Upload
raminshamshiri
View
458
Download
0
Embed Size (px)
DESCRIPTION
STA5328_Ramin_Shamshiri_HW3
Citation preview
Page 1 of 6
Ramin Shamshiri STA 5328, HW #3 Due 07/20/09
STA 5328, Homework #3
Due July 20, 2009
Ramin Shamshiri
UFID # 90213353 Note: Problem numbers are according to the 6
th text edition.
8.2. Suppose that πΈ π 1 = πΈ π 2 = π,π π 1 = π12, and π π 2 = π2
2 .
Consider the estimator π 3 = ππ 1 + 1 β π π 2.
a. Show that π 3is an unbiased estimator for π.
b. If π 1 and π 2 are independent, how should the constant a be chosen in order to minimize the variance of
π 3?
Solution a:
π is an unbiased estimator if πΈ(π ) = π. Here we have
πΈ(π 3) = πΈ[ππ 1 + 1β π π 2]
= ππΈ(π 1) + 1β π πΈ(π 2)
= ππ + 1 β π π
= ππ½+ π½β ππ½ = π½
β
Solution b:
Recall that:
π ππ + ππ = π2π π + π2π(π)
Therefore,
π π 3 = π ππ 1 + 1β π π 2
= π2π π 1 + 1 β π 2π(π 2)
π π 3 = π2π12 + 1β π 2π2
2
In order to find the minimum value of π π 3 for a critical point a, we should set the first derivative of π π 3 with respect to a equal to zero to find a.
ππ(π 3)
ππ= 0
2ππ12 β 2 1β π π2
2 = 0
ππ12 β π2
2 + ππ22 = 0
π π12 + π2
2 = π22
π =πππ
πππ+ππ
π
In order to check that the value of a will minimize π π 3 , we can either substitute a in π π 3 or we can use the
second derivative test.
π2π(π 3)
ππ2= 2ππ1
2 + 2ππ22 β₯ 0
Using the second derivative test, it is confirmed that π =πππ
πππ+ππ
π
β
Page 2 of 6
Ramin Shamshiri STA 5328, HW #3 Due 07/20/09
8.13. If Y has a binomial distribution with parameters n and p, then π 1 = π/π is an unbiased estimator of p.
Another estimator of p is π 2 = (π + 1)/(π + 2).
a. Derive the bias of π 2.
b. Derive πππΈ(π 1) πππ πππΈ(π 2).
c. For what values of p is πππΈ(π 1) < πππΈ(π 2)?
Solution a:
The bias of a point estimator π is given by π΅ π = πΈ π β π
Therefore, π΅ π 2 = πΈ π 2 β π
= πΈ π + 1
π + 2 β π =
1
π + 2πΈ π + 1 β π
=1
π + 2πΈ π +
1
π + 2πΈ 1 β π
=ππ
π + 2+
1
π + 2β π =
ππ + 1 β π(π + 2)
π + 2=π β ππ
π+ π
β
Solution b:
πππΈ(π 1) = π π 1 + π΅ π 1 2
π π 1 =π(1 β π)
π , π΅ π 1 = 0
Therefore: π΄πΊπ¬(π π) = π½ π π =π(πβπ)
π
πππΈ(π 2) = π π 2 + π΅ π 2 2
π π 2 = π π+1
π+2 , Recall that: π ππ + ππ = π2π π + π2π(π)
π π 2 =1
π + 2 2π π +
1
π + 2 2π 1 =
1
π + 2 2π π + 0 =
ππ(1β π)
π + 2 2
π π 2 =ππ 1β π
π + 2 2 πππ π΅ π 2
2 = 1 β 2π
π + 2
2
πππΈ(π 2) =ππ 1βπ
π+ 2 2 +
1 β 2π
π + 2
2
=ππ π β π + π β ππ π
π+ π π
β
Solution c:
π(1 β π)
π<ππ 1 β π + 1 β 2π 2
π + 2 2
π + 2 2π 1 β π β π2π 1β π β π 1 β π2 < 0
π + 2 2 β π π 1 β π β π 1 β 2π 2 < 0
4ππ β 4ππ2 + 4π β 4π2 β π + 4ππ β 4ππ2 < 0
π2 8π + 4 β π 4 + 8π + π > 0
β= π2 β 4ππ = 4 + 8π 2 β 4 8π + 4 π
π1,π2 = 4 + 8π Β± 4 + 8π 2 β 4 8π + 4 π
2 8π + 4 =
1
2Β±
[ 4 + 8π 2 β 4 8π + 4 π]
4 8π + 4 2 =
π
πΒ±
π + π
ππ + π
Therefore π βπ
π
β
Page 3 of 6
Ramin Shamshiri STA 5328, HW #3 Due 07/20/09
8.24. In a study of the relationship between birth order and college success, an investigator found that 126 in a
sample of 180 college graduates were first born or only children; in a sample of 100 nongraduates of comparable age and socioeconomic background, the number of firstborn or only children was 54. Estimate the
difference in the proportions of first-born or only children for the two populations from which these samples
were drawn. Give a bound for the error of estimation.
Solution:
π1 = 180, π1 = 126
π2 = 100, π2 = 54
π 1 β π 2 =?
