POL 138 Final exam ISU

Suppose that the island country of Madripoor has 200,000 native residents and 50,000 immigrants. In 2023,300 native Madripoor residents and 100 immigrants to Madripoor were a victim of a hate crime. Presuming that the data above are correct, indicate whether each statement below is true or false. True or false? There were fewer hate crimes against immigrants to Madripoorthan against native Madripoor residents. A. True B. False

A. True

Can an IRB, in some circumstances, permit research involving human participants in which the human participants do not provide informed consent? A. Yes B. No

A. Yes

If the p-value is p=0.0001 for a single statistical test of a null hypothesis that there is no association, do we have enough evidence to claim that there is statistically significant evidence for the detected association? A. Yes B. No

A. Yes

Suppose that a high school has two sets of students: the Jets, and the Sharks. Data indicate that, last year, 50 Jets students were suspended from school, and 20 Sharks students were suspended from school. Is a possible explanation for this gap the possibility that a higher percentage of students are Jets than are Sharks? A. Yes B. No

A. Yes

Suppose that a high school has two sets of students: the Jets, and the Sharks. Data indicate that, last year, of all students that were suspended from school, 67% were Jets and 33% were Sharks. Is a possible explanation for this gap the possibility that a higher percentage of students are Jets than are Sharks? A. Yes B. No

A. Yes

Suppose that researchers in Florin are interested in whether the mean income among married men differs from the mean income among never married men. For a representative sample of Florin men, the researchers compare the mean income of married Florin men to the mean income of never married Florin men. The p-value is p<0.01 for a test of the null hypothesis that these means equal each other, with the mean income of married Florin men 11% higher than the mean income of never married Florin men. Does this analysis contain sufficient evidence to conclude, at the conventional level in political science, that, at least among men in this analysis and at least on average, the mean income of married Florin men is higher than the mean income of never married Florin men? A. Yes B. No

A. Yes

Suppose that, in group A, men are on average older than women are. Suppose that, in group B, men are on average older than women are. If group A and group B are combined into group C, then, in group C, ___. A. men will be older than women on average B. men will not necessarily be older than women on average

B. men will not necessarily be older than women on average

The image below is an example of a ___. A. uniform distribution B. normal distribution

B. normal distribution

Later this year, school administrators test students for covid-23. School administrators would rather erroneously conclude that a student has covid-23when the student truly doesn't have covid-23, than to erroneously conclude that a student does not have covid-23when the student truly has covid-23. Which p-value threshold below would be more appropriate for testing the null hypothesis that a student does not have COVID-23? A. p=0.01 B. p=0.10

B. p=0.10

Research focusing on numbers is ___. A. qualitative research B. quantitative research

B. quantitative research

Suppose that, in a randomized experiment, the mean response from participants in the control group differs from the mean response from participants in the treatment group. One reason for this is that participants in the control group were treated differently than participants in the treatment group. The other possible reason why the mean response from participants in the control group differed from the mean response from participants in the treatment group is ___. A. a ceiling effect B. random assignment error C. regression toward the mean D. Simpson's paradox

B. random assignment error

Which score below indicates a higher degree of political knowledge, for a political knowledge test? A. scoring at the 1st percentile on the test B. scoring at the 99th percentile on the test

B. scoring at the 99th percentile on the test

Suppose that we measure participant ratings about the president on a scale from 0 to 100. The mean rating is 60 and the standard deviation of ratings is 12. If we divide all the ratings by 100 so that the scale ranges from 0 to 1, then standard deviation of the ratings on this0-to-1 scale will be ___. A. 12 B. smaller than 12 C. larger than 12

B. smaller than 12

Suppose that we conducted a randomized experiment to test the effect of a treatment on an outcome. The mean of the outcome is higher in the treatment group than in the control group, but the p-value isp=0.19 for a test of the null hypothesis that the treatment mean equals the control mean. Therefore, we should conclude that the randomized experiment provided___ that the treatment had an effect on the outcome. A. no evidence B. some evidence C. sufficient

