal pdf of Y is ( ( + for, E( d d ( + d ( d ( + + ( + first intgral is not finit. Thus r itslf is undfind., and th. Sinc E(XY E(X E(Y, Cov(X,Y E(XY E(X E(Y E(X E(Y - E(X E(Y, and sinc Corr(X,Y Cov( X, Y, thn Corr(X,Y 4. a. In th discrt cas, Var[h(X,Y] E{[h(X,Y E(h(X,Y] } [ h(, E( h( X, Y ] p(, with rplacing in th continuous cas. [ h(, p(, ] [ E( h( X, Y ] b. E[h(X,Y] E[ma(X,Y] 9.6, and E[h (X,Y] E[(ma(X,Y ] ( (. +(5 (.6 + + (5 (. 5.5, so Var[ma(X,Y] 5.5 (9.6.4 5. a. Cov(aX + b, cy + d E[(aX + b(cy + d] E(aX + b E(cY + d E[acXY + adx + bcy + bd] (ae(x + b(ce(y + d ace(xy ace(xe(y accov(x,y b. Corr(aX + b, cy + d Cov( ax + b, cy + d accov( X, Y Var( ax + b Var( cy + d a c Var( X Var( Y Corr(X,Y whn a and c hav th sam signs. c. Whn a and c diffr in sign, Corr(aX + b, cy + d -Corr(X,Y. 6. Cov(X,Y Cov(X, ax+b E[X (ax+b] E(X E(aX+b a Var(X, so Corr(X,Y avar( X Var( X Var( Y avar( X Var( X a Var( X if a >, and if a < 86

Chaptr 5: Joint Probabilit Distributions and Random Sampls Sction 5. 7. P(..5. P( 5 4 65. 5.4..6.5 4..5.5. 65.6.5.9 a. 5.5 4 45 5.5 65 p (.4..5...9 E ( (5(.4 +.5(. +... + 65(.9 44. 5 µ b. s.5.5 8 P(s.8... E(s.5 8. a. T 4 P(T.4..7..9 b. µ E. µ T ( T c. T E( T E( T 5.8 (..98 87

Chaptr 5: Joint Probabilit Distributions and Random Sampls 9. 4 5 6 7 8 9 /n....4.5.6.7.8.9. p(/n.....5.7.88...69.7 X is a binomial random variabl with p.8. 4. a. Possibl valus of M ar:, 5,. M whn all nvlops contain mon, hnc p(m (.5.5. M whn thr is a singl nvlop with $, hnc p(m p(no nvlops with $ (.8.488. p(m 5 [.5 +.488].87. M 5 p(m.5.87.488 An altrnativ solution would b to list all 7 possibl combinations using a tr diagram and computing probabilitis dirctl from th tr. b. Th statistic of intrst is M, th maimum of,, or, so that M, 5, or. Th population distribution is a s follows: 5 p( / / /5 Writ a computr program to gnrat th digits 9 from a uniform distribution. Assign a valu of to th digits 4, a valu of 5 to digits 5 7, and a valu of to digits 8 and 9. Gnrat sampls of incrasing sizs, kping th numbr of rplications constant and comput M from ach sampl. As n, th sampl siz, incrass, p(m gos to zro, p(m gos to on. Furthrmor, p(m 5 gos to zro, but at a slowr rat than p(m. 88

Chaptr 5: Joint Probabilit Distributions and Random Sampls 4. Outcom,,,,4,,,,4 Probabilit.6..8.4..9.6..5.5.5.5 r Outcom,,,,4 4, 4, 4, 4,4 Probabilit.8.6.4..4... a..5.5.5.5 4 r b. P(.5.8.5.5.5 4 p (.6.4.5...4. c. r p(r..4..8 d. P ( X.5 P(,,, + P(,,, + + P(,,, + P(,,, + + P(,,, + P(,,, + + P(,,, (.4 4 + 4(.4 (. + 6(.4 (. + 4(.4 (..4 4. a. 7.75 8. 9.7 9.95.65.9.6 4 6 4 8 4 p ( b. 7.75.65.9 p ( c. all thr valus ar th sam:.4 89

