20.01.2015 Views

1Final Exam Review

1Final Exam Review

1Final Exam Review

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

AP Statistics Final <strong>Exam</strong> <strong>Review</strong><br />

I. Multiple Choice<br />

1. You have sampled 25 students to find the mean SAT scores at Morris Knolls High School.<br />

A 95% confidence interval for the mean SAT score is 900 to 1100. Which of the following<br />

statements gives a valid interpretation of this interval<br />

A) 95% of the 25 students have a mean score between 900 and 1100<br />

B) 95% of the population of all students at Morris Knolls have a score between 900 and<br />

1100<br />

C) If this procedure were repeated many times, 95% of the resulting confidence intervals<br />

would contain the true mean SAT score at Morris Knolls<br />

D) If this procedure were repeated many times, 95% of the sample means would be<br />

between 900 and 1100<br />

E) If 100 samples were taken and a 95% confidence interval was computed, 5 of them<br />

would be in the interval from 900 to 1100<br />

2. According to a poll, approximately 30% of Americans spent over $750 on holiday presents<br />

in 1998. Suppose you took a random sample of 85 shoppers and found that 23 spent over<br />

$750 on holiday presents in 1999. What test statistic would you use to conduct a hypothesis<br />

test to see if the percentage of people spending more than $750 on holiday presents has<br />

decreased<br />

A)<br />

23<br />

85<br />

!.3<br />

(.3)(.7)<br />

85<br />

B)<br />

.3<br />

(.3)(.7)<br />

85<br />

C) z -<br />

pˆ<br />

n<br />

D)<br />

23<br />

85<br />

!<br />

(<br />

23<br />

85<br />

)(<br />

85<br />

.3<br />

62<br />

85<br />

)<br />

E)<br />

23<br />

85<br />

( 23 62<br />

85)(<br />

85)<br />

85<br />

3. A sampling distribution (n=20) of the number of penalties served last season by members of<br />

the Hitemhard hockey team has a mean of 2,000 with a standard error of 53. What is the<br />

probability of obtaining a sample mean that is less than 145<br />

A) 0.1551<br />

B) 0<br />

C) 1.557<br />

D) 0.1557<br />

E) 0.005<br />

1final exam review.doc p. 1


4. A large sample hypothesis test with σ known, a null hypothesis of µ = 15, and an alternative<br />

hypothesis of µ ≠ 15 results in the test statistic value of z = 1.37. Assuming σ is known, the<br />

corresponding P-value is approximately<br />

A) 0.0853 B) 0.1707 C) 0.4147 D) 0.8293 E) 0.9147<br />

5. The level of significance is always<br />

A) the maximum allowable probability of Type II error<br />

B) the maximum allowable probability of Type I error<br />

C) the same as the confidence<br />

D) the same as the P-value<br />

E) 1 – P(type II error)<br />

6. Which of the following is (are) true<br />

I. If the sample size is constant, then reducing the probability of Type I error will reduce<br />

the probability of Type II error<br />

II. Increased power can be achieved by reducing the type II error<br />

III. If the P-value of a test is 0.015, the probability that the null hypothesis is true is 0.015<br />

A) I only<br />

B) II only<br />

C) I and III only<br />

D) II and III only<br />

E) I, II, and III<br />

7. At a certain high school a simple random sample was taken asking fifty-two 11 th and 12 th<br />

graders their political affiliation. The following two-way table was established. If a χ 2 test<br />

of independence were performed on these data, what would be the corresponding degrees of<br />

freedom<br />

11 th Grade 12th Grade<br />

Republican 11 5<br />

Democrat 10 15<br />

Independent 5 6<br />

A) 1 B) 2 C) 3 D) 6 E) 25<br />

1final exam review.doc p. 2


8. Failing to reject a null hypothesis that is false can be characterized as<br />

A) a Type I error<br />

B) a Type II error<br />

C) both a Type I and a Type II error<br />

D) a standard error of the mean<br />

E) no error<br />

9. If a 95% confidence interval is given by (86.52, 89.48), which of the following could be a<br />

99% confidence interval for the same data<br />

I. (86.98, 89.02)<br />

II. (86.37, 89.63)<br />

III. (87, 89)<br />

A) I only<br />

B) II only<br />

C) III only<br />

D) I and III<br />

E) II and III<br />

10. In constructing a confidence interval based on a large sample to estimate the mean µ of a<br />

population with known standard deviation σ, which of the following does NOT affect the<br />

