Sampling

January 29, 2019

When it comes to research, how you gather data is as important as what data you decide to gather. Welcome to the world of sampling.

Let’s say you want to find out what Miami University undergraduate students think about Hypercolor clothing. In order to find out, you decide to ask your closest friends who all know you like the way Hypercolor highlights your armpits when you get hot. Do you think your buddies are going to shoot straight with you and say they think you look silly with bright yellow pits? Probably not. Your sample of convenience (your buddies) is a biased sample and not the best way to go about finding an objective answer to the Hypercolor quandary. Now, if you asked completely random undergraduate students at Miami, you’d be more likely to get objective opinions.

Sampling is essential because it will shape the answers you’ll get which will affect the validity of your results. Here’s a video that shares some insights on different sampling methods.

The video covers some of the most common sampling methods:

  • Convenience Sample
  • Voluntary Response Sample
  • Simple Random Sampling
  • Multistage Sampling
  • Stratified Random Sampling

Depending on the type of information you want to learn, other sampling methods may make sense. For instance:

  • Snowball or Network Sampling: The initial point of contact for the research identifies someone else they know to include in the study. This continues person-by-person through peoples’ social networks. The result is a sample that follows existing networks.

Learn the sampling methods and know when to use them. Sometimes a biased method may be okay, but shoot for that unbiased method to get responses that are more likely to be objective. 

More Resources on Sampling

How many people/instances you need in a sample to reach a solid conclusion? This is a pretty common question and it’s a good one.

Here’s another nice tutorial on sampling that includes cluster sampling.

Bounding a Population

This video uses a clear example to walk through the steps of bounding a population, selecting a sampling method, and determining sample size.

More Sources

Methods of sampling from a population – HealthKnowledge

dennischeatham

Associate Professor

Miami University