Chaptr 5: Joint Probabilit Distributions and Random Sampls 4. Th statistic of intrst is th fourth sprad, or th diffrnc btwn th mdians of th uppr and lowr halvs of th data. Th population distribution is uniform with A 8 and B. Us a computr to gnrat sampls of sizs n 5,,, and from a uniform distribution with A 8 and B. Kp th numbr of rplications th sam (sa 5, for ampl. For ach sampl, comput th uppr and lowr fourth, thn comput th diffrnc. Plot th sampling distributions on sparat histograms for n 5,,, and. 44. Us a computr to gnrat sampls of sizs n 5,,, and from a Wibull distribution with paramtrs as givn, kping th numbr of rplications th sam, as in problm 4 abov. For ach sampl, calculat th man. Blow is a histogram, and a normal probabilit plot for th sampling distribution of for n 5, both gnratd b Minitab. This sampling distribution appars to b normal, so sinc largr sampl sizs will produc distributions that ar closr to normal, th othrs will also appar normal. 45. Using Minitab to gnrat th ncssar sampling distribution, w can s that as n incrass, th distribution slowl movs toward normalit. Howvr, vn th sampling distribution for n 5 is not t approimatl normal. n Normal Probabilit Plot 9 Frqunc 8 7 6 5 4 4 5 6 7 8 9 Probabilit.999.99.95.8.5..5.. 5 5 5 5 45 n 55 65 75 85 Andrson-D arling N ormalit Tst A-Squard: 7.46 P-Valu:. n 5 Normal Probabilit Plot Frqunc 7 6 5 4 Probabilit.999.99.95.8.5..5.. 4 5 6 5 5 5 4 5 55 65 Andrson- Darl ing Normali t Ts t A- Squa r d : 4. 4 8 P-Valu :. 9

Chaptr 5: Joint Probabilit Distributions and Random Sampls Sction 5.4 46. µ cm.4 cm a. n 6 E( X cm.4 µ. cm n 4 b. n 64 E( X cm.4 µ. 5cm n 8 c. X is mor likl to b within. cm of th man ( cm with th scond, largr, sampl. This is du to th dcrasd variabilit of X with a largr sampl siz. 47. µ cm.4 cm.99. a. n 6 P(.99 X. P Z.. P(- Z Φ( - Φ(-.84 -.587.686. b. n 5 P( X >. Z >.4 / 5 P P( Z >.5 - Φ(.5 -.8944.56 48. µ X,. n 49.75 5 5.5 5 P( 49.75 X 5.5 P Z.. a. µ 5 P(-.5 Z.5.9876 49.75 49.8 5.5 49.8 b. P( 49.75 X 5.5 P Z.. P(-.5 Z 4.5.695 9

Chaptr 5: Joint Probabilit Distributions and Random Sampls 49. a. P.M. 6:5 P.M. 5 minuts. With T X + + X 4 total grading tim, µ T nµ (4(6 4 and n, so P( T 5 P Z 5 4 P 7.95 ( Z.6. 66 T 7.95 6 4 7.95 b. P ( T > 6 P Z > P( Z >.5. 98 5. µ, psi 5 psi a. n 4 9,9,,, P( 9,9 X, P Z 5/ 4 5/ 4 P(-.6 Z.5 Φ(.5 - Φ(-.6.994 -.8.895 b. According to th Rul of Thumb givn in Sction 5.4, n should b gratr than in ordr to appl th C.L.T., thus using th sam procdur for n 5 as was usd for n 4 would not b appropriat. 5. X ~ N(,4. For da, n 5 P( X P Z P( Z.. 8686 / 5 For da, n 6 P( X P Z P( Z.. 8888 / 6 For both das, P( X (.8686(.8888.77 5. X ~ N(, n 4 µ T nµ (4( 4 and n ((, T W dsir th 95 th prcntil: 4 + (.645( 4.9 9

