solutions5

solutions5 - Stat 651 (Winter 2011) Kaizar Homework 5...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

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

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Stat 651 (Winter 2011) Kaizar Homework 5 Solutions 40 points total Exercises 1. (10 points) Chapter 5, question 2 (a) Cluster sampling is when you divide the population of interest into groups, and then only sample some of those groups. In this case, the population is all the households in Chicago. The researcher divided these up into clinics and parents, and then only questioned some of these parents. Thus, this is a cluster sample. • PSU = Clinic • SSU = parent This is a one-stage cluster sample, since all the parents in the selected clinics were questioned. Since I do not know the total number of households in the population, I would have to use ratio estimation to estimate the percentage and standard error. (b) The sampling population in this study is all parents who were in Chicago during that week and would possibly take their child to a clinic. This is probably not a representative sample, since it will likely oversample those households with lower incomes (who use clinics instead of more traditional PCPs), and will possibly sample some households twice (for example if both parents attend the clinic with their child). 2. (10 points) Chapter 5, question 4 • Cluster sampling is when you divide the population of interest into groups, and then only sample some of those groups. In this case, the population is all the articles in all the selected journals. The researcher divided these up into issues, and then sampled only some of the issues. Thus, this is a cluster sample. • Since I don’t know the total number of journal articles, I can not use unbiased estimation. I need to use ratio estimation. Further, note that the sample includes 10 journal issues that do not contain any articles that use sampling. We can think about this two ways. First, we could note that this is a case of domain estimation, which (remember) is a special case of ratio estimation. Since we are already doing ratio estimation, we wouldn’t need to worry about it.we are already doing ratio estimation, we wouldn’t need to worry about it....
View Full Document

This note was uploaded on 07/26/2011 for the course STA 651 taught by Professor Kaizar during the Winter '11 term at Ohio State.

Page1 / 7

solutions5 - Stat 651 (Winter 2011) Kaizar Homework 5...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online