hw8-stat516

# hw8-stat516 - 20 Some Special Distributions 3.3.1(1 — my6...

• Notes
• MinisterIronDragonfly8373
• 4
• 100% (1) 1 out of 1 people found this document helpful

This preview shows pages 1–4. Sign up to view the full content.

This preview has intentionally blurred sections. Sign up to view the full version.

This preview has intentionally blurred sections. Sign up to view the full version.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 20 Some Special Distributions 3.3.1 (1 — my6 = (1 — zen-W? => X is x202). Fiom tables, P(X < 5.23) = 0.05. 3.3.4 2:2: 392732 4!23t3 M(t) — 1 + + 3! + 3! = 1+ 2(2t) + 3(2):)2 + 4(2t)3 + - -- = (1 — 20-2 = (1 — 20-4/9, s X is X2(4). 3.3.6 P(Y s y) = 1- [P(X > 3)]3 — (e-y)3 =1 — e-39 = G(y), 9(11) = 0(9) = 3e‘3", 0 < y < 00. 3.3.7 f’(:z:) = Elie—2m + Elite—I/W—l/ﬂ) = 0; hence, a: = ,6 which is given as 2. Thus X is x2(4). 3.3.9 P(X 2 204;) g e-Zaﬁ‘u — pair“, for all t < l/ﬁ. The minimum of the right side, say K (t), can be found by W) = e-Qﬂﬁwamu — ﬁt)“’“ + rem—2am - m)” = 0 which implies that (1 —ﬁt)‘1 — 2 = 0 and t =1/2ﬁ. That minimum is K(1/2ﬂ) = e"’(1 - (1/2))” = (2/6)"- 3.3.10 If r = 0, M(t) = 1 = em”, which is the mgf of a degenerate distribution at a: = 0. . 3.3.14 The differential equation requires log g(0,w) = —kw" + c. The boundary condition g(0,0) = 1 imlies that c = 0. Thus g(0,w) = exp{—kw"} and C(11)) = 1 — exp{—kw’} and G’(w) = krwr‘l exp{—kw"}, 0 < w < oo. 3.3.15 he joint pdf of X and the parameter is e‘mm“ ﬂﬂmMWQ = ﬂ mfm,\$=mLan0<m<a) 2 oo 1+1 —2m 2 3+2 P<x=o.1.2) = 2/ ﬂ+dm=sz+2>gL2>_ 1:0 0 11?- I=o 2:. 2 1 2 3 11 _ 2+2 _ _ _ _ = _ — §(m+1)(1/2) — 4+8+ 16 16. 3.3.16 C(21) = P(Y S y) = P(-2log X s y) = P(X 2 exp{—y/2}) 1 / (1)dm=1-,— exp{—y/2}, 0<y <00 exp(-y/2) ‘ G’(y) = (1/2) exp{*y/2}. 0 < y < 00; g(y) so Y is x2(2). 3.3.17 f(a:) = 1/(b —- a), a. < x < b, has respective mean and variance of ﬂzi=sand\$b+gﬁ=13 Solve for a, and b. Em P(a+mr(a+1>r(m _ a I‘(cx)l‘(ﬂ)l“(oz + t! +1) _ a + ﬂ“ E(X2) _ F(a + ﬁ)1‘(av+ 2)I‘(ﬁ) _ (a + 1):): ' ‘ l“(6!)1‘(ﬁ)1‘(01+:6+2)_(0t+ﬁ+1)(cv+ﬁ)' aﬂ “’2 “2)— WW = 3.3.20 3 1 = 6/ a:(3—a:)4d:1:.Letm=3y,—g§=3. 1 . c A (3y)(3 — 3y)43dy = 3%“?555); so c = 6- 5/36 = 10/35. 1 3.3.21 If a = [3, show that f + z) = f — 2:). 3.3.22 Note that k—l 77' 1» n—w 7"! — "— D‘[‘ = (11920”) “1‘” k' 100 22 Some Special Distributions 3.3.26 (a). Using the mean value theorem, we have P(a:sX<a:+A) = m 00A AP(X 2 27:) 1(3): lim A_.o m, Ado where 5 —» a: as A —) 0. Letting A —» 0, we then get the desired result. ((1) The pdf of X is mm) = exp {:0 — ebo} from which the desired result follows. I the integral for cl§(—z), let w = —v and it follows that ‘I>(—z) = 1 — @(z). 0.90 P(X'#<89?#) = a a~ P<X—p<94—p) ___ 0' 0 Thus 39—0—5 = 1.282 and 94—;5 = 1.645. Solve for p and a. 0.95. 3.4.5 2 Thus if c = 1/[x/2_1r‘/1/(2 log 2) , we would have 3 N(0, 1/(2 log 2)) distribu- lOIl. 62—12 = Ce—zglog 2 = cexP {_M}. E(IX -ul) 00 2/ (a: — ,u.) 1 «3'(:“‘“)2/""’2 dz # 27m 2 exp {—(rv — #)2/202}]: = mg- 3.4.8 /3 exp{—(x — 02/20/11)} dm 2 3 1 v-mr m %[¢(31—7§)[email protected](21+§)l= %[ Of course, X is N(3, 16). P [00004 < “€551,— < 3.84] and w is 98(1), so, the answer is 0.95 — 0.05 = 0.90. 1 2 exp{—(90 — 3)2/2(1/4)} dz <1>(—2)] . 23 3.4.13 P(1<X2<9) = p(—3<X< —1)+P(1<X<3) ~1 -1 —3 — 1 3 — 1 - H 2 >-¢( 2 )l+[¢<—2 imi- 3.4.15 I l I 2 I M(t) = 1+0+ Mg”? +0+ 4'“; )2't4 +~- t2 2 t2 2 2 = 1+1—/'+( 5') +--- =exp{t2/2}; so X is N(0,1). 3.4.20 '-' . 02132 (71,1330 [exp {M + — expW}, which is the mgf of a degenerate distribution at a: = p. ‘ 3.4.22 (1 / wen/F(b) dy = —f(b)/F(b)- —OO Multiply both sides by F(b) then differentiate both sides with respect to b. This yields, bf(b) = f’(b) and -—(b2/2) + c = log f(b). Thus 2 f(b) = ale—5 /2, which is the pdf of a N (0, 1) distribution. 3.4.25 Using W = Z11.E + @270 ~ 11-5). the independence of Z and I1_E, and 1&6 = 11-6, we get E(W) = 0(1 — e) + ac0[1 — (1 — 6)] = o Var(W) = E(W2) = 4221,24 + 2a6221,_,(1 — 11_£)+ 0322(1 — 11-32] = (l—e)+a§[l—(1—e)], . which is the desired. 3.4.26 If R or SPLUS is available, the code on page 168, i.e., (i-eps) *pnorm (w) +eps*pnorm (w/sigc) evaluates the contaminated normal cdf with parameters eps and sigc. Using R, the probability asked for in Part (d) is ...
View Full Document

• Fall '08
• Staff

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern