How large a sample does the analyst need?
The determination of sample size is a function of many factors, including the variance in the data, the size of the effect that is being investigated, the assigned probabilities of making statistical type I and II errors, and sampling variability. There is not a standard or cook book answer for determining sample size, especially for complex studies with many objectives found commonly in transportation research. Generally, sample size is back-calculated using information obtained from past studies, a pilot study, or other methods for obtaining estimates of effect-size and sample variance. There are many good references on sample size determination that can aid the analyst through the design of a particular study.
