COURSE: DSCI 3710.002
Print Name:
Exam 1 – version A
Signature:
Summer 2008
Student ID#:
INSTRUCTIONS:

Please print your name and student ID number on this exam. Also, put your
signature on this exam.

On your scantron PRINT your name and exam version. To better protect your
privacy also print your name on the backside of your scantron.

You have 90 minutes to complete this exam. The exam is open book, open notes,
and open mind. You may use any type of hand calculator but please show all your
work on the exam and mark all answers on the scantron. Usage of cell phones,
digital cameras, PDAs, and other communication devices is strictly prohibited.

Many of the questions follow the format of those in Hawkes Learning Systems
Business Statistics. The remaining questions are either based on the Excel
assignments or use an HLSBS-like approach with problems nearly identical to
those assigned in the textbook.

Please DO NOT pull this exam apart. When you have completed the exam, please
turn your scantron and exam booklet into your instructor, at the front desk.

No cheating.

Good luck and we wish you well on the exam.
Note: Whenever question(s) are connected you may be asked to assume a result (given a
value) as an answer for the previous question but this result (value) may or may not be
correct. The procedure is set in place to prevent you from losing points on a subsequent
question because you made a mistake on some previous question/s.
1
Use the information given in the following paragraph to answer first five questions.
The City of Denton Municipal Laboratory routinely monitors chlorine (bleach) levels in drinking
water. Twice a month, the familiar white mini-van stops outside Denton houses and collects
water samples straight from the water main. To ensure bacteria and other microbes are killed,
the average desirable chlorine level in drinking water is 3.0 mg/liter. While there is some
acceptable fluctuation around this mean, if the chlorine level is significantly higher, the residents
will start complaining about chlorine taste in water. To test the claim that the automatic chlorine
dispenser is set too high, a water lab researcher measured the chlorine level in the latest 15
sampling bottles. Statistical analysis on the data using Excel is shown below.
t Test for Population Mean
Number of Observations
Sample Standard Deviation
Sample Mean
Ho:XXXXX
T*
P[T  T*]
T Critical,  = 0.01
15
1.297507
3.493333
Ha: XXXXX
XXXXX
0.081495
2.624494
1. What is the alternative hypothesis for testing the residents’ claim?
A. Ha:  > 3.0
B. Ha:   3.0
C. Ha:  > 3.0 *
D. Ha:  < 3.0
E. Ha:  < 3.0
2. What is the calculated test statistic to test the residents’ claim?
A. 1.47 *
B. 3.29
C. 2.62
D. 2.97
E. 0.08
3. What is the p-value of this test?
A. 1.47
B. 3.29
C. 2.62
D. 2.97
E. 0.08 *
2
4.
Suppose the calculated test statistic were 4.20. Which one of the following would best
describe the p-value for the test?
A. p > .1
B. .05 < p < .10
C. .025 < p < .05
D. .01 < p < .025
E. p < .01*
5.
Using the provided Excel output, what is the conclusion of the test, conducted at the 0.01
significance level, concerning the residents’ belief and the reason for the conclusion?
A. Conclude there is evidence the average chlorine level is more than 3.0mg/L because the
p-value is greater than the significance level.
B. Conclude there is insufficient evidence the average chlorine level is more than 3.0mg/L
because the p-value is greater than the significance level. *
C. Conclude there is evidence the average chlorine level is more than 3.0mg/L because the
p-value is smaller than the significance level.
D. Conclude there is insufficient evidence the average chlorine level is more than 3.0mg/L
because the p-value is smaller than the significance level.
E. Conclude there is evidence the average chlorine level is less than 3.0mg/L because the
test statistic is greater than the significance level.
3
Use the information given in the next paragraph to answer the next four questions.
In early 2006, Dallas City Council decided to approve the installation of red-light cameras.
Critical to this decision was the experience of Garland, the first city in Texas to use them since
2001 (Dallas Morning News, January 12, 2006). Garland had plainclothes officers recording (but
not ticketing) red-light violators in 9 main intersections during peak hours, before and after the
installation of red-light cameras. The results of the analysis at the 10% level is shown below.
t-Test: Paired Two Sample for Means
Intersection Before After
1
180
145
2
155
127
3
121
102
4
93
86
5
160
129
6
117
96
7
85
32
8
149
130
9
133
99
Mean
Variance
Observations
Pearson Correlation
Hypothesized Mean Difference
df
t Stat
P(T<=t) one-tail
t Critical one-tail
P(T<=t) two-tail
t Critical two-tail
Before
After
132.5555556 105.1111111
997.5277778 1137.611111
9
9
0.92188478
20
8
1.707733986
0.063033932
1.39681531
0.126067865
1.859548033
6. What is the table value (at the 10 % level) of the appropriate test statistic to test the belief that
there is a reduction of more than 20 violations in the average number of violations per