width of the confidence interval<br />

A) the sample mean<br />

B) the population standard deviation<br />

C) the confidence level<br />

D) the sample size<br />

E) the population mean<br />

11. Which of the following accurately describes the power of a statistical test of a hypothesis<br />

A) It is equal to the P-value<br />

B) It is equal to 1 – (P-value)<br />

C) It is equal to α, the significance level<br />

D) It is the probability that a test using a fixed value of α will reject H0 when a particular<br />

alternative value of the parameter is true<br />

E) It is equal to β<br />

1final exam review.doc p. 3


12. An inspector inspects large truckloads of potatoes to determine the proportion p in the<br />

shipment with major defects prior to using the potatoes to make potato chips. Unless there is<br />

clear evidence that this proportion is less than 0.10, she will reject the shipment. To reach a<br />

decision she will test the hypotheses<br />

H 0 : p = 0.10, H a : p < 0.10<br />

using the large sample test for a population proportion. To do so, she selects an SRS of fifty<br />

potatoes from the over 2000 potatoes on the truck. Suppose that only two of the potatoes<br />

sampled are found to have major defects.<br />

The P-value of her test is<br />

A) 0.4207. B) 0.0786. C) 0.0154. D) less than 0.0002.<br />

13. A tire manufacturer claims that it has developed a new all-season radial tire for passenger<br />

cars (excluding SUVs) which has a shorter skid distance than the known mean skid distance,<br />

140 feet, for all tires currently available. A consumer group wishes to test this claim. If µ<br />

represents the true mean skid distance for this new tire, which of the following states the null<br />

hypothesis and alternative hypothesis that the consumer group should test<br />

A) H 0 : µ < 140 ft. H a : µ ≥ 140 ft.<br />

B) H 0 : µ ≤ 140 ft. H a : µ > 140 ft.<br />

C) H 0 : µ = 140 ft. H a : µ < 140 ft.<br />

D) H 0 : µ = 140 ft. H a : µ ≤ 140 ft.<br />

E) H 0 : µ = 140 ft. H a : µ ≠ 140 ft.<br />

14. A building inspector believes that the percentage of new construction with serious code<br />

violations may be even greater than the previously claimed 7%/ she conducts a hypotesis<br />

test on 200 new homes and finds 23 with serious code violations. Is this strong evidence<br />

against the .07 claim<br />

A) Yes, because the p-value is .0062<br />

B) Yes, because the p-value is 2.5<br />

C) No, because the p-value is .0062<br />

D) No, because the p-value is over 2.0<br />

E) No, because the p-value is .045<br />

1final exam review.doc p. 4


15. A telephone survey of 1000 adult Americans reveals the following data concerning the<br />

President’s tax cut plan:<br />

Support Oppose Undecided<br />

Male 300 180 90<br />

Female 210 190 30<br />

Suppose a study is conducted to test the association between gender and position on the tax<br />

cut plan. What is the expected number in the cell representing females who support the tax<br />

cut plan<br />

A) 210<br />

B) 215<br />

C) 219.3<br />

D) 240.3<br />

E) Not enough information given<br />

16. A historian believes that the average height of soldiers in World War II was greater than that<br />

in World War I. She examines a random sample of records of 100 men in each war and<br />

notes standard deviations of 2.5 inches for WWI and 2.3 inches for WWII. If the average<br />

height from the sample of World War II soldiers is 1 inch greater than that from World War<br />

I soldiers, what conclusion is justified from a two-sample hypothesis where.<br />

H : µ µ and H µ < µ<br />

0 1<br />

=<br />

2<br />

a<br />

:<br />

1<br />

2<br />

A) The observed difference in average height is significant<br />

B) The observed difference in height is not significant<br />

C) A conclusion os not possible without knowing the mean height in each sample<br />

D) A conclusion is not possiblewithout knowing both the sample means and the two<br />

original population sizes<br />

E) A two-sample hypothesis test should not be used in this sample<br />

17. Two independent random samples of size n 1 = 45 and n 2 = 38, with respective standard<br />

deviations σ 1 = 2.3 and σ 2 = 1.8, are drawn from two normally distributed populations.<br />

