24.9 Is astrology scientific? The University of Chicago’s General Social Survey (GSS) is the nation’s most important social science sample survey. The GSS asked a random sample of adults their opinion about whether astrology is very or sort of scientific or not at all scientific. Is belief that astrology is scientific related to amount of higher education? Here is a two-
Degree Held | |||
Opinion | Junior college | Bachelor | Graduate |
Not at all scientific | 44 | 122 | 71 |
Very or sort of scientific | 31 | 62 | 27 |
Calculate percentages that describe the nature of the relationship between amount of higher education and opinion about whether astrology is very scientific or sort of scientific or not at all scientific. Give a brief summary in words.
24.9 Very or sort of scientific by degree held: Junior college 41.3%, Bachelor 33.7%, Graduate 27.6%. The data suggest that the more higher education received, the less likely the person is to believe that astrology is scientific.
24.10 Weight-
Age | Accidental | Not accidental | Total |
8– |
295 | 102 | 397 |
14– |
655 | 916 | 1571 |
19– |
239 | 533 | 772 |
23– |
363 | 1008 | 1371 |
Total | 1552 | 2559 | 4111 |
Calculate percentages that describe the nature of the relationship between age and whether the weight-
24.11 Smoking by students and their families. How are the smoking habits of students related to the smoking habits of their close family members? Here is a two-
Student smokes | Student does not smoke | |
At least one close family member smokes | 115 | 207 |
No close family member smokes | 25 | 75 |
Write a brief answer to the question posed, including a comparison of selected percentages.
24.11 At least one close family member smokes: 115/322 = 35.7%; No close family member smokes: 25/100 = 25%. In our sample, male students with at least one close family member who smokes are more likely to smoke than are male students with no close family member who smokes.
24.12 Smoking by parents of preschoolers. How are the smoking habits of parents of preschoolers related to the education of the father? Here is a two-
Both parents smoke | One parent smokes | Neither parent smokes | |
University education | 42 | 68 | 90 |
Intermediate education | 47 | 69 | 75 |
High school education | 183 | 281 | 273 |
Primary education or none | 69 | 73 | 62 |
Write a brief answer to the question posed, including a comparison of selected percentages.
24.13 Python eggs. How is the hatching of water python eggs influenced by the temperature of the snake’s nest? Researchers assigned newly laid eggs to one of three temperatures: hot, neutral (room temperature), or cold. Hot duplicates the extra warmth provided by the mother python, and cold duplicates the absence of the mother. Here are the data on the number of eggs and the number that hatched:
Eggs | Hatched | |
Cold | 27 | 16 |
Neutral | 56 | 38 |
Hot | 104 | 75 |
(a) Make a two-
(b) Calculate the percentage of eggs in each group that hatched. The researchers anticipated that eggs would not hatch in the cold environment. Do the data support that anticipation?
24.13 (a) Hatched: 16, 38, 75. Did not hatch: 11, 18, 29. (b) In order of increasing temperature, the percent hatched are 16/27 = 59.3%, 38/56 = 67.9%, 75/104 = 72.1%. The percent hatching increases with temperature; the cold water did not prevent hatching, but made it less likely.
24.14 Firearm violence. Here are counts from a study of firearm violence reported by the Annual Review of Public Health in 2015. In particular, we will examine homicides and suicides and whether a firearm was involved.
Firearm | No firearm | Total | |
Homicides | 8089 | 3533 | 11,622 |
Suicides | 10,519 | 10,147 | 20,666 |
(a) Make a bar graph to compare whether a firearm was used in homicides and suicides. What does the graph suggest about deaths involving long guns versus handguns?
(b) Calculate the percentage of homicides and suicides in which firearms were used. Comment on your findings.
24.15 Who earns academic degrees? How do women and men compare in the pursuit of academic degrees? The following table presents counts (in thousands), as projected by the National Center for Education Statistics, of degrees earned in 2015–
Associate’s | Bachelor’s | Master’s | Professional/doctorate | |
Female | 375 | 788 | 335 | 87 |
Male | 577 | 1059 | 467 | 92 |
Total | 952 | 1847 | 802 | 179 |
(a) How many total people are predicted to earn a degree in the 2015–
(b) How many people earned associate’s degrees?
