Students at a local high school were randomly selected to participate in a math fluency program. The program is designed to increase their math fluency. A total of 12 students each took a pretest before the program and posttest after the program. The mean of the differences in the posttest and pretest scores is 13. The administration decided that all students in the school would participate in the program next school year. Let D denote the mean difference in the student scores. The 95 percent confidence interval estimate of the mean difference for all students is (8, 18). What is an appropriate interpretation of the confidence interval?

	For any D, the sample result is quite likely.
	For any D with 8 < D < 18, the sample result is quite likely.
	D is positive, with a probability of 0.95.
	D is negative, with a probability of 0.95.
	D is between 8 and 18.

2.

Neck size, in inches, and number of teeth of 18 randomly selected puppies are compared. Which significance test should be used to see if neck size and number of teeth have a linear relationship? Assume all test conditions are met.

	Two-sample z-test
	Two-sample t-test
	Two-proportion z-test
	t-test for slope of regression line
	One-proportion z-test

3.

Sophia, a yoga instructor at Yoga for You, selected random samples of 210 students from a nearby high school and 210 students from a nearby college to compare levels of physical fitness. The mean and standard deviation of the fitness levels of the high school students were 82 and 14 respectively. The mean and standard deviation of the fitness levels of the college students were 86 and 17 respectively. She conducted a two-sided t-test with a resulting t-value of 2.63. If = 0.05, what is an appropriate conclusion from this study?

	Because the sample means only differ by four, the population means are not significantly different.
	Because the second group has a larger standard deviation, their mean fitness score is significantly higher.
	Because the second group has a larger standard deviation, the mean fitness score of the first group is significantly higher.
	Because the p-value is greater than = 0.05, the mean fitness scores for the two groups of students are not significantly different.
	Because the p-value is less than = 0.05, the mean fitness scores for the two groups of students are significantly different.

4.

Amara was working on a report on Greek and Egyptian mathematicians. She decided to find a 98 percent confidence interval for the difference in mean age at the time of significant mathematics discoveries for Greek versus Egyptian mathematicians. She found the ages at the time of math discovery of all the members of both groups and found the 98 percent confidence interval based on a t-distribution using a calculator. The procedure she used is not appropriate in this context because

	The sample sizes for the two groups are not equal.
	Age at the time of math discovery occurs at different intervals in the two countries, so the distribution of ages cannot be the same.
	Ages at the time of math discovery are likely to be skewed rather than bell shaped, so the assumptions for using this confidence interval formula are not valid.
	Age at the time of math discovery is likely to have a few large outliers, so the assumption for using this confidence interval formula is not valid.
	The entire population is measured in both cases, so the actual difference in means can be computed and a confidence interval should not be used.

5.

Deja is conducting a test on viruses on oak leaves. She uses 8 leaves to compare two strains of a virus. She applies one strain to the left side of the leaf and one strain to the right side. She flips a coin to decide which strain goes on the right side of the leaf. The virus abrasions that appear on each side are counted and she records them in a table.

Leaf	Number of Abrasions for Strain 1	Number of Abrasions for Strain 2
1	29	21
2	25	19
3	17	17
4	14	16
5	15	12
6	11	9
7	8	7
8	7	4

If Deja is to perform an appropriate t-test to determine if there is a mean difference between the number of abrasions per leaf produced by the two strains, how many degrees of freedom should she use? (4 points)

	7
	8
	9
	14
	16

6.

A t statistic was used to conduct a test of the null hypothesis H₀: = 7 against the alternative H_a: 7, with a p-value equal to 0.034. A two-sided confidence interval for is to be considered. Of the following, which is the largest level of confidence for which the confidence interval will NOT contain 7?

	A 90% confidence level
	A 93% confidence level
	A 95% confidence level
	A 97% confidence level
	A 99% confidence level

7.

Fluoxetine, a generic anti-depressant, claims to have, on average, at least 20 milligrams of active ingredient. An independent lab tests a random sample of 80 tablets and finds the mean content of active ingredient in this sample is 18.7 milligrams with a standard deviation of 5 milligrams. If the lab doesn't believe the manufacturer's claim, what is the approximate p-value for the suitable test?

	0.0226
	0.4885
	0.5115
	0.15
	0.0113

8.

A regression line is used to satisfactorily describe the relationship between amount of hair per square inch and drying time (in minutes) of 17 participants in a hair dryer performance study. The regression analysis is shown.

Variable	Coeff	SE Coeff	t Ratio	p-Value
Constant	3.2893	0.0217	151.58	0.0001
Amount of hair	1.2874	0.1635	7.87	0.0001
R squared = 88.5%	R squared (adj) = 87.9%

Which expression should be used to compute a 90 percent confidence interval for the slope of the regression line?

	1.2874 1.74(0.1635)
	1.2874 1.746(0.1635)
	1.2874 1.753(0.1635)
	3.2893 1.753(0.0217)
	3.2893 1.746(0.0217)

9.

The mean family income for a random sample of 600 suburban households in Loganville shows that a 95 percent confidence interval is ($43,100, $59,710). Alma is conducting a test of the null hypothesis H₀: = 42,000 against the alternative hypothesis H_a: 42,000 at the = 0.05 level of significance. Does Alma have enough information to conduct a test of the null hypothesis against the alternative?

	No, because the value of is not known
	No, because it is not known whether the data are Normally distributed
	No, because the entire data set is needed to do this test
	Yes, because $42,000 is not contained in the 95% confidence interval, the null hypothesis would not be rejected, and it could be concluded that the mean family income is not significantly different from $42,000 at the = 0.05 level
	Yes, because $42,000 is not contained in the 95% confidence interval, the null hypothesis would be rejected in favor of the alternative, and it could be concluded that the mean family income is significantly different from $42,000 at the = 0.05 level

10.

Thirty mechanics in an automotive shop are randomly selected to participate in a study comparing two oil changing techniques. They are randomly assigned one of the two techniques. The manager trains 15 mechanics on one technique and trains the other 15 mechanics on the second technique. He then records the number of oil changes each mechanic does in one week. Which inferential statistical test would be most appropriate for this scenario?

	A one-sample z-test
	A two-sample t-test
	A paired t-test
	A chi-square goodness-of-fit test
	A one-sample t-test

11.

Which of the following statements would be appropriate to investigate a claim that the mean speed of drivers through town exceeds the posted limit of 30 miles per hour?

	The null hypothesis states the mean speed of drivers in this town is less than 30 miles per hour.
	The null hypothesis states the mean speed of drivers in this town is greater than 30 miles per hour.
	The alternative hypothesis states the mean speed of drivers in this town is greater than 30 miles per hour.
	The alternative hypothesis states the mean speed of drivers in this town is less than 30 miles per hour.
	The alternative hypothesis states the mean speed of drivers in this town is less than or equal to 30 miles per hour.

12.

Buyers are skeptical of a speed boat advertisement that claims the newest model gets an average of 24 miles per gallon. They believe the dealer is overstating the average. Which null and alternative hypotheses should the buyers test? Let represent the true average gas mileage.

	H0: < 24 miles per gallon, Ha: 24 miles per gallon
	H0: 24 miles per gallon, Ha: > 24 miles per gallon
	H0: = 24 miles per gallon, Ha: > 24 miles per gallon
	H0: = 24 miles per gallon, Ha: < 24 miles per gallon
	H0: = 24 miles per gallon, Ha: 24 miles per gallon