Which of the following represents an estimate of the standard deviation of the sampling<br />

distribution corresponding to x<br />

1<br />

! x2<br />

<br />

A) 0.25 B) 0.31 C) 0.45 D) 0.50 E) 2.05<br />

1final exam review.doc p. 5


18. A researcher wishes to use a 95% confidence interval to estimate the proportion of<br />

Americans who have visited an entertainment theme park near Orlando within the last five<br />

years. The searcher wishes to choose a size that will insure a margin of error not to exceed<br />

0.05. Which of the following is the smallest size that meets these criteria<br />

A) 40 B) 200 C) 400 D) 600 E) 800<br />

19. A health fitness group wishes to estimate the mean amount of time (in hours) that members<br />

of a fitness center spend each week exercising at the center. They want to estimate the mean<br />

within a margin of error of 0.5 hours with a 95% level of confidence. Previous data suggests<br />

that σ = 2.2. Which of the following is the smallest sample size that meets these criteria<br />

A) 60 B) 75 C) 90 D) 180 E) 190<br />

20. Data was collected to test whether there is a difference between the mean heights of women<br />

born in two different countries. It is assumed that the heights of women in each of these<br />

countries are normally distributed. Also, there is no reason to believe that population<br />

variances of the population of heights of women from the two different countries are equal.<br />

The data collected indicate the following:<br />

n 1 = 130 x<br />

1<br />

= 63. 8 s 1 = 2.3<br />

n 2 = 190 x<br />

2<br />

= 62. 4 s 2 = 2.7<br />

Which of the following represents an estimate of the standard deviation of the sampling<br />

distribution corresponding to x<br />

1<br />

! x2<br />

<br />

A) 0.04 B) 0.29 C) 2.24 D) 2.50 E) 3.16<br />

21. In a sample survey taken of 450 residents of a given community, 180 of them indicated that<br />

they shop at the local mall at least once per month. Construct a 95% confidence interval to<br />

estimate the true percentage of the residents who shop monthly at the local mall.<br />

A) (0.355, 0.445)<br />

B) (0.366, 0.434)<br />

C) (0.377, 0.423)<br />

D) (0.380, 0.420)<br />

E) It cannot be determined from the information given<br />

22. You want to compute a 90% confidence interval for the mean of a population with unknown<br />

population standard deviation. The sample size is 30. The value of t you would use to<br />

construct this interval is:<br />

A) 0.90 B) 1.311 C) 1.645 D) 1.699 E) 1.96<br />

1final exam review.doc p. 6


23. A researcher wishes to test the following hypothesis:<br />

H 0 : µ = 100<br />

H a : µ < 100<br />

If the population mean is actually 95, but the researcher concludes that the mean is 100,<br />

what type of error has occurred<br />

A) Type I error<br />

B) Type II error<br />

C) Standard error of the mean<br />

D) No error has occurred<br />

E) The data do not provide enough information to determine the type of error<br />

24. A consumer group believes that boxes of Sugar Toasties Cereal contain, on average, less<br />

than the 15 ounces of cereal as advertised. They randomly sample 36 boxes of this cereal<br />

and find the mean x = 14. 9 and standard deviation s = 0.43. Assume that the weights are<br />

normally distributed and that α = 0.05. In testing the consumer group’s claim, what is the P-<br />

value for this hypothesis test<br />

A) –0.6511<br />

B) 0.0001<br />

C) 0.0500<br />

D) 0.0859<br />

E) 0.2547<br />

25. A standard 6-sided die was rolled 24 times with the following results:<br />

Number of dots 1 2 3 4 5 6<br />

Frequency 2 8 2 1 3 8<br />

A goodness-of-fit χ 2 test is to be used to test the null hypothesis that the die is fair. At a<br />

significance level of α = 0.01, the value of the χ 2 statistic and the statistical conclusion are:<br />

A) χ 2 = 12.5; fail to reject the null hypothesis<br />

B) χ 2 = 12.5; reject the null hypothesis<br />

C) χ 2 = 25.0; fail to reject the null hypothesis<br />

D) χ 2 = 25.0; reject the null hypothesis<br />

E) χ 2 = 75.5; reject the null hypothesis<br />

1final exam review.doc p. 7


II.<br />

Free Response. Show all work. Clearly indicate the methods you use. If you use<br />

your calculator, clearly indicate the test, inputs, settings, and outputs. For<br />

hypothesis tests, clearly give H 0 and H a , in both words and symbols (where<br />

applicable).<br />

1. All current-carrying wires produce electromagnetic (EM) radiation, including the<br />

electrical wiring running into, through, and out of our homes. High frequency EM<br />

