In: Statistics and Probability
There are 1254 machinery rebuilding and repairing companies in the United States. A tool manufacturer wishes to survey a simple random sample of these firms to find out what proportion of them are interested in a new tool design. Assume that we’re dealing with a finite population in the following sub-questions.
(a) If the tool manufacturer would like to be 95% confident that the sample proportion is within 0.01 of the actual population proportion, how many machinery rebuilding and repairing companies should be included in the sample (Hint: use the conservative value of p for when p is not given)?
b) Suppose the tool manufacturer has carried out the study, using the sample size determined in part (a), and 39.0% of the machinery rebuilding and repairing companies are interested in the new tool design. Which of the following 95% confidence interval for the population percentage? Show work.
A. CI = (0.3710, 0.4091)
B. CI = (0.3613, 0.4187)
C. CI = (0.3572, 0.4228)
D. CI = (0.3338, 0.4462)
(c)Which of the following is the best interpretation of the confidence interval from the previous part?
A. After performing a large number of samples, we expect to arrive at the same confidence interval as above 95% of the time.
B. We are 95% confident that the unknown population parameter, π, falls in this interval.
C. 95% of all the data values in the population fall within the interval.
D. There is a 5% margin of error in our statistical analysis.
a)
without prior estimate, let sample proportion
, p̂ = 0.5
sampling error , E =
0.01
Confidence Level , CL=
0.95
alpha = 1-CL =
0.05
Z value = Zα/2 =
1.960 [excel formula =normsinv(α/2)]
Sample Size,n = p̂ * (1-p̂) /((E / Z)² +
p̂(1-p̂)/N) = 0.50 * ( 1 - 0.50
)/((0.01/1.96)²+0.5*0.5/1254) ≈1109.17
so,Sample Size required=
1110
b)
Level of Significance, α =
0.05
Sample Size, n = 1110
Sample Proportion , p̂ = 0.3900
z -value = Zα/2 = 1.960 [excel
formula =NORMSINV(α/2)]
Standard Error , SE = √[p̂(1-p̂)/n] =
0.0146
margin of error , E = Z*SE = 1.960
* 0.0146 = 0.0287
95% Confidence Interval is
Interval Lower Limit = p̂ - E = 0.390
- 0.0287 = 0.361
Interval Upper Limit = p̂ + E = 0.390
+ 0.0287 = 0.419
95% confidence interval is (
0.3613 < p < 0.4187
)
c)
B. We are 95% confident that the unknown population parameter, π, falls in this interval.