Exercise 11. To review the concepts of standard error and 95% confidence interval (Cl), see the Statistical Guide for Exer- cise 35. While the guide for Exercise 35 deals with how these statistics apply to means, the guide- lines for that exercise also apply to the interpretation of standard errors for medians and the associ- ated confidence intervals. As you may recall from Exercise 36, for a 68% confidence interval, add the standard error of the mean to determine the upper limit, and then subtract the standard error of the mean to determine the lower limit. The same procedure applies to medians.

Excerpt from the Research Article1:

We recruited 445 men and women who were homeless and without kin from the municipal shelter care system for homeless adults in New York City. [After voluntary informed consent was obtained], participants were carefully tracked throughout the 18-month follow-up period to document the number of days spent [homeless].

Part A : Factual Questions

1. On the average, did younger or older participants remain homeless a larger number of days? Explain.

2. What percentage of the males spent less than 188 days homeless? Explain the basis for your answer.

3. What percentage of the males spent more than 188 days homeless? Explain the basis for your answer.

4. What are the limits of the 68% Cl for females on the number of days homeless?

5. What are the limits of the 95% Cl for females on the number of days homeless?

6. What is the median for number of days homeless for veterans?

7. What are the limits of the 68% Cl for those with more than a high school education?

8. What are the limits of the 95% Cl for those with more than a high school education?

Part B: Questionsfor Discussion

9. Compare your answers to Questions 4 and 5. If your answers are correct, the 95% confidence interval is larger than the 68% confidence interval. Does this make sense? Explain.

Exercise 60 Duration of Homelessness: Standard Error of the Median and 68% and 95% Confidence Intervals

10. In your opinion, do the statistics suggest that "Past employment status" is predictive of the dura- tion of homelessness?

11. In their research article, the researchers refer to their study as a "preliminary study." In your opinion, what aspects of the study, if any, qualify it as preliminary?

12. Are the results of this study interesting or surprising to you? Explain.