B. some evidence

Suppose that the CEO of a firm graduated from Illinois State University and gives preference in hiring to applicants who graduated from Illinois State University, even though the CEO has no data that applicants from Illinois State University are any better or worse than other applicants. Which of the following types of discrimination does this better reflect? A. statistical discrimination B. taste-based discrimination

B. taste-based discrimination

Amy flips her coin a certain number of times, and Bob flips his coin a different number of times. Amy and Bob then each test the null hypothesis that their coin is far. Amy's p-value is p=0.04, and Bob's p-value is p=0.50. This is sufficient evidence at the conventional level in political science to conclude___. A. that Amy's coin is more unfair than Bob's coin B. that Amy has more evidence that her coin is fair than Bob has that his coin is fair C. both A and B D. neither A nor B

B. that Amy has more evidence that her coin is fair than Bob has that his coin is fair

Which of the following would be wider, for the same set of measurements? A. the 83% confidence interval for the mean of the measurements B. the 95% confidence interval for the mean of the measurements

B. the 95% confidence interval for the mean of the measurements

Suppose that a POL 138 class has 10male students and 20 female students. The instructor selects two students at random to come to the front of the room. What is the probability that both students are male? A. (10/20) * (10/20) B. (10/30) * (10/30) C. (10/30) * (9/29) D. (10/30) * (10/29) E. None of the above

C. (10/30) * (9/29)

Suppose that Blacks are 13% of the population but are 10% of our sample of that population. What weight should be applied to each observation of a Black person, if weighting on only race? A. 10 * 13 B. 10 / 13 C. 13 / 10 D. None of the above

C. 13 / 10

Suppose that null hypothesis is true. Researcher A conducts a well-designed test of the null hypothesis. Independently of Researcher A, Researcher B conducts a well-designed test of the null hypothesis. What is known, if anything, about the probability that at least one of these two researchers gets a p-value that is less than p=0.05? A. 0% B. 5% C. Above 5% but under 100% D. 100% E. Cannot be determined with the information provided

C. Above 5% but under 100%

17. Political scientists weight survey data for which of the following reasons? A. Because the sample is too small B. Because the population is much larger than the sample C. Because the population characteristics do not match the sample characteristics

C. Because the population characteristics do not match the sample characteristics

Which of the following are organizations designed to protect human subjects in scientific research? A. CODs B. DOJs C. IRBs D. RBDs E. REMs

C. IRBs

Amy randomly samples 30 ISU students and asks them to rate the president on a scale from 0 for very cold to 100 for very warm. Bob randomly samples 200ISU students and asks them to rate the president on a scale from 0 for very cold to 100 for very warm. Which of the following, if any, should be expected due to this difference in sample size? A. The mean support for the president is lower in Amy's sample than in Bob's sample. B. The mean support for the president is higher in Amy's sample than in Bob's sample. C. Neither of the above

C. Neither of the above

Suppose that data from a large representative sample of college students indicated that political knowledge was higher among political science majors than among physics majors. The p-value for this comparison was p<0.001. Is this sufficient evidence that, at least on average, being a political science major causes higher levels of political knowledge than being a physics major does? A. Yes, because the p-value is less than p=0.05. B. Yes, because the p-value is less than p=0.05 and it makes sense that being a political science major would cause higher levels of political knowledge. C. No, because the analysis did not eliminate alternate explanations such as the possibility that, even before these students entered their majors, the students who became political science majors had higher political knowledge than the students who became physics majors.

C. No, because the analysis did not eliminate alternate explanations such as the possibility that, even before these students entered their majors, the students who became political science majors had higher political knowledge than the students who became physics majors.

In 2019, Illinois State University had 335 undergraduate mathematics majors and 2,369 undergraduate education majors. Suppose that we wanted to estimate the gap in GPA between these undergraduate mathematics majors and these undergraduate education majors. How, if at all, is the difference between the sample sizes expected to affect that comparison? A. The difference between the sample sizes is expected to bias the estimated size of the gap to be smaller than it truly is. B. The difference between the sample sizes is expected to bias the estimated size of the gap to be larger than it truly is. C. The difference between the sample sizes is not expected to bias the estimated size of the gap.

