Premium
The design of an experiment using statistical power with a startlechamber study as an example
Author(s) -
Bittman Richard M.,
Carniello Michael L.
Publication year - 1990
Publication title -
journal of applied toxicology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.784
H-Index - 87
eISSN - 1099-1263
pISSN - 0260-437X
DOI - 10.1002/jat.2550100211
Subject(s) - statistical power , sample size determination , statistics , power (physics) , research design , power analysis , sampling (signal processing) , design of experiments , sensitivity (control systems) , computer science , reliability engineering , econometrics , mathematics , engineering , electronic engineering , telecommunications , physics , quantum mechanics , detector
Using a startle chamber experiment as a case study, it is shown how the sensitivity of a study's design can be quantified by using the concept of statistical power and how the design can be planned to achieve the power desired. The purpose of the experiment was to compare background responses in three empty startle chambers. The study design nested groups of noise events into trials, entailing two sources of experimental error, variation within trials and between trials. For this nested design, the proper statistical analysis and calculation of power are described. It is shown how the power depends on the numbers of trials and events per trial (sampling effort), magnitudes of the sources of variability and background differences to be detected. A worked example shows the power associated with several sampling alternatives. Associated implications for cost and benefit are also discussed.