intersection if red-light cameras are installed?
A. 0.126
B. 1.71
C. 1.86
D. 0.063
E. 1.40*
7. What is the calculated value of the appropriate test statistic to test the belief that there is a
reduction of more than 20 violations in the average number of violations after the installation?
A. 0.126
B. 1.71*
C. 1.86
D. 0.063
E. 1.40
8. What is the p-value for testing the hypothesis that there is a reduction of more than 20
violations in the average number of violations after the installation?
A. 0.126
B. 1.71
C. 1.86
D. 0.063*
E. 1.40
9. What is the point estimate for the mean reduction (the number of violations avoided) of
violations after the installation of red-light cameras?
A. 132.55
B. 105.11
C. 27.44 *
D. 1137.61
E. 20
4
Use the following paragraph for the next four questions.
In response to the No Child Left Behind law, a recently published Academic Excellence Indicator
System (AEIS) report examined, among other issues, the Texas Assessment of Knowledge and
Skills (TAKS) test results during the 2005-06 school year. The state average for the TAKS-math
scores was 75 percent passing. Hoping to disprove parents' widespread claim that this year the
Tyler school district is doing worse than the state average, a high-school principal in Tyler, TX,
summarized her latest TAKS-math scores from the 11th grade. Out of 120 11th-graders, 85 got a
passing TAKS-math score. Is there evidence at the 5% level to support parents' claim?
10. What are the null and alternative hypotheses for this test?
A.
Ho: p = 0.75 Ha: p ≠ 0.75
B.
Ho:  > 0.75 Ha:  < 0.75
C.
Ho: p > 0.75 Ha: p < 0.75 *
D.
Ho: p > 0.05 Ha: p < 0.05
E.
Ho:  > 5
Ha:  < 5
11. What is the critical value of the test statistic?
A.
B.
C.
D.
E.
-2.33
1.645
-1.645 *
-1.28
2.33
12. What is the calculated (observed) value of the test statistic?
A.
B.
C.
D.
E.
-0.797
0.797
1.054
1.00
–1.054 *
13. Assume the calculated test statistic is –2.12. What conclusion can be drawn?
A. Reject Ha. There is evidence that supports parents' claim.
B. Reject Ho. There is evidence that supports parents' claim.*
C. Reject Ho. Parents' claim is not supported.
D. Fail to reject Ho. There is insufficient evidence to support parents' claim.
E. Fail to reject Ho. Parents' claim is supported.
5
Use the following information to answer the next four questions.
A recent survey asked 300 adults to see how many consider the practice of telemarketing
unacceptable. The responses are listed below:
Men
Women
Acceptable Unacceptable Total
35
130 165
50
85 135
Test the hypothesis that the proportions of men and women who find telemarketing unacceptable
are different. Consider the difference between the two proportions, pm - pw and use 0.10 as the
significance level.
14. What is the alternative hypothesis?
A. pm < pw
B. pm ≠ pw *
C. pm > pw
D. pm < pw
E. pm = pw
15. What is the mean proportion of customers that consider telemarketing unacceptable? (i.e., for
the combined sample.)
A. 0.7167 *
B. 0.2121
C. 0.7879
D. 0.6296
E. 0.3704
16. What is the absolute critical (Table) value of the test statistic?
A. 1.645 *
B. 1.96
C. 1.28
D. 2.33
E. 2.92
17. Assuming that the calculated value of the test statistic is +3.13, what is the p-value?
A. 0.9991
B. 0.0485
C. 0.4991
D. 0.0009
E. 0.0018 *
6
Use the information given in the paragraph below to answer the next eight questions.
February 14, 2006, marked the 60th anniversary of ENIAC, the first computer in the world. In a
Computerworld magazine interview, ENIAC’s inventor Pres Eckert explains how they chose the
right type of wires back in 1946: “We only used wire that passed the mouse test”. They threw a
number of wire samples in a cage full of hungry mice and let them eat the insulation, in order to
determine which insulation type mice liked the least. ANOVA results with amounts of
insulation (in mg) eaten by the mice are shown below. Test at the 0.05 level the claim that mice
have different preferences among insulation types.
Anova: Single Factor
SUMMARY
Groups
Insulation1
Insulation2
Insulation3
Count Sum Average Variance
10 436
43.6 75.1556
10 502
50.2 86.844
10 404
40.4 116.711
ANOVA
Source of Variation
Between Groups
Within Groups
SS
499.7
2508.4
Total
3007.9
df
MS
XX
XXXX
27 92.9037
F
P-value F crit
XXXX
XXXX 3.3541
29
TUKEY MULTIPLE COMPARISON TEST
Critical Q
Distance
Alpha
3.53
10.75947843
0.05
Means joined by a double line are not significantly different.
Insulation3
40.400001526
Insulation1
43.599998474
Insulation2
50.200000763
18. Which of the following is the correct null hypothesis?
A.
B.
C.
D.
E.
Ho: the mean amount of insulation eaten is the same for all three types. *
Ho: the mean amount of insulation eaten is not the same for all three types.
Ho: the mean amounts of insulation eaten are different for all three types.
Ho: the mean amount of insulation eaten is the same for types 1 and 2.
Ho: the mean amount of insulation eaten is the same for types 1 and 3.
7
19. Estimate the error variance for this ANOVA design.
A. 2508.4
B. 1627.4
C. 3726.3
D. 249.73
E. 92.90 *
20. What is the critical (table) value to test the null hypothesis?
