| Sampling Type | Probability | What Is It? | How Useful |
|---|---|---|---|
| Random | yes | Randomly sample an area | Not efficient but sometimes useful in understanding a population |
| Systematic | yes | Sample every x feet, x minutes or on a grid | Provides a structure on where to sample, can spread out the measurements throughout time or space so more efficient than random. |
| Stratified | yes | Break things into groups, then randomly or systematically sample within the group | Can look at different parts of a system even though they might not occur equally in time in space. For example, you could sample during floods and between floods on a river. |
| Convenience | no | Sample one of the ways above, where you can. You don't have access to the entire population | Often in geology, we don't have full access to the population, so we don't know that our sample is representative of the population. It is often the best that we can do. |
Probability sample means that the sample is drawn from the entire population. Alternatively, a non-probability sample is not drawn from the entire population.
Before determining a sampling strategy, you need to think about two things:
- Does your sampling scheme allow you to answer your research question?
- Have you captured the sources of variability in your system? What are the main factors (land cover, climates, soils, etc.) that may cause a property or a process to vary?