November 13th, 2014

Today we discussed bias in sampling. This might be caused by:

• The sample being non-random
• A small sample
• Leading questions
• Dishonesty
• Perhaps not using a 'Blind Test'

HW: Explain 5 reasons why a survey might be biased.

A Small Sample Size Lacks Representation:
A small sample size may result in the lack of statistical representation of a phenomenon. For example, a researcher performs a study of transportation behaviors to find out what percentage of college students in a particular city take the bus to school. If her study includes a small sample size of 10 people and those 10 people all walk, bicycle or drive to school, then her sample size has failed to represent those who take the bus. Lack of representation as a result of small sample size becomes particularly evident when attempting to study phenomena that occur infrequently.