Objectives

  1. Identify and utilize a simple random sample
  2. Identify sources of possible bias in sampling strategies

Key vocabulary

  1. A simple random sample is a sample is a subset drawn from the population where each observation from the population is equally likley to be included in the sample.
  2. A biased sample is a sample where some members of the population are more or less likely to be included in our sample
  3. Convenience bias is a bias that arises because some members of the sample are more convenient to include than others.
  4. Volunteer bias arises when some people from the population voluntarily join the sample with higher probability than others.
  5. Non-response bias arises wen some individuals selected for the sample fail to show up or respond
  6. Response bias refers to a broad range of factors that influence how a person responds, such as question wording, question order, and influence of the interviewer.

Case study 1: GPA and sampling

You want to estimate the average GPA at SMART but don’t want to survey everyone at the school so you decide to take a simple random sample.

  1. Propose a method which will generate a simple random sample.
  2. Propose a sample which will produce a biased sample.

Case study 2: Marijuana usage and simple random sampling

You are interested in estimating the percentage of people in Denver that use recreational Marijuana so you decide to take a simple random sample. You decide you will do this by going to reggae fest 2015 and asking whether or not those people use recreational Marijuana.

  1. Do you think that this sampling strategy will generate a sample that is representative of the average Denver resident? Why or why not?
  2. What sort of bias does this strategy introduce?
  3. Propose a better sampling strategy that will be more representative of Denver residents.

Case study 3: Cars and gas mileage

You are interested in estimating the average gas mileage for all cars on the road but you don’t want to measure every car’s gas mileage so you take a simple random sample of 75 cars.

  1. Propose a sampling strategy which would generate a simple random sample.
  2. Propose a sampling strategy that would introduce bias into the sample.