Chaptr 5: Joint Probabilit Distributions and Random Sampls 5. µ 5,. a. n 9 5 5 P( X 5 P Z P( Z.5.998. 6. / 9 b. n 4 5 5 P( X 5 P Z P( Z 5.7. / 4 54..85 µ X,. 7 n 5 a. µ. 65..65 P( X. P Z P( Z.6. 98.7 P(.65 X. P ( X. P( X.65. 48..65.5 b. P( X. P Z. 99 implis that.,.85/ n 85/ n which n.. Thus n will suffic. from µ npq. 464 55. np a. 4.5 P( 5 X P Z P(. Z. 968.464 b. 4.5 5.5 P( 5 X 5 P Z.464.464 P (.59 Z.59.888 56. a. With Y # of tickts, Y has approimatl a normal distribution with µ 5, 4.5 5 7.5 5 7.7, so P( 5 Y 7 Z 7.7 7.7 Z.9.988 P P( -.9 b. Hr µ 5, 5, 5. 8 4.5 5 75.5 5 Z 5.8 5.8, so P( 5 Y 75 P P( -.6 Z.6.896 9

Chaptr 5: Joint Probabilit Distributions and Random Sampls 57. E(X, Var(X, 4. 4 P( Z.77.966 5, so P( X 5 P Z 4.4 Sction 5.5 58. a. E( 7X + 5X + 5X 7 E(X + 5 E(X + 5 E(X 7( + 5(5 + 5( 87,85 V(7X + 5X + 5X 7 V(X + 5 V(X + 5 V(X 7 ( + 5 ( + 5 (8 9,,6 b. Th pctd valu is still corrct, but th varianc is not bcaus th covariancs now also contribut to th varianc. 59. a. E( X + X + X 8, V(X + X + X 45, 6. 78 + + 8 P(X + X + X P Z P( Z.98. 9986 6.78 P(5 X + X + X P ( 4.47 Z.98. 9986 5 µ X,. 6 n 55 6 P ( X 55 P Z P( Z.6.9875.6 P ( 58 X 6 P.89 Z.89. b. µ 6 ( 666 c. E( X -.5X -.5X ; V( X -.5X -.5X +.5 +.5.5, sd 4.744 P(- X -.5X -.5X 5 (..5 Z 5 P Z 4.744 4.744 P.85 -.74.857 94

Chaptr 5: Joint Probabilit Distributions and Random Sampls d. E( X + X + X 5, V(X + X + X 6, 6 + + 6 5 P(X + X + X P Z P( Z.67. 955 6 W want P( X + X X, or writtn anothr wa, P( X + X - X E( X + X - X 4 + 5 (6 -, V(X + X - X + + 78, 6, sd 8.8, so 4 ( P( X + X - X P Z P( Z.4. 8.8 6. Y is normall distributd with ( µ + µ ( µ + µ + µ µ Y, and 4 5 Y + + + 4 + 5.67, Y.7795. 4 4 9 9 9 ( Thus, P ( Y P Z P(.56 Z. 877 and.7795 P ( Y P Z P( Z.. 686.7795 6. a. Th marginal pmf s of X and Y ar givn in th solution to Ercis 7, from which E(X.8, E(Y.7, V(X.66, V(Y.6. Thus E(X+Y E(X + E(Y.5, V(X+Y V(X + V(Y.7, and th standard dviation of X + Y is.5 b. E(X+Y E(X + E(Y 5.4, V(X+Y 9V(X + V(Y 75.94, and th standard dviation of rvnu is 8.7 6. E( X + X + X E( X + E(X + E(X 5 + + 65 min., V(X + X + X + +.5 7.5, 7.5. 696 + + 6 65 Thus, P(X + X + X 6 P Z P( Z.86. 4.696 6. a. E(X.7, E(X.55, E(X X p(,. E(X X - E(X E(X..65.695, so Cov(X,X b. V(X + X V(X + V(X + Cov(X,X.59 +.875 + (.695 4.675 95