π 1 =π1
π1=
126
180= 0.7
π 2 =π2
π2=
54
100= 0.54
Estimating the difference in the proportions:
π 1 β π 2 = 0.7β 54 = π.ππ
The bound error estimation using probability of 95%:
2ππ 1βπ 2 = 2 π1(1β π1)
π1+π2(1β π2)
π2= 2
0.7(0.3)
180+
0.54(0.44)
10= 2 0.6042 = π.πππππ
β
Page 4 of 6
Ramin Shamshiri STA 5328, HW #3 Due 07/20/09
8.76. Do SAT scores for high school students fifer depending on the studentβs intended field of study? Fifteen
students who intended to major in engineering were compared with 15 students who intended to major language and literature. Given in the accompanying table are the means and standard deviations of the scores on the
verbal and mathematics portion of the SAT for the two groups of students.
Verbal Math
Engineering π¦ = 446 s=42 π¦ = 548 s=57
Language/Literature π¦ = 534 s=45 π¦ = 517 s=52
a. Construct a 95% confidence interval for the difference in average verbal scores of students majoring in engineering and of those majoring in language/literature.
b. Construct a 95% confidence interval for the difference in average math scores of students majoring in
engineering and of those majoring in language/literature. c. Interpret the results obtained in (a) and (b).
d. What assumptions are necessary for the methods used previously to be valid?
Solution a:
π1 = 15 and π2 = 15, π 1 = 42 and π 2 = 45, π 1 = 446 and π 2 = 534
π π = π1 β 1 π 1
2 + π2 β 1 π 22
π1 + π2 β 2 =
14 42 2 + 14 45 2
28 = 43.525
95% confidence interval, (using t-table to find π‘(0.025 ,ππ=28))
π 1 β π 2 Β± π‘(πΌ/2,ππ=28)π π 1
π1+
1
π2 = 446 β 534 Β± 2.048 43.525
1
15+
1
15= βππΒ± ππ.ππ
= [βπππ.ππ,βππ.ππ] Solution b:
π1 = 15 and π2 = 15, π 1 = 57 and π 2 = 52, π 1 = 548 and π 2 = 517
π π = π1 β 1 π 1
2 + π2 β 1 π 22
π1 + π2 β 2 =
14 57 2 + 14 52 2
28 = 54.557
95% confidence interval, (using t-table to find π‘(0.025 ,ππ=28))
π 1 β π 2 Β± π‘(πΌ/2,ππ=28)π π 1
π1+
1
π2= 548 β 517 Β± 2.048 54.557
1
15+
1
15= ππΒ± ππ.πππ
= [βπ.πππ,ππ.πππ] Solution c: It means that we are 95% confidence that the difference in average verbal scores of students
majoring in engineering and of those majoring in language/literature is in the interval = β120.54,β55.46 . Since this interval contains only negative values, we can claim that it appears to be difference in the two mean verbal scores achieved by engineering and language students.
Since the seconds interval, = [β9.797,71.797], contains both positive and negative values, we cannot claim
that there is difference in average math scores of engineering students and language students. In the other
words, we do not have 95% confidence to claim which group has a larger mean.
Solution d:
Samples are independent
Equal variance assumption (π12 = π2
2)
Page 5 of 6
Ramin Shamshiri STA 5328, HW #3 Due 07/20/09
8.79. A factory operates with two machines of type A and one machine of type B. The weekly repair costs X for
type A machine are normally distributed with mean π1 and variance π2. The weekly repair costs Y for machines
of type B are also normally distributed but with mean π2 and variance 3π2. The expected repair cost per week
for the factory is thus 2π1 + π2. If you are given a random sample X1,X2,β¦,Xn on costs of type A machines and
an independent random sample Y1, Y2, β¦,Ym on costs for type B machines, show how you would construct a
95% confidence interval for 2π1 + π2:
a. If π2 is known.
b. If π2 is not known.
Solution a:
Let π = 2π1 + π2 and π = 2π + π The 95% Confidence interval for π = 2π1 + π2 is:
π β ππΌ2
. (ππ ) < π < π + ππΌ2
. (ππ )
Where ππ = π(2π +π ) = 4ππ + ππ = 4π2
π+
3π2
π and ππΌ
2= π0.25 = 1.96. Therefore:
2π + π β 1.96. 4π2
π+
3π2
π < π < (2π + π ) + 1.96. (
4π2
π+
3π2
π)
ππΏ + π β π.πππ π
π+π
π< πππ + ππ < (2πΏ + π ) + π.πππ
π
π+π
π
β
Solution b:
When π2 is not known, we should use pooled variance and t-distribution.
Pooled variance, ππ is calculated as follow:
ππ = π β 1 π 1
2 + π β 1 π 22
π + πβ 2
(2π + π ) Β± π‘πΌ/2. ππ 4
π+
3
π
In order to make an inference about the population variance π2 based on a random sample Y1, Y2, β¦,Ym from a
normal population, a good estimator of π2 is the sample variance.
π12 =
1
π β 1 ππ β π
2
π
π=1
π22 =
1πβ 1
ππ β π 2π
π=1
3
ππ2 =
ππ β π 2π
π=1 + ππ β π
2ππ=1
3π + πβ 2
ππΏ + π Β± π.ππ πΏπ βπΏ π
ππ=π +
ππ β π πππ=π
ππ +πβπ
π
π+π
π
β
Page 6 of 6
Ramin Shamshiri STA 5328, HW #3 Due 07/20/09
6. Suppose on the average I will receive one phone call per evening. Show that under reasonable assumptions
that the probability y that I will receive exact one phone call tonight is e-1
Solution