Skip to content
Textbook Guides

Solution Manual for Introduction to Mathematical Statistics, 8th Edition

Solution Manual for Introduction to Mathematical Statistics, 8th Edition is here to help you with textbook problems, offering clear solutions and helpful explanations.

Preview 16 of 138 pages

See the first 16 pages exactly as they appear in the document.

  1. Page 1
    Read page 1 as text

    S OLUTIONS M ANUAL J OSEPH W. M C K EAN I NTRODUCTION TO M ATHEMATICAL S TATISTICS E IGHTH E DITION Robert V. Hogg University of Iowa Joseph W. McKean Western Michigan University Allen T. Craig Late Professor of Statistics University of Iowa

  2. Page 2
  3. Page 3
    Read page 3 as text

    Contents 1 Probability and Distributions 1 2 Multivariate Distributions 11 3 Some Special Distributions 19 4 Some Elementary Statistical Inferences 31 5 Consistency and Limiting Distributions 53 6 Maximum Likelihood Methods 59 7 Sufficiency 75 8 Optimal Tests of Hypotheses 89 9 Inferences about Normal Models 97 10 Nonparametric and Robust Statistics 113 11 Bayesian Statistics 131 iii

  4. Page 4
    Read page 4 as text

    Chapter 1 Probability and Distributions 1.2.1 Part (c): C 1 ∩ C 2 = { ( x, y ) : 1 < x < 2 , 1 < y < 2 } . 1.2.3 C 1 ∩ C 2 = { mary,mray } . 1.2.6 lim k →∞ C k = { x : 0 < x < 3 } . Note: neither the number 0 nor the number 3 is in any of the sets C k , k = 1 , 2 , 3 , . . . 1.2.7 Part (b): lim k →∞ C k = φ , because no point is in all the sets C k , k = 1 , 2 , 3 , . . . 1.2.9 Because f ( x ) = 0 when 1 ≤ x < 10, Q ( C 3 ) = ∫ 10 0 f ( x ) dx = ∫ 1 0 6 x (1 − x ) dx = 1 . 1.2.11 Part (c): Draw the region C carefully, noting that x < 2 / 3 because 3 x/ 2 < 1. Thus Q ( C ) = ∫ 2 / 3 0 [ ∫ 3 x/ 2 x/ 2 dy ] dx = ∫ 2 / 3 0 x dx = 2 / 9 . 1.2.14 Note that 25 = Q ( C ) = Q ( C 1 ) + Q ( C 2 ) − Q ( C 1 ∩ C 2 ) = 19 + 16 − Q ( C 1 ∩ C 2 ) . Hence, Q ( C 1 ∩ C 2 ) = 10. 1.2.15 By studying a Venn diagram with 3 intersecting sets, it should be true that 11 ≥ 8 + 6 + 5 − 3 − 2 − 1 = 13 . It is not, and the accuracy of the report should be questioned. 1.3.3 P ( C ) = 1 2 + 1 4 + 1 8 + · · · = 1 / 2 1 − (1 / 2) = 1 . 1