Chaptr 5: Joint Probabilit Distributions and Random Sampls 64. Lt X,, X 5 dnot morning tims and X 6,, X dnot vning tims. a. E(X + + X E(X + + E(X 5 E(X + 5 E(X 6 5(4 + 5(5 45 b. Var(X + + X Var(X + + Var(X 5 Var(X + 5Var(X 6 64 8 5 + 68. c. E(X X 6 E(X - E(X 6 4 5-64 64 Var(X X 6 Var(X + Var(X 6 +. 67 d. E[(X + + X 5 (X 6 + + X ] 5(4 5(5-5 Var[(X + + X 5 (X 6 + + X ] Var(X + + X 5 + Var(X 6 + + X ] 68. 65. µ 5.,. E V ( X Y +.,. 566 X Y 5 5 a. ( X Y ; (. X Y. P(.77 Z.77. 9 P (b th CLT b. V ( X Y +.,. 47 X Y 6 6 P. X Y. P. Z.. ( ( 966 66. a. With M 5X + X, E(M 5( + (4 5, Var(M 5 (.5 + ( 6.5, M.8. 75 5.8 b. P( 75 < M P < Z P(.4 < Z. 75 c. M A X + A X with th A I s and X I s all indpndnt, so E(M E(A X + E(A X E(A E(X + E(A E(X 5 d. Var(M E(M [E(M]. Rcall that for an r.v. Y, E(Y Var(Y + [E(Y]. Thus, E(M E ( A X + AX A X + A X E ( A E( X + E( A E( X E( A E( X + E( A E( X (b indpndnc (.5 + 5(.5 + 4 + (5(((4 + (.5 + ( + 6 6.565, so Var(M 6.565 (5.565 96

Chaptr 5: Joint Probabilit Distributions and Random Sampls. E(M 5 still, but now Var ( M avar( X + a acov( X, X + avar( X 6.5 + (5((-.5 + 8.5 67. Ltting X, X, and X dnot th lngths of th thr pics, th total lngth is X + X - X. This has a normal distribution with man valu + 5 4, varianc.5+.6+..4, and standard dviation.648. Standardizing givs P(4.5 X + X - X 5 P(.77 Z.54.588 68. Lt X and X dnot th (constant spds of th two plans. a. Aftr two hours, th plans hav travld X km. and X km., rspctivl, so th scond will not hav caught th first if X + > X, i.. if X X < 5. X X has a man 5 5 -, varianc +, and standard dviation 4.4. Thus, 5 ( P ( X X < 5 P Z < P( Z <.77.966. 4.4 b. Aftr two hours, # will b + X km from whr # startd, whras # will b X from whr it startd. Thus th sparation distanc will b al most if X X, i.. X X, i.. X X. Th corrsponding probabilit is P( X X P(.4 Z..98 -.97.6. 69. a. E(X + X + X 8 + + 6 4. b. Assuming indpndnc of X, X, X, Var(X + X + X (6 + (5 + (8.5 c. E(X + X + X 4 as bfor, but now Var(X + X + X Var(X + Var(X + Var(X + Cov(X,X + Cov(X, X + Cov(X, X 745, with sd 4.77 7. a. E (.5, so Y i n n n( n + E( W i E( Yi.5 i 4 i i n n n( n + (n + Var Y i so Var( W i Var( Yi.5 i 4 b. (.5, i i 97

Chaptr 5: Joint Probabilit Distributions and Random Sampls 7. W a. M a X + a X + W d a X + a X + 7, so E(M (5( + ((4 + (7(.5 58m M ( 5 (.5 + ( ( + ( 7 (.5 4. 5,. 74 M 58 b. P ( M P Z P( Z.. 9788.74 7. Th total lapsd tim btwn laving and rturning is T o X + X + X + X 4, with E ( 4, 4, 5. 477 T o T o T o. T o is normall distributd, and th dsird valu t is th 99 th prcntil of th lapsd tim distribution addd to A.M.: : + [4+(5.477(.] :5.76 7. a. Both approimatl normal b th C.L.T. b. Th diffrnc of two r.v. s is just a spcial linar combination, and a linar combination X Y has approimatl a normal 8 6 µ and +.69,. 6 X Y X Y XY 4 5 of normal r.v s has a normal distribution, so distribution with 5 5 5 P X Y & P Z.6.6 P (.7 Z.47.68 c. ( 5 P & This probabilit is.6 µ d. ( X Y P Z P( Z.8.. quit small, so such an occurrnc is unlikl if µ 5, and w would thus doubt this claim. 74. X is approimatl normal with (5(.7 5 µ and (5(.7(.. 5 is Y with µ and. Thus 5 X Y p X Y 5 P Z 4.74 4.74 X Y., so µ and 5 ( 5 P(. Z. 486, as 98

