|
Year |
2001 |
|---|---|
|
Question Number |
165. |
|
Category |
Select |
Question
A study is being designed to compare the results of two new drugs on bone mineral density. The number of subjects needed for this study should be determined by:
1- Student’s t test
2- Power analysis
3- Probability distribution
4- Regression analysis
5- Spearman rank correlation
Figures
Answer (click for answer)
Preferred response: 2.
Power analysis (AKA sample-size determination) is the process of calculating the power of a study. Power is defined as the probability of finding a significant association when one truly exists. The calculations for power analyses differ depending on the statistical method used for analysis; however, the variables involved in a power analysis include sample size, power, clinically important difference, alpha level, and variance. In the pre-hoc scenario, power is set at 80% and the alpha level is set at 0.05 by convention, the clinically important difference and the variance are estimated from pilot data or the literature, and the equation is solved for the necessary sample size.
Student’s t test is a statistical test for comparison of means between two independent groups. Probability distribution is an area under a curve indicating the likelihood that an event will occur (i.e. Bell shaped curve). Regression analysis is a multivariable method used to predict a dependent variable from independent variables. Spearman rank correlation is a statistical test for nonparametric variables.
Reference: Buckwalter JA, Einhorn TA, Simon SR (eds): Orthopedic Basic Science: Biology and Biomechanics of the Musculoskeletal System, ed 2. Rosemont, IL, AAOS, 2000, pp 2-17.