This preview shows pages 1–3. Sign up to view the full content.
ADM 2304 Midterm
Winter 2009
Question 1 [7 marks]
The number of withdrawals at a bank machine was monitored during randomly chosen 10
minute intervals over the past month.
Appendix A gives the data distribution and
various analyses.
a.
Suppose you were to test whether the average number of withdrawals
exceeded 3.
Identify the most appropriate test, and explain briefly.
[1]
The boxplot shows a reasonably symmetric distribution with no outliers.
It is reasonable to assume a normal distribution for the pop. Data.
b.
Perform the hypothesis test that you selected above.
[3]
Ho: mu = 3; Ha: mu > 3;
T = (3.76 – 3 ) / (1.73877/sqrt(25)) = .76/.34775 =
2.185
Based on 24 d.f. the critical value is 1.71.
Since 2.185 > 1.71, we reject Ho at the .05 level
Conclude the average number of withdrawals exceeds 3.
c.
What is the pvalue of the test statistic.
[1]
Based on 24 d.f. the pvalue is between .025 and .01.
d.
Suppose you wanted to estimate the average number of withdrawals with a
margin of error of ±.5 and a 95% confidence level.
What sample size
would be required?
n = (1.96*1.73877/ .5)^2 = 47 (rounded up)
[2]
Question 2 [ 7 marks ]
An undercover investigative team decides to determine whether it costs more to have a
moderately damaged car repaired at
Jo’s Trusty Mechanic shop
or
Uncle Bob’s Honest
Mechanics
.
a)
Design an experiment and an appropriate hypothesis test that would
best
help
answer this question.
You may assume that the cost for fixing moderately
damaged cars is normally distributed.
Note that there are at least two types of
experiments that would work here but one is clearly better than the other.
Justify
your choice.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentADM 2304 Midterm
Winter 2009
[2]
Define moderately damaged more specifically to be a range of repair costs.
Collect a random sample of such cars and get an estimate both from Jo’s and
This is the end of the preview. Sign up
to
access the rest of the document.
 Spring '09
 na

Click to edit the document details