C. The difference between the sample sizes is not expected to bias the estimated size of the gap.

Which of the following best indicates what a placebo is? A. a treatment that has a positive effect B. a treatment that has a negative effect C. a treatment that has no effect D. a treatment that has an effect

C. a treatment that has no effect

Inclusion of an irrelevant control variable in a non-experimental analysis can ___. A. bias an estimate of an effect only to be lower than it truly is B. bias an estimate of an effect only to be higher than it truly is C. bias an estimate of an effect to be lower than or higher than it truly is

C. bias an estimate of an effect to be lower than or higher than it truly is

Omission of a relevant control variable in a non-experimental analysis can ___. A. bias an estimate of an effect only to be lower than it truly is B. bias an estimate of an effect only to be higher than it truly is C. bias an estimate of an effect to be lower than or higher than it truly is

C. bias an estimate of an effect to be lower than or higher than it truly is

Random assignment error in a randomized experiment can ___. A. bias an estimate of an effect only to be lower than it truly is B. bias an estimate of an effect only to be higher than it truly is C. bias an estimate of an effect to be lower than or higher than it truly is

C. bias an estimate of an effect to be lower than or higher than it truly is

A researcher conducted a randomized experiment and then compared the mean response of participants in Group A to the mean response of participants in Group B. The p-value for the difference between mean responses was p=0.22.Based on this p-value, the researcher should ___. A. conclude that there is an effect B. conclude that there is no effect C. conclude that there is not enough evidence to conclude that there is an effect

C. conclude that there is not enough evidence to conclude that there is an effect

NBA basketball players tend to be tallerthan the average U.S. resident. Suppose that Bob is at the 80th percentile of height among NBA basketball players. Bob's percentile height among U.S. residents is likely ___. A. less than the 80th percentile B. at the 80th percentile C. greater than the 80th percentile

C. greater than the 80th percentile

How do control variables help improve causal inference in a correlational study? A. reduce bias in measurements B. remove sample bias C. help address alternate explanations D. randomly assign participants

C. help address alternate explanations

18. In the United States, compared to women, a higher percentage of men support Republican candidates for president. If a survey oversampled men relative to women, then the estimate of support for a Republican candidate for president will likely be ___. A. lower than it is in reality B. equal to reality C. higher than it is in reality

C. higher than it is in reality

Amy and Bob are testing the null hypothesis that, on a scale from 0 to 100,the mean rating for the president is 60 in a population. The mean from Amy's sample of 200 participants is 58 with a standard deviation of 10. The mean from Bob's sample of 100 participants is 58with a standard deviation of 10. Amy's p-value is p=0.005. Bob's p-value is ___. A. p=0.005 B. lower than p=0.005 C. higher than p=0.005

C. higher than p=0.005

Amy and Bob are testing the null hypothesis that, on a scale from 0 to 100,the mean rating for the president is 60 in a population. The mean from Amy's sample of 200 participants is 58, and the mean from Bob's sample of 200 participants is 58, but Amy's standard deviation of ratings is 10 and Bob's standard deviation of ratings is 12. Amy's p-value is p=0.005. Bob's p-value is ___. A. p=0.005 B. lower than p=0.005 C. higher than p=0.005

C. higher than p=0.005

Suppose that, in a given dataset, the mean weight given to Hispanic participants is 0.80. That indicates that Hispanics were ___ in the sample, relative to the Hispanic percentage of the population. A. under-represented B. correctly represented C. over-represented

C. over-represented

Suppose that data from the Freedonia Department of Transportation indicate that the number of traffic crash fatalities from 2016 through 2022 had been 978,990, 935, 910, 996, and 1134. After the jump from 996 fatalities to 1134fatalities, Freedonia state troopers began a program to more frequently ticket speeding vehicles. The next year, the number of traffic crash fatalities fell from 1134 to 960. Using these data to conclude that the new ticketing policy caused the drop from 1134 to 960 best reflects a lack of consideration of which of the following? A. an ecological fallacy B. Kelley's paradox C. regression toward the mean D. Simpson's paradox