(c) What percentage of each level of degree is earned by women? Write a brief description of what the data show about the relationship between sex and degree level.
24.15 (a) 3780. (b) 952. (c) Associate’s 39.4%, Bachelor’s 42.7%, Master’s 41.8%, Professional/Doctorate 48.6%. While all of the percents are under 50%, the higher degree levels tend to have a higher percent of female recipients.
24.16 Smokers rate their health. The University of Michigan Health and Retirement Study (HRS) surveys more than 22,000 Americans over the age of 50 every two years. A subsample of the HRS participated in a 2009 Internet-
Current smoker | ||
Health | Yes | No |
Excellent | 25 | 484 |
Very good | 115 | 1557 |
Good | 145 | 1309 |
Fair | 90 | 545 |
Poor | 29 | 11 |
Describe the differences between the distributions of health status for those who are and are not current smokers with percentages with a graph and in words.
24.17 Totals aren’t enough. Here are the row and column totals for a two-
a | b | 40 |
c | d | 60 |
60 | 40 | 100 |
Find two different sets of counts a, b, c, and d for the body of the table that give these same totals. This shows that the relationship between two variables cannot be obtained from the two individual distributions of the variables.
30 | 10 | 40 | 0 | |
30 | 30 | 20 | 40 |
24.18 Airline flight delays. Here are the numbers of flights on time and delayed for two airlines at five airports during a one-
Alaska Airlines | America West | |||
On time | Delayed | On time | Delayed | |
Los Angeles | 497 | 62 | 694 | 117 |
Phoenix | 221 | 12 | 4840 | 415 |
San Diego | 212 | 20 | 383 | 65 |
San Francisco | 503 | 102 | 320 | 129 |
Seattle | 1841 | 305 | 201 | 61 |
(a) What percentage of all Alaska Airlines flights were delayed? What percentage of all America West flights were delayed? These are the numbers usually reported.
(b) Now find the percentage of delayed flights for Alaska Airlines at each of the five airports. Do the same for America West.
(c) America West does worse at every one of the five airports, yet does better overall. That sounds impossible. Explain carefully, referring to the data, how this can happen. (The weather in Phoenix and Seattle lies behind this example of Simpson’s paradox.)
24.19 Bias in the jury pool? The New Zealand Department of Justice did a study of the composition of juries in court cases. Of interest was whether Maori, the indigenous people of New Zealand, were adequately represented in jury pools. Here are the results for two districts, Rotura and Nelson, in New Zealand (similar results were found in all districts):
Rotura | ||
---|---|---|
Maori | Non- |
|
In jury pool | 79 | 258 |
Not in jury pool | 8810 | 23,751 |
Total | 8889 | 24,009 |
Nelson | ||
---|---|---|
Maori | Non- |
|
In jury pool | 1 | 56 |
Not in jury pool | 1328 | 32,602 |
Total | 1329 | 32,658 |
(a) Use these data to make a two-
(b) Show that Simpson’s paradox holds: a higher percentage of Maori are in the jury pool overall, but for both districts, a higher percentage of non-
(c) Use the data to explain the paradox in language that a judge could understand.
24.19 (b) Overall, 0.8% of Maori and 0.6% of non-Maori were in the jury pool. However, for Rotura, the percents are 0.9% and 1.1%, respectively; for Nelson, they are 0.1% and 0.2%. (c) Overall, 0.8% of Maori serve on juries compared to 0.6% of non-Maoris. However, in each of the two districts, non-Maoris served at a higher rate than did Maoris.
24.20 Field goal shooting. Here are data on field goal shooting for two members of the Benedict College 2014–
Seth Fitzgerald | Roberto Mantovani | |||
Made | Missed | Made | Missed | |
Two- |
5 | 4 | 62 | 50 |
Three- |
3 | 3 | 1 | 4 |
(a) What percentage of all field goal attempts did Seth Fitzgerald make? What percentage of all field goal attempts did Roberto Mantovani make?
