B. Samples and Sampling

Extension/Questions

A survey is carried out at a university to estimate the percentage of undergraduates living at home during the current semester. The university's registrar keeps an alphabetical list of all undergraduates, with their current addresses. Suppose there are 10,000 undergraduates registered in the semester during which this research is conducted. Someone proposes to choose a number at random between one and one hundred, count that far down the list, then take that name and every hundredth name after it for the
sample.

  1. What will the sample size be?
  2. Is this a probability method? Is it the same as simple random sampling
  3. Assume now that the registrar's list is not alphabetical, but rather ordered by GPA (from low to high). Would this method of sampling be adequate?

  4. Someone else proposes to go out and take the first hundred undergraduates she sees as the sample.

  5. Is this a probability method? Is it the same as simple random sampling?

Part 2

Earlier in the lesson, you saw that opinion polling firms and news organizations use sampling to create a small group of individuals whose opinions reflect broader national sentiment on some topic or set of issues. One news organization that uses different forms of sampling in their news coverage is NBC/MSNBC. Please follow this link to ABC News that describes the methodologies they use in their polls, live votes, and surveys.

Based on this description, please answer the following questions.

  1. Of the types of sampling described in this lesson, which type best describes the methodology of the NBC News-Wall Street Journal poll? Please indicate whether it was a probability or non-probability sample and what particular sampling strategy this represents.
  2. Of the types of sampling described in this lesson, which type best describes the methodology of the MSNBC Live Votes poll? Please indicate whether it was a probability or non-probability sample and what particular sampling strategy this represents.