  5. Page 5
    Read page 5 as text

    2 Probability and Distributions 1.3.6 P ( C ) = ∫ ∞ −∞ e −| x | dx = ∫ 0 −∞ e x dx + ∫ ∞ 0 e − x dx = 2  = 1 . We must multiply by 1 / 2. 1.3.8 P ( C c 1 ∪ C c 2 ) = P [( C 1 ∩ C 2 ) c ] = P ( C ) = 1 , because C 1 ∩ C 2 = φ and φ c = C . 1.3.11 The probability that he does not win a prize is ( 990 5 ) / ( 1000 5 ) . 1.3.13 Part (a): We must have 3 even or one even, 2 odd to have an even sum. Hence, the answer is ( 10 3 )( 10 0 ) ( 20 3 ) + ( 10 1 )( 10 2 ) ( 20 3 ) . 1.3.14 There are 5 mutual exclusive ways this can happen: two “ones”, two “twos”, two “threes”, two “reds”, two “blues.” The sum of the corresponding proba- bilities is ( 2 2 )( 6 0 ) + ( 2 2 )( 6 0 ) + ( 2 2 )( 6 0 ) + ( 5 2 )( 3 0 ) + ( 3 2 )( 5 0 ) ( 8 2 ) . 1.3.15 (a) 1 − ( 48 5 )( 2 0 ) ( 50 5 ) (b) 1 − ( 48 n )( 2 0 ) ( 50 n ) ≥ 1 2 , Solve for n . 1.3.20 Choose an integer n 0 > max { a − 1 , (1 − a ) − 1 } . Then { a } = ∩ ∞ n = n 0 ( a − 1 n , a + 1 n ) . Hence by (1.3.10), P ( { a } ) = lim n →∞ P [( a − 1 n , a + 1 n )] = 2 n = 0 . 1.3.21 Choose n 0 such that 0 < a − (1 /n 0 ) < a < a + (1 /n 0 ) < 1. Let A n = ( a − (1 /n ) , a + (1 /n )), for n ≥ n 0 . Since { a } = ∩ ∞ n = n 0 A n , we have P ( { a } ) = P ( ∩ ∞ n = n 0 A n ) = lim n →∞ P ( A n ) = lim n →∞ 2 n = 0 .

  6. Page 6
    Read page 6 as text

    3 1.4.2 P [( C 1 ∩ C 2 ∩ C 3 ) ∩ C 4 ] = P [ C 4 | C 1 ∩ C 2 ∩ C 3 ] P ( C 1 ∩ C 2 ∩ C 3 ) , and so forth. That is, write the last factor as P [( C 1 ∩ C 2 ) ∩ C 3 ] = P [ C 3 | C 1 ∩ C 2 ] P ( C 1 ∩ C 2 ) . 1.4.5 [( 4 3 )( 48 10 ) + ( 4 4 )( 48 9 )] / ( 52 13 ) [( 4 2 )( 48 11 ) + ( 4 3 )( 48 10 ) + ( 4 4 )( 48 9 )] / ( 52 13 ) . 1.4.10 P ( C 1 | C ) = (2 / 3)(3 / 10) (2 / 3)(3 / 10) + (1 / 3)(8 / 10) = 3 7 < 2 3 = P ( C 1 ) . 1.4.12 Part (c): P ( C 1 ∪ C c 2 ) = 1 − P [( C 1 ∪ C c 2 ) c ] = 1 − P ( C ∗ 1 ∩ C 2 ) = 1 − (0 . 4)(0 . 3) = 0 . 88 . 1.4.14 Part (d): 1 − (0 . 3) 2 (0 . 1)(0 . 6) . 1.4.16 1 − P ( T T ) = 1 − (1 / 2)(1 / 2) = 3 / 4, assuming independence and that H and T are equilikely. 1.4.19 Let C be the complement of the event; i.e., C equals at most 3 draws to get the first spade. (a) P ( C ) = 1 4 + 3 4 1 4 + ( 3 4 ) 2 1 4 . (b) P ( C ) = 1 4 + 13 51 39 52 + 13 50 38 51 39 52 . 1.4.22 The probability that A wins is: 1 / 6+5 / 6 × 4 / 6 × 3 / 6+5 / 6 × 4 / 6 × 3 / 6 × 2 / 6 × 5 / 6. 1.4.26 Let Y denote the bulb is yellow and let T 1 and T 2 denote bags of the first and second types, respectively. (a) P ( Y ) = P ( Y | T 1 ) P ( T 1 ) + P ( Y | T 2 ) P ( T 2 ) = 20 25 . 6 + 10 25 . 4 . (b) P ( T 1 | Y ) = P ( Y | T 1 ) P ( T 1 ) P ( Y ) . 1.4.30 Suppose without loss of generality that the prize is behind curtain 1. Con- dition on the event that the contestant switches. If the contestant chooses curtain 2 then she wins, (In this case Monte cannot choose curtain 1, so he must choose curtain 3 and, hence, the contestant switches to curtain 1). Like- wise, in the case the contestant chooses curtain 3. If the contestant chooses curtain 1, she loses. Therefore the conditional probability that she wins is 2 3 .

