大至急お願い致します！課題の意味が全く分かりません
1. Context and Divorce Rates
Each person belongs to at least three groups - a cohort, a culture, and a socioeconomic group - that tend to guide his or her life path by influencing the context in which development occurs.
To highlight the impact of context on development, consider a Census Bureau study that tracked tens of thousands of families over two-year periods between 1983 and 1988. The study found that married couples below the federal poverty line separated or divorced nearly twice as often (one out of seven) as those above the poverty line (one out of thirteen). African American families were hardest hit by low socioeconomic status, as 1 out of 5 African American couples split up during the study, compared to 1 out of 8 white couples and 1 out of 9 Hispanic couples. "It appears that stresses arising from low income and poverty may have contributed substantially to breakups of parents," said the study's senior author, Donald Hernandez.
The Census Bureau study also found that when a marriage breaks up, three times out of four a mother and her children who formerly were above the poverty line, fall below it. In 1970, 90% of households consisted of both biological parents and their children; by 1990, that number had dropped to 75%.
Another good example of the impact of context on development concerns the consequences of divorce on the children's later marriages. A recent study reports that children of divorced parents are less likely to divorce than their counterparts one generation ago. Before 1975, children from divorced families were 2.5 times more likely to divorce than their counterparts from intact families; by 1996, this rate had dropped to 1.4.
A final example of the impact of context on development is the strong association between marital status and nearly any measure of health, including mortality rates. And examination of age-adjusted death rates shows that adults who never married have the highest death rate, followed by those widowed, divorced, and married. Those never married have a 79% higher mortality rate than those widowed or divorced, and 2.2 times the mortality rate of those who are currently married. Adults who are widowed or divorced have age-adjusted death rates that are 86% and 78% higher, respectively, than for those who were married at the time of their death.
In your report to me, address each of these issues:
1.All of these examples are correlations. Discuss each of these examples in terms of the risks associated with drawing causal conclusions from correlational data.
2.Explain the context effects that may account for the differences described in each example. That is, what factors from the environment might have contributed to the behavior being described?
3.In each case, the researchers were trying to find a single causation for a multiply-caused effect. Identify the evidence for that.
4.In the first and fourth examples, the researchers controlled for at least one other variable besides the one of interest. Identify the variable(s) in each of those examples.
2. Estimating the Effect of Test Error: The Base-rate Fallacy
Begin by reading these two articles, which constitute a series about probabilistic reasoning:
http://www.scientificamerican.com/article.cfm?id=why-our-brains-do-not-intuitively-grasp-probabilities
http://www.scientificamerican.com/article.cfm?id=how-randomness-rules-our-world
Now, apply your knowledge from these articles and from Chapter 10 of the text.
Although a 70 percent rate of accuracy for the polygraph may sound pretty good, the text shows that it is not. For example, if 5 percent of 1000 employees are guilty of misconduct, and all are given the test, 285 innocent employees will be wrongly accused. Please avoid the base-rate fallacy while considering the following example:
In your report to me: Explain your reasoning and tie your discussion to evidence from the text and the articles about probabilistic reasoning.
お礼
ありがとうございました。 とりあえず、このTheoryについていくつか文献を探してから（これが難しいのですが）、考えてみます。