ps3_soln

# ps3_soln - BE.104 Spring Problem Set 3 Answers Sherley See...

This preview shows pages 1–3. Sign up to view the full content.

BE.104 Spring Problem Set 3 Answers Sherley See Table III from the Feb. 25, 2005 issue of Mortality Morbidity Weekly Report (Vol 54, p. 191). http://www.cdc.gov/mmwr/mmwr_wk.html 1) Generate a frequency histogram for all deaths (i.e., "All Ages" entries) in the listed cities. What should you do with the “U”’s? Answer: 0.5pt 0 5 10 15 20 25 30 35 Count 0 500 1000 1500 2000 All Deaths Answer: 0.25pt Nothing. There is no data, which is not the same as a zero. The information is not known. 2) Describe the distribution. Answer: 0.25pt Skewed 3) Suggest at least 3 distinct classes of “processes or factors” that might yield this distribution. Justify your answers. Will a similar distribution occur next week? Answers (any 3 are acceptable, including multiple versions of c): 1.5pts (0.5pt for each) a) Difference in population of cities. Number of deaths will have some relationship to number of individuals. If the distribution of population size among the cities is skewed, then the distribution of deaths might be skewed accordingly b) Differences in the age distribution of cities. Older individuals have a higher risk of dying. If the median age of the cities is not normally distributed, then the distribution of deaths might be skewed accordingly c) There may be other factors such as crowding, poor sanitation, or population demographics (which may be related or unrelated to population size) that result in a skewed distribution of deaths. d) This group of cities is self-selected. This selection bias may lead to a non-normal distribution of deaths. Answer: 0.25pt Yes, given that the same cities will be reporting, and the responsible factors are likely to be chronic , it is probable that the similar distribution will occur each week (and it does!).

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
4) Generate a new distribution based on the log(X), where X = the number of deaths for each city. Describe the log-transformed distribution.
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 11/11/2011 for the course BIO 20.010j taught by Professor Lindagriffith during the Spring '06 term at MIT.

### Page1 / 5

ps3_soln - BE.104 Spring Problem Set 3 Answers Sherley See...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online