Chaptr 5: Joint Probabilit Distributions and Random Sampls Supplmntar Erciss 75. a. p X ( is obtaind b adding joint probabilitis across th row labld, rsulting in p X (.,.5,. for, 5, rspctivl. Similarl, from column sums p (.,.5,.55 for, 5, rspctivl. b. P(X 5 and Y 5 p(, + p(,5 + p(5, + p(5,5.5 c. p ( p ( (.(..5 p(,, so X and Y ar not indpndnt. (Almost an othr (, pair ilds th sam conclusion. d. E ( X + Y ( + p(,. 5 (or E(X + E(Y.5. E ( X Y + p(,. 85 76. Th roll-up procdur is not valid for th 75 th prcntil unlss 77. and or or both, as dscribd blow. Sum of prcntils: µ + Z + µ + ( Z µ + µ + ( Z( + Prcntil of sums: ( µ + + µ + ( Z Ths ar qual whn Z (i.. for th mdian or in th unusual cas whn + +, which happns whn. + or or both and + a. f (, dd kdd+ 8,5 k k 8,5 kdd b. f X ( kd k(5 kd k(45 + and b smmtr f Y ( is obtaind b substituting for in f X (. Sinc f X (5 >, and f Y (5 >, but f(5, 5, f X ( f Y ( f(, for all, so X and Y ar not indpndnt. 99

Chaptr 5: Joint Probabilit Distributions and Random Sampls 5 c. P ( X + Y 5 kdd+ 5 5 kdd,65.55 8,5 4 d. E X + Y E( X + E( Y { k( 5 + ( } k 45 d k ( d + (5,666.67 5. 969. E ( XY f (, dd + k k dd k dd,5, 6.4 Cov(X,Y 6.4 (.9845 -.9, and E(X E(Y 4.654, so.9 4.654 (.9845 6.8 and ρ. 894 6.8 f. Var (X + Y Var(X + Var(Y + Cov(X,Y 7.66, so 78. F Y ( P( ma(x,, X n P( X,, X n [P(X ] n. n for. n n n E n n n n + + + u du n n + n + n Thus f Y ( ( n ( d ( u + n ( Y u du n n n for 79. E ( X + Y + Z 5 + 9 + 4 5 8 Var ( X + Y + Z + +.4, and th std dv.9. 65 65 65 P ( X + Y + Z 5 P( Z 9.

Chaptr 5: Joint Probabilit Distributions and Random Sampls 8. a. Lt X,, X dnot th wights for th businss-class passngrs and Y,, Y 5 dnot th tourist-class wights. Thn T total wight X + + X + Y + + Y 5 X + Y E(X E(X ( 6; V(X V(X (6 4. E(Y 5E(Y 5(4 ; V(Y 5V(Y 5( 5. Thus E(T E(X + E(Y 6 + 6 And V(T V(X + V(Y 4 + 5 54, std dv 7.7 5 6 7.7 b. P ( T 5 P Z P( Z.9. 97 8. a. E(N µ ((4 4 minuts b. W pct componnts to com in for rpair during a 4 hour priod, so E(N µ ((.5 7 8. X ~ Bin (,.45 and Y ~ Bin (,.6. Bcaus both n s ar larg, both X and Y ar approimatl normal, so X + Y is approimatl normal with man ((.45 + ((.6 7, varianc (.45(.55 + (.6(.4.4, and standard dviation.. Thus, P(X 49.5 7. + Y 5 P Z P( Z.86. 9686.. 8..95 P( µ. X µ +. & P Z./ n./ n P(. n Z. n, but (.96 Z.96. 95..96 n 97. n Th C.L.T. P so 84. I hav 9 oz. Th amount which I would consum if thr wr no limit is T o X + + X 4 whr ach X I is normall distributd with µ and. Thus T o is normal with µ 8 and 7. 48, so P(T o < 9 P(Z <.4.999. T o T o 85. Th pctd valu and standard dviation of volum ar 87,85 and 47.7, rspctivl, so, 87,85 P ( volum, P Z P( Z.78.997 47.7 86. Th studnt will not b lat if X + X X, i.. if X X + X. This linar combination has man, varianc 4.5, and standard dviation.6, so ( P ( X X + X P Z P( Z.97.84.6