C. regression toward the mean

If we flipped a fair coin and got 10 heads and 0 tails, what would be the p-value for a statistical test of the null hypothesis that the coin is fair? A. 0 B. 1

C. something between 0 and 1

If we flipped a fair coin and got 10 heads and 5 tails, what would be the p-value for a statistical test of the null hypothesis that the coin is fair? A. 0 B. 1 C. something between 0 and 1

C. something between 0 and 1

Which one of these is correct about double-blind peer review for a submitted manuscript? A. the author of a submission is told who peer reviewed the submission B. the peer reviewers are told who authored the submission C. the peer reviewers are not told who authored the submission

C. the peer reviewers are not told who authored the submission

Of the following, which best describes what a p-value measures? A. the precision of an estimate B. the size of an association controlling for other model factors C. the strength of evidence against the null hypothesis

C. the strength of evidence against the null hypothesis

Which one of the following regards whether a measure measures what the measure is supposed to measure? A. reliability B. skew C. validity

C. validity

Of the p-values below, which p-value indicates the strongest evidence against the null hypothesis? A. 0.01 B. 0.05 C. 0.50 D. 0.99 E. 1.00

A. 0.01

The probability of X happening is 10%, and the probability of Y happening is10%. X and Y are independent events. What is the probability that X and Y both occur? A. 1% B. 10% C. 20% D. 100% E. Cannot be determined from the information provided

A. 1%

The standard deviation of the set of numbers {0,10,25} is 10.3. If we added 5 to each number in the set to get a new set {5,15,30}, then the standard deviation of that new set will be ___. A. 10.3 B. smaller than 10.3 C. larger than 10.3

A. 10.3

Suppose that scores on a national test follow a normal distribution and have a mean of 100 and a standard deviation of10. If Student A raises her score from 90to 100, and Student B raises her score from 80 to 90, which of the following statements is true? A. Student A had the higher percentile increase on the test. B. Student B had the higher percentile increase on the test. C. Student A had the same percentile increase on the test as Student B had

A. Student A had the higher percentile increase on the test.

Which best indicates what the null hypothesis is? A. The hypothesis being tested B. The complement of the hypothesis being tested C. The hypothesis that the effect is not zero

A. The hypothesis being tested

Suppose that the island country of Madripoor has 200,000 native residents and 50,000 immigrants. In 2023,300 native Madripoor residents and 100 immigrants to Madripoor were a victim of a hate crime. Presuming that the data above are correct, indicate whether each statement below is true or false. True or false? The per capita rate of being a victim of a violent crime was higher among immigrants to Madripoorthan among natives of Madripoor. A. True B. False

A. True

Suppose that researchers in Latveria are interested in whether married men have a different income on average than never married men have. For a representative sample of Latverian men, the researchers compare the mean income of married Latverian men to the mean income of never married Latverian men. The p-value is p=0.25 for a test of the null hypothesis that these means equal each other. Which of the confidence intervals below for the difference in mean incomes would be a more informative null? A. [-$200, +$300] B. [-$40,000, +$40,000]

A. [-$200, +$300]

Which of these is closest to what an inference is? A. a conclusion B. a flawed idea C. a prediction D. a reason for a prediction

A. a conclusion

Test A has a mean of 50 points and a standard deviation of 20 points. Test B has a mean of 50 points and a standard deviation of 25 points. Both Test A and Test B have scores that follow a normal distribution. Student A scored at the 50thpercentile on Test A, and Student B scored at the 50th percentile on Test B. Student A and Student B were then each given an extra 5 points on their test. This extra 5 points would have produced ___. A. a higher percentile increase for Student A on Test A than for Student B on Test B B. a higher percentile increase for Student B on Test B than for Student A on Test A C. the same percentile increase for Student A on Test A as for Student Bon Test B

