PSYC 251 Lecture Notes - Lecture 5: List Of Disney Comics By Carl Barks, Stratified Sampling, Cluster Sampling
Document Summary
The group you wish to make generalizations about - often everyone. A subset of the population, our participants constitute our sample. Samples are representative of a population to the degree that they reflect a microcosm of the population. With a representative sample we can conclude that the patterns we see in the sample will translate well to the larger population. Biased or unrepresentative samples occur when we sample poorly. Every member of the population has an equal chance of being selected. On average leads to the most representative, accurate sample. Great in theory but realistically very hard (if not impossible) to implement. Opposite end of the spectrum, we simply sample those that are easy to get access to. Unfortunately a technique commonly used in psychology research due to practical limitations. Not completely invalid but definitely introduces limitations. Population is divided into sub-groups and samples are drawn such that they have the same relative sub-group sizes as population.