  7. Page 7
    Read page 7 as text

    4 Probability and Distributions 1.4.31 (1) The probability is 1 − ( 5 6 ) 4 . (2) The probability is 1 − [ ( 5 6 ) 2 + 10 36 ] 24 . 1.5.2 Part (a): c [(2 / 3) + (2 / 3) 2 + (2 / 3) 3 + · · · ] = c (2 / 3) 1 − (2 / 3) = 2 c = 1 , so c = 1 / 2. 1.5.5 Part (a): p ( x ) = { ( 13 x )( 39 5 − x ) ( 52 5 ) x = 0 , 1 , . . . , 5 0 elsewhere . 1.5.9 Part (b): 50 ∑ x =1 x/ 5050 = 50(51) 2(5050) = 51 202 . 1.5.10 For Part (c): Let C n = { X ≤ n } . Then C n ⊂ C n +1 and ∪ n C n = R . Hence, lim n →∞ F ( n ) = 1. Let  > 0 be given. Choose n 0 such that n ≥ n 0 implies 1 − F ( n ) <  . Then if x ≥ n 0 , 1 − F ( x ) ≤ 1 − F ( n 0 ) <  . 1.6.2 Part (a): p ( x ) = ( 9 x − 1 ) ( 10 x − 1 ) 1 11 − x = 1 10 , x = 1 , 2 , . . . 10 . 1.6.3 (a) p ( x ) = ( 5 6 ) x − 1 ( 1 6 ) , x = 1 , 2 , 3 , . . . (b) ∞ ∑ x =1 ( 5 6 ) x − 1 ( 1 6 ) = 1 / 6 1 − (25 / 36) = 6 11 . 1.6.5 Here are R functions which compute the pmf and the cdf: p165 <- function(){ x = 0:5 p165 = choose(20,x)*choose(80,5-x)/choose(100,5) return(p165) } cdf165 <- function(){ pm <- p165(); dm = -1:6; dx = c(dm,dm); dy = c(rep(0,8),rep(1,8)) plot(dy~dx,pch=" ",xlab="x",ylab=expression(F(x)));segments(-1,0,0,0) ct = 0; cx = -1

  8. Page 8
    Read page 8 as text

    5 for(j in 1:6){ ct = ct + pm[j]; cx = cx + 1 segments(cx,ct,cx+1,ct) } } 1.6.8 D y = { 1 , 2 3 , 3 3 , . . . } . The pmf of Y is p ( y ) = ( 1 2 ) y 1 / 3 , y ∈ D y . 1.7.1 If √ x < 10 then F ( x ) = P [ X ( c ) = c 2 ≤ x ] = P ( c ≤ √ x ) = ∫ √ x 0 1 10 dz = √ x 10 . Thus f ( x ) = F ′ ( x ) = { 1 20 √ x 0 < x < 100 0 elsewhere . 1.7.2 C 2 ⊂ C c 1 ⇒ P ( C 2 ) ≤ P ( C c 1 ) = 1 − (3 / 8) = 5 / 8 . 1.7.4 Among other characteristics, ∫ ∞ −∞ 1 π (1 + x 2 ) dx = 1 π arctan x ∣ ∣ ∣ ∣ ∞ −∞ = 1 π [ π 2 − ( − π 2 )] = 1 . 1.7.6 Part (b): P ( X 2 < 9) = P ( − 3 < X < 3) = ∫ 3 − 2 x + 2 19 dx = 1 18 [ x 2 2 + 2 x ] 3 − 2 = 1 18 [ 21 2 − ( − 2) ] = 25 36 . 1.7.8 Part (c): f ′ ( x ) = xe − x − 1 2 x 2 e − x = 1 2 xe − x (2 − x ) = 0; hence, x = 2 is the mode because it maximizes f ( x ). 1.7.9 Part (b): ∫ m 0 3 x 2 dx = 1 2 ; hence, m 3 = 2 − 1 and m = (1 / 2) 1 / 3 .