(b) Now find the percentage of all two-
(c) Roberto had a lower percentage for both types of field goals but had a better overall percentage. That sounds impossible. Explain carefully, referring to the data, how this can happen.
24.21 Smokers rate their health. Exercise 24.16 gives the responses of a survey of 4310 Americans to questions about their health and whether they currently smoke cigarettes.
(a) Do these data satisfy our guidelines for safe use of the chi-
(b) Is there a statistically significant relationship between smoking status and opinions about health?
24.21 (a) All expected counts are 1 or greater, and only 1 (10%) of the expected counts is less than 5, so the chi-square test is safe. (b) The chi-square statistic is 229.660, df = 4. This result is significant at α = 0.001 (and much smaller). There is a statistically significant relationship between smoking status and opinions about health.
24.22 Is astrology scientific? In Exercise 24.9, you described the relationship between belief that astrology is scientific and amount of higher education. Is the observed association between these variables statistically significant? To find out, proceed as follows.
(a) Add the row and column totals to the two-
(b) Find the chi-
(c) What are the degrees of freedom? Use Table 24.1 to say how significant the chi-
24.23 Smoking by students and their families. In Exercise 24.11, you saw that there is an association between smoking by close family members and smoking by high school students. The students are more likely to smoke if a close family member smokes. We want to know whether this association is statistically significant.
(a) State the hypotheses for the chi-
(b) Find the expected cell counts. Write a sentence that explains in simple language what “expected counts’’ are.
(c) Find the chi-
24.23 (a) The hypotheses are as follows:
H0 : There is no association between whether the student smokes and whether close family members smoke.
Ha : There is some association between whether the student smokes and whether close family members smoke.
Population is male students in secondary schools in Malaysia.
(b) The expected counts are 106.82, 215.18, 33.18, and 66.82. These are the counts we would expect—except for random variation—if H0 were true. (c) The chi-square statistic is 3.951, df = 1. This result is significant at the 5% level, but not 1%.
24.24 Python eggs. Exercise 24.13 presents data on the hatching of python eggs at three different temperatures. Does temperature have a significant effect on hatching? Write a clear summary of your work and your conclusion.
24.25 Stress and heart attacks. You read a newspaper article that describes a study of whether stress management can help reduce heart attacks. The 107 subjects all had reduced blood flow to the heart and so were at risk of a heart attack. They were assigned at random to three groups. The article goes on to say:
One group took a four-
In the next three years, only three of the 33 people in the stress management group suffered “cardiac events,’’ defined as a fatal or non-
(a) Use the information in the news article to make a two-
(b) What are the success rates of the three treatments in preventing cardiac events?
(c) Find the expected cell counts under the null hypothesis that there is no difference among the treatments. Verify that the expected counts meet our guideline for use of the chi-
(d) Is there a significant difference among the success rates for the three treatments?
24.25 (b) Stress management 90.9%, Exercise 79.4%, Usual Care 70%. (c) 6.79, 26.21, 6.99, 27.01, 8.22, 31.78. All expected counts are greater than 5, so the chi-square test is safe. (d) The chi-square statistic is 4.840, df = 2. This result is significant at the 10% level, but not 5%.
24.26 Standards for child care. Do unregulated providers of child care in their homes follow different health and safety practices in different cities? A study looked at people who regularly provided care for someone else’s children in poor areas of three cities. The numbers who required medical releases from parents to allow medical care in an emergency were 42 of 73 providers in Newark, New Jersey, 29 of 101 in Camden, New Jersey, and 48 of 107 in South Chicago, Illinois.
(a) Use the chi-
(b) How should the data be produced in order for your test to be valid? (In fact, the samples came in part from asking parents who were subjects in another study who provided their child care. The author of the study wisely did not use a statistical test. He wrote: “Application of conventional statistical procedures appropriate for random samples may produce biased and misleading results.’’)
EXPLORING THE WEB
Follow the QR code to access exercises.