Hypothesis Testing: Concepts and Applications
Chapter 1: Hypothesis Testing
1. After you conduct a coin-flipping simulation, a graph of the ________ will be very close to 0.50.
D. Proportion of heads
2. The graph of a null distribution will be centered approximately on:
C. The value of the probability in the null hypothesis
3. The p-value of a test of significance is:
A. The probability, assuming the null hypothesis is true, that we would get a result at least as extreme as the one that was
actually observed.
4. Suppose a researcher is testing to see if a basketball player can make free throws at a rate higher than the NBA average of 75%.
The player is tested by shooting 10 free throws and makes 8 of them. In conducting the related test of significance we have acomputer applet do an appropriate simulation, with 1,000 repetitions, and produce a null distribution. The distributionrepresents:
B. Repeated results if the player makes 75% of his shots in the long run
5. The simulation (flipping coins or using the applet) done to develop the distribution we use to find our p-values assume whichhypothesis is true?
A. Null hypothesis
6. When using the coin-flipping chance model, the most important reason you repeat a simulation of the study many times is:
D. To see how much variability there is in the null distribution
7. When we get a p-value that is very large, we may conclude that:
C. The null hypothesis is plausible.
8. When we get a p-value that is very small, we may conclude that:
B. There is strong evidence for the alternative hypothesis.
9. Which standardized statistic (standardized sample proportion) gives you the strongest evidence against the null hypothesis?
C. ???????? = −3
10. Suppose that your hypotheses are ????????0: ???????? = 0.25 and ????????????????: ????????
D. ???????? = −1.80
11. Supposoe that a standardized statistic (standardized sample proportion) for a study is calculated to be 2.45. Which of the
following g is the most appropriate interpretation of the standardized statistic?
B. The observed value of the sample proportion is 2.45 SDs above the hypothesized parameter value.
12. Researchers want to investigate whether a spun tennis racquet is equally likely to land with the label facing up or down. Doesthis racquet spinning study call for a one-sided or a two-sided alternative?
D. Two-sided, because the researchers want to know whether the spinning process is fair or biased in either direction.
13. Researchers want to investigate whether a spun tennis racquet is equally likely to land with the label facing up or down. Whichof the following will always be true about the standardized statistic for the racquet-spinning study?
A. The standardized statistic increases as the sample proportion that land “up” increases.
14. Researchers want to investigate whether a spun tennis racquet is equally likely to land with the label facing up or down. Which
of the following will always be true about the p-value for the racquet-spinning study?
D. The p-value decreases as the sample proportion that land “up” gets farther from 0.50.
15. Which long-run proportion of success, ????????, gives the largest standard deviation of the null distribution when the sample size is 10?
C. 0.25
16. Which sample size, ????????, gives the smallest standard deviation of the null distribution where the long-run proportion, ????????, is 0.25?
D. 60
17. Suppose you are using the theory-based techniques (e.g. a one-proportion z-test) to determine p-values. How will a two-sidedp-value compare to a one-sided p-value (assuming the one-sided p-value is less than 0.50)?
C. The two-sided p-value will be exactly twice as large as the one-sided.
Chapter 2: Sampling and Data
18. The population will always be ________________ the sample.
A. At least as large as
19. In most statistical studies the _________________ is unknown and the _____________ is known.
A. Parameter/statistic
20. The reason for taking a random sample instead of a convenience sample is:
B. Random samples tend to represent the population of interest.
21. True or False? Larger samples are always better than smaller samples, regardless of how the sample was collected.
B. False
22. True or False? Larger random samples are always better than smaller random samples.
A. True
23. True or False? You shouldn’t take a random sample of more than 5% of the population size.
A. True
24. True or False? Random sample only generate unbiased estimates of long-run proportion, not long-run means.
B. False
25. True or False? Nonrandom samples are always biased.
B. False
26. True or False? There is no way that a sample of 100 people can be representative of all adults living in the United States.
B. False
27. When stating null and alternative hypotheses, the hypotheses are:
A. Always about the parameter only
28. When using simulation- or theory-based methods to test hypotheses about a proportion, the process of computing a p-value is:
B. The same if the sample is from a process instead of from a finite population
29. The monthly salaries of the three people working in a small firm are $3,500, $4,000, and $4,500. Suppose the firm makes aprofit and everyone gets a $100 raise. How if at all would the average of the three salaries change?
B. The average would increase.
30. The monthly salaries of the three people working in a small firm are $3,500, $4,000, and $4,500. Suppose the firm makes aprofit and everyone gets a $100 raise. How if at all would the standard deviation of the three salaries change?
A. The standard deviation would stay the same.
31. The monthly salaries of the three people working in a small firm are $3,500, $4,000, and $4,500. Suppose the firm makes aprofit and everyone gets a 10% raise. How if at all would the average of the three salaries change?
B. The average would increase.
32. The monthly salaries of the three people working in a small firm are $3,500, $4,000, and $4,500. Suppose the firm makes aprofit and everyone gets a 10% raise. How if at all would the standard deviation of the three salaries change?
B. The standard deviation would increase.
33. Suppose that the birthweights of babies in the U.S. have a mean of 325
0 grams and standard deviation of 550 grams. Based onthis information, which of the following is more unlikely?
B. A random sample of 10 babies has an average birth weight greater than 400 grams.
34. In which scenario would you expect to see more variability in the data: heights of a random sample of 100 college students orheights of a random sample of 500 college students?
C. Both samples will have similar variability