  9. Page 9
    Read page 9 as text

    6 Probability and Distributions 1.7.10 ∫ ξ 0 . 2 0 4 x 3 dx = 0 . 2 : hence, ξ 4 0 . 2 = 0 . 2 and ξ 0 . 2 = 0 . 2 1 / 4 . 1.7.13 x = 1 is the mode because for 0 < x < ∞ because f ( x ) = F ′ ( x ) = e − x − e − x + xe − x = xe − x f ′ ( x ) = − xe − x + e − x = 0 , and f ′ (1) = 0. 1.7.16 Since Δ > 0 X > z ⇒ Y = X + Δ > z. Hence, P ( X > z ) ≤ P ( Y > z ). 1.7.19 Since f ( x ) is symmetric about 0, ξ . 25 < 0. So we need to solve, ∫ ξ . 25 − 2 ( − x 4 ) dx = . 25 . The solution is ξ . 25 = − √ 2. 1.7.22 For 0 < y < 27, x = y 1 / 3 , dx dy = 1 3 y − 2 / 3 g ( y ) = = 1 3 y 2 / 3 y 2 / 3 9 = 1 27 . 1.7.24 f ( x ) = 1 π , − π 2 < x < π 2 . x = arctan y, dx dy = 1 1 + y 2 , −∞ < y < ∞ . g ( y ) = 1 π 1 1 + y 2 , −∞ < y < ∞ . 1.7.25 G ( y ) = P ( − 2 log X 4 ≤ y ) = P ( X ≥ e − y/ 8 ) = ∫ 1 e − y/ 8 4 x 3 dx = 1 − e − y/ 2 , 0 < y < ∞ g ( y ) = G ′ ( y ) = { e − y/ 2 0 < y < ∞ 0 elsewhere .

  10. Page 10
    Read page 10 as text

    7 1.7.26 G ( y ) = P ( X 2 ≤ y ) = P ( − √ y ≤ X ≤ √ y ) = ⎧ ⎨ ⎩ ∫ √ y − √ y 1 3 dx = 2 √ y 3 0 ≤ y < 1 ∫ √ y − 1 1 3 dx = √ y 3 + 1 3 1 ≤ y < 4 g ( y ) = ⎧ ⎪ ⎪ ⎪ ⎨ ⎪ ⎪ ⎪ ⎩ 1 3 √ y 0 ≤ y < 1 1 6 √ y 1 ≤ y < 4 0 elsewhere . 1.8.5 E (1 /X ) = 100 ∑ x =51 1 x 1 50 . The latter sum is bounded by the two integrals ∫ 101 51 1 x dx and ∫ 100 50 1 x dx. An appropriate approximation might be 1 50 ∫ 101 . 5 50 . 5 1 x dx = 1 50 (log 100 . 5 − log 50 . 5) . 1.8.7 E [ X (1 − X )] = ∫ 1 0 x (1 − x )3 x 2 dx. 1.8.9 When 1 < y < ∞ G ( y ) = P (1 /X ≤ y ) = P ( X ≥ 1 /y ) = ∫ 1 1 /y 2 x dx = 1 − 1 y 2 g ( y ) = 2 y 3 E ( Y ) = ∫ ∞ 1 y 2 y 3 dy = 2 , which equals ∫ 1 0 (1 /x )2 x dx . 1.8.11 The expectation of X does not exist because E ( | X | ) = 2 π ∫ ∞ 0 x 1 + x 2 dx = 1 π ∫ ∞ 1 1 u du = ∞ , where the change of variable u = 1 + x 2 was used. 1.8.14 Here is the pmf of G :