A. a higher percentile increase for Student A on Test A than for Student B on Test B

Suppose that, for a multiple-choice political science knowledge test, students from State A have a mean score of 40 and students from State B have a mean score of 60. Scores in both states follow a normal distribution, and the standard deviation of scores in both states is10. Because of Kelley's paradox, a randomly selected student from State A who has a score of 80 will be expected to be more likely to have___ true level of political science knowledge than a randomly selected student from State B who has a score of 80. A. a lower B. the same C. a higher

A. a lower

Suppose that we have a six-sided die that is numbered from 1 through 6. We roll the die once and record the number on the top. We do this again and again until we have 5,000 numbers recorded. A plot of the frequency of those numbers would more closely look like ___. A. a uniform distribution B. a normal distribution

A. a uniform distribution

A researcher randomly selects 200 people from a population and then randomly assigns 100 of these people to a group that receives Treatment A and randomly assigns the other 100 people to a group that receives Treatment B. The random selection from the population ___. A. better permits the researcher to make an inference about the population B. better permits the researcher to make an inference about whether Treatment A has a different effect than Treatment B has among participants in the sample

A. better permits the researcher to make an inference about the population

Suppose that the true effect of a treatment is +7 among men but is +3among women. Across a population that has the same number of men and women, the average effect of the treatment will be +5. But, if our sample has many more women than men, and if we don't weight our analysis to account for this, then the estimated effect size from the sample will plausibly be ___. A. biased lower than +5 B. biased higher than +5

A. biased lower than +5

A researcher conducted a randomized experiment and then compared the mean response of participants in Group A to the mean response of participants in Group B. The p-value for the difference between mean responses was p=0.02.Based on this p-value, the researcher should ___. A. conclude that there is an effect B. conclude that there is no effect C. conclude that there is not enough evidence to conclude that there is an effect

A. conclude that there is an effect

Which type of validity concerns the ability to make correct claims about the sample? A. internal validity B. external validity

A. internal validity

The conventional threshold for accepting a political science association as indicating a true association is a p-value under 0.05. If we want to have fewer false positives in which we falsely reject the null hypothesis, which of the following could we do? A. lower the p-value threshold to 0.01 B. raise the p-value threshold to 0.10

A. lower the p-value threshold to 0.01

Suppose that we conduct a randomized experiment to test the effect of a treatment on an outcome. The mean of the outcome in the treatment group equals the mean of the outcome in the control group, and the p-value is p=1.00 for a test of the null hypothesis that the treatment mean equals the control mean. Therefore, we should conclude that the randomized experiment provided___ that the treatment had an effect on the outcome. A. no evidence B. some evidence C. sufficient

A. no evidence

The standard deviation of the set of numbers {-4,-5,-7} is ___. A. positive B. negative C. zero

A. positive

The standard deviation of the set of numbers {0,1,2} is ___. A. positive B. negative C. zero

A. positive

Discrimination in which unknown information for an individual is estimated based on known or perceived data for the individual's group is referred to as ___. A. statistical discrimination B. taste-based discrimination

A. statistical discrimination

Suppose that the CEO of a firm gives preference in hiring to applicants who graduated from Illinois State University, because, in data from applicant hires over the past ten years, applicants who had graduated from Illinois State University have performed better on average than other similar applicants have performed. Which of the following types of discrimination does this better reflect? A. statistical discrimination B. taste-based discrimination

A. statistical discrimination

Outliers tend to have more influence on___ of a set of numbers. A. the mean B. the median

A. the mean

Which type of validity concerns the ability of a research result to generalize to the population? A. internal validity B. external validity

B. external validity

What is the most common p-value threshold in political science? A. 0.01 B. 0.05 C. 0.50 D. 0.95 E. 1.00

B. 0.05

If we flipped a fair coin and got 10 heads and 10 tails, what would be the p-value for a statistical test of the null hypothesis that the coin is fair? A. 0 B. 1 C. something between 0 and 1