A. 2.511
B. 10.4673
C. 0.00043
D. 3.354 *
E. 4.242
21. What is the calculated value of the test statistic to test the claim that there is a difference in
the mean amount of insulation eaten for the three types?
A. 2.511
B. 2.688 *
C. 0.00043
D. 3.354
E. 4.242
22. What degrees of freedom should be used to find the critical value of the test statistic?
A. 3
B. 2
C. 23
D. 2 and 27 *
E. 29
23. Which one of the following would best describe the p-value for the test?
A. p > .1
B. .05 < p < .10 *
C. .025 < p < .05
D. .01 < p < .025
E. p < .01
24. What are the statistical decision and reason for the decision concerning the null hypothesis?
A. Fail to reject Ho because the p-value of the test is larger than α. *
B. Reject Ho because the p-value of the test is larger than the F critical (table) value.
C. Reject Ho because the p-value of the test is larger than α.
D. Fail to reject Ho because the p-value of the test is smaller than α.
E. Reject Ho because the p-value of the test is smaller than α.
25. Which insulation type should be chosen for ENIAC’s wires?
A. Type 1
B. Type 2
C. Type 3
D. It doesn’t matter because they are all different
E. It doesn’t matter because they are all essentially the same*
8
Use the information given in the paragraph below to answer the next two questions.
Hourly wages in the gaming industry that included casinos etc. are known to be normally
distributed with a hypothesized mean of $18 and a historically known (i.e. population) standard
deviation of $5. A random sample of 20 workers from a specific casino was collected. The
sample average hourly wage in this casino was $16. Using this sample, we wish to test whether a
peer group’s accusation of gaming industry wages being lower than hypothesized, is in order?
26. What is the alternative hypothesis for this test?
A. Ha:   18
B. Ha:  > 18
C. Ha:   16
D. Ha:  < 16
E. Ha:  < 18*
27. What is the appropriate test statistic to use here?
A. F
B. t
C. Z*
D. None of these.
E. Any of a. through c.
Use the information given below to answer the next three questions.
A study is designed to determine the effect of an office-training course on typing productivity.
Ten typists who have not taken the course are randomly selected and are asked to type 15 pages
of text. Then ten typists who have completed the course are selected independently of the first
sample and are given the same typing assignment. The productivity of each is measured by the
number of errors made and the data from the two samples are analyzed using Excel, assuming
equal population variances and α = .05.
t-Test: Two-Sample Assuming Equal Variances
Mean
Variance
Observations
Pooled Variance
Hypothesized Mean Difference
df
t Stat
P(T<=t) one-tail
t Critical one-tail
P(T<=t) two-tail
t Critical two-tail
No Course
33.4
57.1556
10
43.5556
0
18
0.8809
0.1950
1.7341
0.3900
xxxxxx
9
Course
30.8
29.9556
10
28. To construct a 90% confidence interval for the difference in the mean number of errors
between typists who did not take the training course and those who completed the course, the
absolute table value needed is
A.
0.881
B.
0.195
C.
1.734*
D.
0.390
E.
2.101
29. The 98% confidence interval for the difference in the mean number of errors between typists
who did not take the training course and those who completed the course is
A.
-1.600 to 7.400
B.
-3.601 to 8.801
C.
-2.185 to 7.985
D.
-4.941 to 10.141*
E.
-1.339 to 4.628
30. Assuming the calculated value of the test statistic is 3.3 and the hypothesis test for
ascertaining if there is a difference in the mean number of errors between typists who did not
take the training course and those who completed the course is conducted at the 5%
significance level, what should be the conclusion?
A.
There is evidence of a difference in the mean number of errors between typists who did
not take the training course and those who completed the course because the absolute
value of the test statistic (calculated) is larger than the table (critical) value.*
B.
There is insufficient evidence of a difference in the mean number of errors between
typists who did not take the training course and those who completed the course because
the absolute value of the test statistic (calculated) is larger than the table (critical) value.
C.
There is evidence of a difference in the mean number of errors between typists who did
not take the training course and those who completed the course because the absolute
value of the test statistic (calculated) is smaller than the table (critical) value.
D.
There is insufficient evidence of a difference in the mean number of errors between
typists who did not take the training course and those who completed the course because
the absolute value of the test statistic (calculated) is smaller than the table (critical) value.
E.
There is overwhelming evidence that the mean number of errors between typists who did
not take the training course and those who completed the course is the same because the
absolute value of the test statistic (calculated) is equal to the table (critical) value.
Thank you
10