You are looking at the difference in minutes of TV watched between girls and boy

Question

You are looking at the difference in minutes of TV watched between girls and boys A statistical test of this difference lead to a P-value of 0.08. Your friend wondered if this study just wasn't highly powered. What is the most efficeint way to understand if the study was underpowered or not? Choose from the following options.

A.) Figure out the size of the difference. If it is small then the study was under powered.

B.) Calculate the 95% confidence interval to figure out whether it contains any clinically meaningful results or not

C.) Calculate the post-hoc power (or the power you have to detect the difference you observed). If it is low then your study was under powered

Explanation / Answer

Answer is B.

Post-hoc power analysis on an under-powered study can let you plan for a new, better-designed study.

To determine whether the study were underpowered, I would not do a post-hoc power analysis. I would look at the confidence interval of the non-significant result. A broad confidence interval which contains values that could be meaningful indicates an underpowered study. A narrow confidence interval where the extremes are so close to zero as to have little visible impact tells me that the study was not underpowered, it just looked for something that was not there.

Related Questions

Navigate

• Browse (All)
• Browse Y
• Subjects

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.