Convenience Samples - You use an intact group like a class. This is very easy to do. For example, a class of psychology students may be OK if you are studying dark adaptation but this sample would certainly not be representative of people on the minimum wage.

Probability Samples - Probability samples are more likely to represent the population than non-probability samples. When using a probability sampling strategy, your fist step is to identify the population and its sampling frame. The sampling frame is usually some type of list or directory (eg. Phone book, clinic records, census tracts). Those selected into the sample are called elements. Use one of the following methods to select your sample. It is hoped that the smaller group will mirror the larger group. Techniques exist to calculate the number of subjects needed to give a reasonable confidence interval for your estimate.