Chaptr 5: Joint Probabilit Distributions and Random Sampls 87. a. Var( ax + Y a + acov( X, Y + a + a ρ + Substituting a Y ilds + Y ρ + Y Y ( ρ X Y, so ρ X Y. b. Sam argumnt as in a c. Suppos ρ. Thn Var ( ax Y Y ( ρ, which implis that ax Y k (a constant, so ax Y ax k, which is of th form ax + b. 88. X + Y t ( + t E ( f (, dd. To find th minimizing valu of t, tak th drivativ with rspct to t and quat it to : ( + t( f (, tf (, dd t ( + f (, dd E( X + Y, so th bst prdiction is th individual s pctd scor (.67. 89. a. With Y X + X, F Y ( ν / ( ν / Γ( ν / ν / Γ But th innr intgral can b shown to b qual to [ ( ν / + ν Γ ( ν + ν / ν ν + ( ν+ ν / ] /, from which th rsult follows. d d. b. B a, ν Z + is chi-squard with Z, tc, until ν, so ( Z Z + Z + 9s chi-squard withν n Z... + Z n + is chi-squard with c. X i µ is standard normal, so is chi-squard with ν n. X i µ is chi-squard with ν, so th sum

Chaptr 5: Joint Probabilit Distributions and Random Sampls 9. a. Cov(X, Y + Z E[X(Y + Z] E(X E(Y + Z E(XY + E(XZ E(X E(Y E(X E(Z E(XY E(X E(Y + E(XZ E(X E(Z Cov(X,Y + Cov(X,Z. b. Cov(X + X, Y + Y Cov(X, Y + Cov(X,Y + Cov(X, Y + Cov(X,Y (appl a twic 6. 9. a. V X V ( W + E + V ( W + E V ( and ( W E X ( X, X Cov( W + E, W + E Cov( W, W + Cov( W, E ( E, W + Cov( E, E Cov( W, W V ( W w. Cov Cov ρ + Thus, W + E W W + E W + W E b. ρ. 9999 +. 9. a. Cov(X,Y Cov(A+D, B+E Cov(A,B + Cov(D,B + Cov(A,E + Cov(D,E Cov(A,B. Thus Corr( X, Y A Cov( A, B + + A D Cov( A, B A B A B + + D B B E E Th first factor in this prssion is Corr(A,B, and (b th rsult of rcis 7a th scond and third factors ar th squar roots of Corr(X, X and Corr(Y, Y, rspctivl. Clarl, masurmnt rror rducs th corrlation, sinc both squar-root factors ar btwn and. b.. 8.95. 855 rducs th corrlation.. This is disturbing, bcaus masurmnt rror substantiall

Chaptr 5: Joint Probabilit Distributions and Random Sampls 9. E Y & h( µ, µ, µ, µ [ + + ] 6 ( 4 5 Th partial drivativs of µ, µ, µ, 4 4,, and 4 h ( µ 4 with rspct to,,, and 4 ar, + +, rspctivl. Substituting, 5,, and 4 givs., -.5, -., and.67, rspctivl, so V(Y ((-. + ((-.5 + (.5(-. + (4.(.67.678, and th approimat sd of is.64. 4 94. Th four scond ordr partials ar, E(Y 6 +. +.56 +.8 6.894. 4, 4, and rspctivl. Substitution givs 4