radiation is thought to be a cause of cancer; the lower frequencies associated with<br />

household current are generally assumed to be harmless. To investigate this<br />

possibility, researchers visited the addresses of children in the Denver area who had<br />

died of some form of cancer (leukemia, lymphoma, or some other type) and<br />

classified the wiring configuration outside the building as either a high-current<br />

configuration (HCC) or a low-current configuration (LCC). Here are some of the<br />

results of the study.<br />

Leukemia Lymphoma Other cancers<br />

HCC 52 10 17<br />

LCC 84 21 31<br />

The Minitab output for the above table is given below. The output includes the cell counts,<br />

the expected cell counts, and the chi-square statistic. Expected counts are printed below<br />

observed counts.<br />

Leukemia Lymphoma Other cancers Total<br />

HCC 52 10 17 79<br />

49.97 11.39 17.64<br />

LCC 84 21 31 136<br />

86.03 19.61 30.36<br />

Total 136 31 48 215<br />

ChiSq = 0.082 + 0.170 + 0.023 + 0.048 + 0.099 + 0.013 = 0.435<br />

a. The appropriate degrees of freedom for the chi-square statistic is<br />

b. The P-value for the chi-square statistic is between what two values<br />

c. The cell that contributes most to the chi-square statistic is<br />

d. What may we conclude<br />

1final exam review.doc p. 8


2. A Television Marketing Group (TMG) claims that at least three out of every four<br />

Americans believe that reality-based television shows are untruthful. They tested<br />

their claim by using data from a recent Gallup poll which indicated that in a sample<br />

of 1,015 Americans, 812 thought the shows were either somewhat or totally<br />

untruthful.<br />

a. Test the claim of the TMG using a significance level of 0.01. State<br />

clearly your assumptions and what test of hypothesis you are using.<br />

Find the appropriate P-value and interpret your results within the<br />

context of the problem.<br />

b. Construct a 95% confidence interval to estimate the true proportion of<br />

Americans who think these shows are essentially untruthful.<br />

1final exam review.doc p. 9


3. In 1908 W.S. Gosset wrote a paper titled, “The Probable Error of a Mean.” In the<br />

paper Gossett reported on the corn yield using two different kinds of seeds. The first<br />

seed was the usual seed used by farmers in England at the time. The second seed<br />

type was kiln-dried. Each type of seed was planted in adjacent plots, accounting for<br />

11 pairs of “split” plots. The data are given below. The numbers are in pounds per<br />

acre.<br />

Plot #<br />

Yield for<br />

Regular Seed<br />

Yield for Kiln-<br />

Dried Seed<br />

1 1903 2009<br />

2 1935 1915<br />

3 1910 2011<br />

4 2496 2463<br />

5 2108 2180<br />

6 1961 1925<br />

7 2060 2122<br />

8 1444 1482<br />

9 1612 1542<br />

10 1316 1443<br />

11 1511 1535<br />

The following computer outputs show the descriptive statistics of the two variables and a<br />

regression output which resulted from fitting a least squares regression line using yield from<br />

“regular” seed to predict yield from “kiln-dried” seed.<br />

Variable N Mean Median TrMean StDev SE Mean<br />

Regular 11 1841 1910 1827 343 103<br />

Kiln-Dri 11 1875 1925 1858 333 100<br />

Variable Minimum Maximum Q1 Q3<br />

Regular 1316 2496 1511 2060<br />

Kiln-Dri 1443 2463 1535 2122<br />

Predictor Coef SE Coef T P<br />

Constant 120.4 116.7 1.03 0.329<br />

Regular 0.95293 0.06241 15.27 0.000<br />

S = 67.6459 R-Sq = 96.3% R-Sq(adj) = 95.9%<br />

1final exam review.doc p. 10


Below are a residual plot and a normal quantile plot of the residuals resulting from the regression.<br />

100<br />

Residuals Versus Regular<br />

(response is Kiln-Dri)<br />

99<br />

Normal Probability Plot of the Residuals<br />

(response is Kiln-Dri)<br />

50<br />

95<br />

90<br />

Residual<br />

0<br />

80<br />

Percent<br />

70<br />

60<br />

50<br />

40<br />

-50<br />

30<br />

20<br />

10<br />

-100<br />

5<br />

1200<br />

1400<br />

1600<br />

1800 2000<br />

Regular<br />

2200<br />

2400<br />

2600<br />

1<br />

-150<br />

-100<br />

-50<br />

0<br />

Residual<br />

50<br />

100<br />

150<br />

a. Use side-by-side box plots to compare the corn yield for the two groups.<br />

