course4solutions_1102

# course4solutions_1102 - November 2002 Course 4 solutions...

This preview shows pages 1–5. Sign up to view the full content.

November 2002 Course 4 solutions Question # 1 Answer: B ρ φ ρφ 1 1 2 22 1 2 2 1 05 1 02 = = =+ =− . . Solving simultaneously gives: 1 2 08 06 = . . Question # 2 Answer: C [12(.45)] [5.4] 5; 5.4 5 0.4. gh == = = = .45 (5) (6) ˆ .6 .4 .6(360) .4(420) 384. xx π =+= + = Question # 3 Answer: D N is distributed Poisson ( λ ) ( ) 1(1.2) 1.2. E µ λα θ = = ( ) 1.2; ( ) 1.44. vE aV a r λλ α = = = = 1.2 5 2 12 ;. 1.44 6 2 5/ 6 17 kZ = = + Thus, the estimate for Year 3 is 12 5 (1.5) (1.2) 1.41. 17 17 += Note that a Bayesian approach produces the same answer.

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

View Full Document
Question # 4 Answer: C At the time of the second failure, 11 23 ˆ ( ) 12. 1 132 H tn nn = + = ⇒= - At the time of the fourth failure, 11 11 ˆ ( ) .3854. 1 2 1 1 1 09 Ht =++ += Question # 5 Answer: E 2 2 22 2 42 ˆ 2.06 5 .9841. 182 i i x R y b = == Question # 6 Answer: B The likelihood is: ( 1 ) ( 1) ( 1). !( j jj j x x rx j j r r L x b bb b -- + + +- = ∝+ + ∏∏ L The loglikelihood is: 1 1 l n ( )ln( 0 1 0 ( 1 ) () ˆ 0 ; /. n j n j j l x x rx l x r x x rn n x r n xr b = =  = - ++  + =-=  + = + - + =- = -= ∑∑
Question # 7 Answer: C The Bühlmann credibility estimate is (1 ) Z xZ µ + where x is the first observation. The Bühlmann estimate is the least squares approximation to the Bayesian estimate. Therefore, Z and must be selected to minimize 22 2 11 1 [( 1)1 . 5 ] [ 2( . 5 ] [ 3( 1)3 ] . 33 3 ZZ µµµ +− + + Setting partial derivatives equal to zero will give the values. However, it should be clear that is the average of the Bayesian estimates, that is, 1 (1.5 1.5 3) 2. 3 =+ + = The derivative with respect to Z is (deleting the coefficients of 1/3): 2( .5)( 1) 2(.5)(0) 2( 1)(1) 0 .75. Z −+ −+ + = = The answer is .75(1) .25(2) 1.25. += Question # 8 Answer: E The confidence interval is 1/ 00 ˆˆ (() ,()) . St θθ Taking logarithms of both endpoints gives the two equations 0 0 1 ˆ ln.695 .36384 ln ( ) ˆ ln.843 .17079 ln ( ). θ =− = = Multiplying the two equations gives 2 0 0 0 ˆ .06214 [ln ( )] ˆ ln ( ) .24928 ˆ ( ) .77936. = = The negative square root is required in order to make the answer fall in the interval (0,1).

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

View Full Document
Question # 9 Answer: E Because k k ρ φ = there are a number of ways to get the value of . 1/2 1/3 .1 .215 .46368; ( .1) .46416; .46512. .215 φφ == = = = = Also, because the mean is zero, δ must be zero. Then (using the first choice for ), 1 ˆ .46368( .431) 0 .1998. T y + =− + = Question # 10 Answer: B The likelihood is: 111 33 1 150 150 150 (150 225) (150 525) (150 950) 150 . (375 675 1100) L ααα α +++ + = = ii The loglikelihood is: 3ln 3 ln150 ( 1)ln(375 675 1100) 3ln150 ln(375 675 1100) 4.4128 ˆ 3/ 4.4128 .6798. l l αα =+ + Question # 11 Answer: D For this problem, r = 4 and n = 7. Then, 33.60 ˆ 1.4 4(7 1) v and 3.3 1.4 ˆ .9.
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 03/27/2012 for the course MATHEMATIC 4523 taught by Professor Zhangqiang during the Spring '12 term at City University of Hong Kong.

### Page1 / 14

course4solutions_1102 - November 2002 Course 4 solutions...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online