  11. Page 11
    Read page 11 as text

    8 Probability and Distributions − p 0 + 2 − p 0 + 5 − p 0 + 8 ( 3 2 ) ( 5 2 ) ( 3 1 )( 2 1 ) ( 5 2 ) ( 2 2 ) ( 5 2 ) It follows that E ( G ) = − p 0 + 4 . 4; so for a fair game take p 0 = $4 . 40. Here is an R function which simulates the game. game1814 <- function(p0,nsims){ collG = c() for(i in 1:nsims){ p = sample(c(1,1,1,4,4),2) collG = c(collG,-p0 + sum(p)) } game1814 = mean(collG) return(game1814) } 1.9.2 M ( t ) = ∞ ∑ x =1 ( e t 2 ) x = e t / 2 1 − ( e t / 2) , e t / 2 < 1 . Find E ( X ) = M ′ (0) and Var( X ) = M ′′ (0) − [ M ′ (0)] 2 . 1.9.4 0 ≤ var( X ) = E ( X 2 ) − [ E ( X )] 2 . 1.9.6 E [ ( X − μ σ ) 2 ] = 1 σ 2 σ 2 = 1 . 1.9.8 K ( b ) = E [( X − b ) 2 ] = E ( X 2 ) − 2 bE ( X ) + b 2 K ′ ( b ) = − 2 E ( X ) + 2 b = 0 ⇒ b = E ( X ) . 1.9.11 For a continuous type random variable, K ( t ) = ∫ ∞ −∞ t x f ( x ) dx. K ′ ( t ) = ∫ ∞ −∞ xt x − 1 f ( x ) dx ⇒ K ′ (1) = E ( X ) . K ′′ ( t ) = ∫ ∞ −∞ x ( x − 1) t x − 2 f ( x ) dx ⇒ K ′′ (1) = E [ X ( X 1 )]; and so forth.

  12. Page 12
    Read page 12 as text

    9 1.9.12 3 = E ( X − 7) ⇒ E ( X ) = 10 = μ. 11 = E [( X − 7) 2 ] = E ( X 2 ) − 14 E ( X ) + 49 = E ( X 2 ) − 91 ⇒ E ( X 2 ) = 102 and var( X ) = 102 − 100 = 2 . 15 = E [( X − 7) 3 ] . Expand ( X − 7) 3 and continue. 1.9.16 E ( X ) = 0 ⇒ var( X ) = E ( X 2 ) = 2 p. E ( X 4 ) = 2 p ⇒ kurtosis = 2 p/ 4 p 2 = 1 / 2 p. 1.9.17 ψ ′ ( t ) = M ′ ( t ) /M ( t ) ⇒ ψ ′ (0) = M ′ (0) /M (0) = E ( X ) . ψ ′′ ( t ) = M ( t ) M ′′ ( t ) − M ′ ( t ) M ′ ( t ) [ M ( t ) 2 ] ⇒ ψ ′′ (0) = M (0) M ′′ (0) − M ′ (0) M ′ (0) [ M (0) 2 ] = M ′′ (0) − [ M ′ (0)] 2 = var( X ) . 1.9.19 M ( t ) = (1 − t ) − 3 = 1 + 3 t + 3 · 4 t 2 2! + 3 · 4 · 5 t 3 3! + · · · Considering the coefficient of t r /r !, we have E ( X r ) = 3 · 4 · 5 · · · ( r + 2) , r = 1 , 2 , 3 . . . . 1.9.21 Integrating the parts with u = 1 − F ( x ), dv = dx , we get { [1 − F ( x )] x } b 0 − ∫ b 0 x [ − f ( x )] dx = ∫ b 0 xf ( x ) dx = E ( X ) . 1.9.24 E ( X ) = ∫ 1 0 x 1 4 dx + 0 · 1 4 + 1 · 1 2 = 5 8 . E ( X 2 ) = ∫ 1 0 x 2 1 4 dx + 0 · 1 4 + 1 · 1 2 = 7 12 . var( X ) = 7 12 − ( 5 8 ) 2 = 37 192 . 1.9.25 E ( X ) = ∫ ∞ −∞ x [ c 1 f 1 ( x ) + · · · + c k f k ( x )] dx = k ∑ i =1 c i μ i = μ.