B. 1

Suppose that, in an experiment, the mean for the control group was 20, the standard deviation for the control group was 12, the mean for the treatment group was 20, and the standard deviation for the treatment group was 20. What would be the p-value for a test of the null hypothesis that the control group mean equals the treatment group mean? A. 0 B. 1 C. something between 0 and 1

B. 1

In data from 2020, the mean rating of the National Rifle Association was 26 among Democrats, 47 among independents, and 75 among Republicans. Moreover, Democrats were 36% of the population, Independents were 32% of the population, and Republicans were 32% of the population. To the nearest decimal place, what would be the mean rating of the National Rifle Association across all three groups? A. 42.1 B. 48.4 C. 49.3 D. 50.1 E. 51.5

B. 48.4

If the null hypothesis is true, what is the probability that the p-value from a single well-designed test of the null hypothesis is p<0.05? A. 0% B. 5% C. 50% D. 95% E. 100%

B. 5%

Suppose that we conduct 900 independent tests of a null hypothesis, using an experiment with a large sample size. In reality, the null hypothesis is true. What is the expected percentage of these tests that are expected to have a p-value of p<0.05? A. 0% B. 5% C. 50% D. 95% E. 100%

B. 5%

Suppose that a score of 90 is at the 70thpercentile for scores on a test. What doesthis mean? A. 70 percent of scores are above 90. B. 70 percent of scores are below 90. C. 70 percent of scores were 90. D. 90 percent of scores were 70 .E. A test with a score of 70 was a test with 90 percent of items correct .F. None of the above

B. 70 percent of scores are below 90.

Which of the following is the "blind" element of single-blind peer review of a paper? A. Peer reviewers are not told the names of the paper's authors B. Authors are not told the names of the peer reviewers

B. Authors are not told the names of the peer reviewers

There are 100 members of Group A, and each member has one test score; there are 100 members of Group B, and each member has one test score. The test scores for Group A follow a normal distribution and have a mean of 100 and a standard deviation of 5; the test scores for Group B follow a normal distribution and have a mean of 100 and a standard deviation of 10. Based on these statements, which ONE of the following statements is true? A. It is more likely that a member of Group A has the highest test score, and not a member of Group B. B. It is more likely that a member of Group B has the highest test score, and not a member of Group A. C. The probability that a member of Group A has the highest test score is the same as the probability that a member of Group B has the highest test score.

B. It is more likely that a member of Group B has the highest test score, and not a member of Group A.

Bob wants to test whether a pill causes weight loss, so he assigns a randomly selected set of 1,000 U.S. residents to take the pill each morning for ten weeks. Results indicated that the mean weight of the participants decreased over the ten weeks of the study (p<0.001). Based on this evidence, can we conclude at the conventional level in political science that the pill caused the weight loss among these participants, at least on average? A. Yes B. No

B. No

If the p-value from a single statistical test of a null hypothesis is p=0.0001, do we have enough evidence to claim that the detected association is substantively large? A. Yes B. No

B. No

In political science, for peer review of papers that report a statistical analysis, is it typical for the peer reviewers to check the data to see whether the statistical analysis has been correctly conducted? A. Yes B. No

B. No

Suppose that, based on a faculty committee's judgment, a law school selected its ten top students every year for a class of a thousand students. For this selection, male students have been more likely than female students to have been selected. If a researcher wanted to assess whether this gender difference is fair, the researcher would be better at analyzing data about ___. A. male students and female students at the 50th percentile of the grade-point-average distribution B. male students and female students at the 99th percentile of the grade-point-average distribution