Write a few sentences commenting on your display.<br />

b. Can yield of “regular seed” be used to predict the yield of “kiln dried<br />

seed” Give statistical justification to support your response.<br />

1final exam review.doc p. 11


4. An educational group claims that teaching fraction concepts using math<br />

manipulatives results in higher student achievement and understanding of fractions<br />

than teaching fractions without the use of any math manipulatives. A teacher in a<br />

middle school taught a unit on fractions to two sixth grade classes, one using math<br />

manipulatives and the other without the use of any manipulatives. The table below<br />

shows the performance of these two classes on a unit test on fractions.<br />

With Manipulatives Without Manipulatives<br />

85 78<br />

75 84<br />

83 81<br />

87 78<br />

80 76<br />

79 83<br />

88 79<br />

94 75<br />

87 85<br />

82 81<br />

Test the claim that students who use manipulatives show higher achievement on a test of<br />

fractions. Give appropriate statistical evidence to support your answer.<br />

1final exam review.doc p. 12


5. In a nationwide random sample of 550 high school boys and 430 high school girls,<br />

all of which have been caught cheating by their teachers at some time, 253 boys and<br />

172 girls admitted to cheating on an exam. Is this sufficient evidence to say that<br />

boys are more likely to admit to cheating than girls Provide appropriate statistical<br />

evidence.<br />

1final exam review.doc p. 13


6. A medical research team is conducting a study to determine whether there is a<br />

relationship between aerobic walking and cholesterol levels. A random sample of<br />

315 subjects is selected and represented in the table below. Test the claim that<br />

aerobic walking and cholesterol levels are related. Include appropriate statistical<br />

evidence to support your findings.<br />

Low Average Elevated<br />

Walkers 51 86 31<br />

Non-Walkers 23 94 30<br />

7. A new cell phone company offers a selection of five colors in their designer<br />

corporate package. The company claims that the 5 colors are equally distributed<br />

among all phones. Goodinvest.com orders 10 corporate packages of 10 phones each<br />

and randomly received 18 red, 17 blue, 20 green, 24 purple, and 21 orange phones.<br />

Does this contradict the phone company’s claim that the 5 colors are equally<br />

distributed<br />

1final exam review.doc p. 14


8. Country A and Country B each have been competing in the 200-meter dash in the<br />

Olympics for many years. A random sample of 13 running times for Country A<br />

shows a mean of 24.52 seconds and a standard deviation of 0.76 seconds. A random<br />

sample of 13 running times for Country B shows a mean of 24.6 seconds and a<br />

standard deviation of 0.82 seconds. Assume times are normally distributed.<br />

a. Is there significant evidence to conclude that there is a difference between<br />

the average speed of the two groups Give appropriate statistical<br />

justification.<br />

b. Construct a 95% confidence interval for the difference between the average<br />

speeds of the two groups. Explain how this interval confirms or contradicts<br />

your conclusion in part a.<br />

1final exam review.doc p. 15


9. A car dealer claimed that the average new car bought by people who live in<br />

Connecticut costs more than $25,000. A local newspaper thought that the claim was<br />

false, and the dealer was saying this so that they could justify charging higher prices.<br />

The newspaper took a random sample of 30 new car registrations in Connecticut and<br />

recorded the sales prices of those cars, which are given here.<br />

19,445 28,403 27,777 38,402 31,337 25,404 27,515 22,490 45,602 16,447<br />

Conduct the appropriate hypothesis test. Is the dealer’s statement supported by the data at<br />

the 0.10 significance level<br />

10. A researcher is studying whether there is a linear relationship between the number of<br />

“grow lights” used to illuminate an African Violet plant and the plant height in<br />

centimeters. The results of the regression are as shown in the following table.<br />

Predictor Coef SE Coef<br />

Constant 30.881 8.062<br />

Lights 10.953 3.948<br />

S = 8.49090 R-Sq = 46.1% R-Sq(adj) = 40.1%<br />

Number of observations = 11<br />

a. What is the regression equation that predicts plant height using number of lights<br />

b. Is the slope significant Calculate the value of the test statistic, compare it to the<br />

critical value of the test statistic, and make a conclusion.<br />

c. Construct a 90% confidence interval for β, using the given data.<br />

1final exam review.doc p. 16

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!