  13. Page 13
    Read page 13 as text

    10 Probability and Distributions Because ∫ ∞ −∞ ( x − μ ) 2 f i ( x ) dx = σ 2 i + ( μ i − μ ) 2 , we have E [( X − μ ) 2 ] = k ∑ i =1 c i [ σ 2 i + ( μ i − μ ) 2 ] . 1.10.2 μ = ∫ ∞ 0 xf ( x ) dx ≥ ∫ ∞ 2 μ 2 μf ( x ) dx = 2 μP ( X > 2 μ ) . Thus 1 2 ≥ P ( X > 2 μ ) . 1.10.5 If, in Theorem 1.10.2, we take u ( X ) = exp { tX } and c = exp { ta } , we have P (exp { tX } ≥ exp { ta } ] ≤ M ( t ) exp {− ta } . If t > 0, the events exp { tX } ≥ exp { ta } and X ≥ a are equivalent. If t < 0, the events exp { tX } ≥ exp { ta } and X ≤ a are equivalent. 1.10.6 We have P ( X ≥ 1) ≤ [1 − exp {− 2 t } ] / 2 t for all 0 < t < ∞ , and P ( X ≤ − 1) ≤ [exp { 2 t } − 1] / 2 t for all −∞ < t < 0. Each of these bounds has the limit 0 as t → ∞ and t → −∞ , respectively.

  14. Page 14
    Read page 14 as text

    Chapter 2 Multivariate Distributions 2.1.2 P ( A 5 ) = 7 8 − 4 8 − 3 8 + 2 8 = 2 8 . 2.1.5 ∫ ∞ 0 ∫ ∞ 0 [ 2 g ( √ x 2 1 + x 2 2 ) /π √ x 2 1 + x 2 2 ] dx 1 dx 2 = ∫ ∞ 0 ∫ π/ 2 0 [2 g ( ρ ) /πρ ] ρ dθdρ = ∫ ∞ 0 g ( ρ ) dρ = 1 . 2.1.6 We can write the double integration as P ( a < X < b, c < Y < d ) = ∫ b a 2 xe − x 2 dx · ∫ d c 2 ye − y 2 dy. Since a, c > 0, the one-to-one transformations z = x 2 and w = y 2 , lead to the answer. 2.1.7 G ( z ) = P ( X + Y ≤ z ) = ∫ z 0 ∫ z − x 0 e − x − y dydx = ∫ z 0 [1 − e − ( z − x ) ] e − x dx = 1 − e − z − ze − z . g ( z ) = G ′ ( z ) = { ze − z 0 < z < ∞ 0 elsewhere . 11

  15. Page 15
    Read page 15 as text

    12 Multivariate Distributions 2.1.8 G ( z ) = P ( XY ≤ z ) = 1 − ∫ 1 z ∫ 1 z/x dydx = 1 − ∫ 1 z ( 1 − z x ) dx = z − z log z g ( z ) = G ′ ( z ) = { − log z 0 < z < 1 0 elsewhere . Why is − log z > 0? 2.1.9 f ( x, y ) = ⎧ ⎨ ⎩ ( 13 x )( 13 y )( 26 13 − x − y ) ( 52 13 ) x ≥ 0 , y ≥ 0 , x + y ≤ 13 , x and y integers 0 elsewhere . 2.1.11 P ( X 1 + X 2 ≤ 1) = 15 ∫ 1 / 2 0 x 2 1 [∫ 1 − x 1 x 1 x 2 dx 2 ] dx 1 . 2.1.15 E [ e t 1 X 1 + t 2 X 2 ] = ∞ ∑ i =1 ∞ ∑ j =1 e t 1 i + t 2 j ( 1 2 ) i + j = ∞ ∑ i =1 ( e t 1 1 2 ) i ∞ ∑ j =1 ( e t 1 1 2 ) j = [ 1 1 − 2 − 1 e t 1 − 1 ] [ 1 1 − 2 − 1 e t 2 − 1 ] , provided t i < log 2, i = 1 , 2. 2.2.1 p ( y 1 , y 2 ) = { ( 2 3 ) y 2 ( 1 3 ) 2 − y 2 ( y 1 , y 2 ) = (0 , 0) , ( − 1 , 1) , (1 , 1) , (0 , 2) 0 elsewhere . 2.2.2 p ( y 1 , y 2 ) = { y 1 / 36 y 1 = y 2 , 2 y 2 , 3 y 2 ; y 2 = 1 , 2 , 3 0 elsewhere . y 1 1 2 3 4 6 9 p ( y 1 ) 1/36 4/36 6/36 4/36 12/36 9/36 2.2.4 The inverse transformation is given by x 1 = y 1 y 2 and x 2 = y 2 with Jacobian J = y 2 . By noting what the boundaries of the space S ( X 1 , X 2 ) map into, it follows that the space T ( Y 1 , Y 2 ) = { ( y 1 , y 2 ) : 0 < y i < 1 , i = 1 , 2 } . The pdf of ( Y 1 , Y 2 ) is f Y 1 ,Y 2 ( y 1 , y 2 ) = 8 y 1 y 3 2 .