B. male students and female students at the 99th percentile of the grade-point-average distribution

Suppose that a POL 138 instructor is interested in testing whether permitting students to use handwritten notes on a notecard will increase final exam scores, so the instructor tells students that they have permission to bring a 3"x5"notecard to use during the final exam, with handwritten notes permitted on the notecard. Results indicate that mean final exams score was higher for students who used a notecard than for students who did not use a notecard, with the p-value of p<0.05 for a test of the null hypothesis that the mean score for students who used a notecard equaled the mean score for students who did not use a notecard. Does this analysis contain sufficient evidence to conclude, at the conventional level in political science, that, at least among students in this analysis and at least on average, using the notecard increased student scores on the final exam? A. Yes B. No

B. No

Suppose that researchers in Freedonia propose a theory that getting married will cause men to work more hours and thus increase their income. Researchers collect data from a representative sample of Freedonia men, and the data indicate that income is 11% higher for married Freedonia men than for never married Freedonia men. The p-value is p<0.01for a test of the null hypothesis that these means equal each other. Does this analysis contain sufficient evidence to conclude, at the conventional level in political science, that, at least among men in this analysis and at least on average, getting married causes men to have a higher salary? A. Yes B. No

B. No

Suppose that researchers in Oceania propose a theory that getting married will cause men to work more hours and thus increase their income. Researchers collect data from a representative sample of Oceania men, and the p-value is p=0.30 for a test of the null hypothesis that the mean income among married men equals the mean income among never married men. Does this analysis contain sufficient evidence to conclude, at the conventional level in political science, that, at least among men in this analysis and at least on average, getting married does not cause men to have a higher salary? A. Yes B. No

B. No

Your doctor recommends that you take a drug for your condition, and you are considering which of two drugs to use. For each drug, there has been one randomized experiment to test the effect of the drug. The first randomized experiment detected evidence at p<0.05that Drug 1 was more effective than a placebo. The second randomized experiment did not detect evidence atp<0.05 that Drug 2 was more effective than a placebo. Can you therefore conclude, at the conventional level in political science, that Drug 1 is more effective than Drug 2? A. Yes B. No

B. No

Suppose that researchers test the effect of a treatment. Results provide evidence at p=0.03 that the treatment worked among men participants, but the p-value is p=0.20 for the test of the effect among women participants. Is this sufficient evidence to support the conclusion that the treatment was more effective among men participants than among women participants? A. Yes: the p-values of p=0.03 and p=0.20 provide sufficient evidence that the treatment worked among men participants but did not provide sufficient evidence that the treatment worked among women participants. B. No: p-values do not directly indicate anything about effect sizes, so we cannot conclude based on these p-values that the effect size was larger for men participants than for women participants.

B. No: p-values do not directly indicate anything about effect sizes, so we cannot conclude based on these p-values that the effect size was larger for men participants than for women participants.

Suppose that a researcher is interested in whether breastfeeding a child causes the child to have higher cognitive ability, on average. Researcher A plans to compare Grade 4 children who were breastfed by their mothers (n=900) to Grade 4children who were not breastfed by their mothers (n=900). Researcher B plans to compare Grade 4 children who were breastfed by their mothers(n=900) to Grade 4 children who tried to breastfeed their child but could not produce milk to breastfeed the child (n=200). Which researcher's design is better? A. Researcher A, because Researcher A's design has a larger sample size B. Researcher B, because Researcher B's design compares groups that are more similar to each other except for the variable of interest

B. Researcher B, because Researcher B's design compares groups that are more similar to each other except for the variable of interest

Suppose that researchers in Lugash test a hypothesis that getting married will cause men to work more hours and thus increase their income. Using data from Lugash, Researcher A compared the average income of all married men(n=2,000,000) to the average salary of all never married men (n=2,000,000),and Researcher B compared the average salary of all married men aged 30 to 40(n=20,000) to the average income of all never married men aged 30 to 40(n=20,000). Which researcher had the better research design for testing the hypothesis that getting married will cause men to work more hours and thus increase their income? A. Researcher A, because Researcher A's research design will have a much larger sample B. Researcher B, because Researcher B's research design addresses an alternate explanation by comparing men of similar ages

B. Researcher B, because Researcher B's research design addresses an alternate explanation by comparing men of similar ages