  16. Page 16
    Read page 16 as text

    13 2.2.5 The inverse transformation is x 1 = y 1 − y 2 and x 2 = y 2 with Jacobian J = 1. The space of ( Y 1 , Y 2 ) is T = { ( y 1 , y 2 ) : −∞ < y i < ∞ , i = 1 , 2 } . Thus the joint pdf of ( Y 1 , Y 2 ) is f Y 1 ,Y 2 ( y 1 , y 2 ) = f X 1 ,X 2 ( y 1 − y 2 , y 2 ) , which leads to formula (2.2.1). 2.3.2 ( a ) c 1 ∫ x 2 0 x 1 /x 2 2 dx 1 = c 1 2 = 1 ⇒ c 1 = 2 and c 2 = 5 . ( b ) 10 x 1 x 2 2 , 0 < x 1 < x 2 < 1; zero elsewhere ( c ) ∫ 1 / 2 1 / 4 2 x 1 / (5 / 8) 2 dx = 64 25 ( 1 4 − 1 16 ) = 12 25 . ( d ) ∫ 1 / 2 1 / 4 ∫ 1 x 1 10 x 1 x 2 2 dx 2 dx 1 = ∫ 1 / 2 1 / 4 10 3 x 1 (1 − x 3 1 ) dx 1 = 135 512 . 2.3.3 f 2 ( x 2 ) = ∫ x 2 0 21 x 2 1 x 3 2 dx 1 = 7 x 6 2 , 0 < x 2 < 1 . f 1 | 2 ( x 1 | x 2 ) = 21 x 2 1 x 3 2 / 7 x 6 2 = 3 x 2 1 /x 3 2 , 0 < x 1 < x 2 . E ( X 1 | x 2 ) = ∫ x 2 0 x 1 (3 x 2 1 /x 3 2 ) dx 1 = 3 4 x 2 . G ( y ) = P ( 3 4 X 2 ≤ y ) = ∫ 4 y/ 3 0 7 x 6 2 dx 2 = ( 4 y 3 ) 7 , 0 < y < 3 4 g ( y ) = { 7 ( 4 3 ) 7 y 6 0 < y < 3 4 0 elsewhere . E ( Y ) = 7 8 3 4 = 21 32 . Var( Y ) = 7 1024 . E ( X 1 ) = 21 32 . Var( X 1 ) = 553 15360 > 7 1024 . 2.3.8 The marginal pdf of X is f X ( x ) = 2 ∫ ∞ x e − x e − y dy = 2 e − 2 x , 0 < x < ∞ . Hence, the conditional pdf of Y given X = x is f Y | X ( y | x ) = 2 e − x e − y 2 e − 2 x = e − ( y − x ) , 0 < x < y < ∞ ,

122 more pages in the full document

Unlock it once and it stays in your library, ready to chat with or turn into flashcards.

Unlock the full document

More Statistics study materials

See all

Study this document with CramX

Once it is in your library, every tool can work from it.