Amy randomly samples 30 ISU students and asks them to rate the president on a scale from 0 for very cold to 100 for very warm. Bob randomly samples 200 ISU students and asks them to rate the president on a scale from 0 for very cold to 100 for very warm. Which of the following, if any, should be expected due to this difference in sample size? A. The 95% confidence interval for mean support for the president is thinner in Amy's sample than in Bob's sample. B. The 95% confidence interval for mean support for the president is wider in Amy's sample than in Bob's sample. C. Neither of the above

B. The 95% confidence interval for mean support for the president is wider in Amy's sample than in Bob's sample.

Suppose that a bin has 101 balls numbered from 0 through 100. We pullout five of those balls, calculate the mean of the numbers on those five balls ,and put the balls back into the bin. We do this again and again until we have5,000 means recorded. A plot of the frequency of those means would more closely look like ___. A. a uniform distribution B. a normal distribution

B. a normal distribution

A researcher randomly selects 200 people from a population and then randomly assigns 100 of these people to a group that receives Treatment A and randomly assigns the other 100 people to a group that receives Treatment B. The random assignment to groups ___. A. better permits the researcher to make an inference about the population B. better permits the researcher to make an inference about whether Treatment A has a different effect than Treatment B has among participants in the sample

B. better permits the researcher to make an inference about whether Treatment A has a different effect than Treatment B has among participants in the sample

Suppose that we accurately measure the height of 100 randomly selected students at Faber College. The 95%confidence interval for the mean height in feet is [5.4, 5.8]. If we randomly lose half of the observations and recalculate a 95%confidence interval for the mean height of students at Faber College based on the 50 observations that we have left, that 95% confidence interval would be expected to be___. A. thinner than [5.4, 5.8] B. the same width as [5.4, 5.8] C. wider than [5.4, 5.8]

C. wider than [5.4, 5.8]

The standard deviation of the set of numbers {2,2,2} is ___. A. positive B. negative C. zero

C. zero

For a test of a null hypothesis that the association between X and Y is zero, the term "statistically significant evidence" refers to sufficient evidence that the association between X and Y ___. A. is large B. is important C. is zero D. is not zero

D. is not zero

If the p-value for a test of a null hypothesis is p=0.01, then we should do which of the following? A. accept the null hypothesis and accept the alternative hypothesis B. reject the null hypothesis and reject the alternative hypothesis C. accept the null hypothesis and reject the alternative hypothesis D. reject the null hypothesis and accept the alternative hypothesis E. none of the above

D. reject the null hypothesis and accept the alternative hypothesis

Standard deviation is a measure of ___. A. central tendency B. correctness C. reliability D. spread E. validity

D. spread

Suppose that a particular defendant is on trial and that, in the population, 95percent of persons would vote to convict this defendant based on the evidence presented at trial. If 12 persons are randomly drawn from the population to serve on a jury for this defendant, there is a 54% chance that all 12 of these jurors will vote to convict the defendant based on the evidence presented at trial, assuming that no juror influences the vote of any other juror. Freedonia is considering reducing the size of a jury to8 persons. If, in the population, 95percent of persons would vote to convict this defendant based on the evidence presented at trial, what is the probability that all 8 persons on an 8-person jury will vote to convict the defendant based on the evidence presented at trial, assuming that no juror influences the vote of any other juror? A. 0% B. 5% C. 23% D. 54% E. 66% F. 73 G. 100%

E. 66%

The probability of X happening is 10%,and the probability of Y happening is 10%. X and Y are not independent events. What is the probability that X and Y both occur? A. 1% B. 10% C. 20% D. 100% E. Cannot be determined from the information provided

E. Cannot be determined from the information provided

If the p-value for a test of a null hypothesis is p=0.99, then we should do which of the following? A. accept the null hypothesis and accept the alternative hypothesis B. reject the null hypothesis and reject the alternative hypothesis C. accept the null hypothesis and reject the alternative hypothesis D. reject the null hypothesis and accept the alternative hypothesis E. none of the above

E. none of the above