Assessing statistical significance in study results: Relationship between 95% confidence intervals, p-values, and power

This figure depicts results from 3 hypothetical trials to demonstrate the relationship between 95% CIs, p-values, and statistical power. CIs and p-values are used to determine whether findings in research studies are statistically significant. The typical threshold used is a p-value of 0.05 (and corresponding 95% CIs). However, this threshold is somewhat arbitrary. Refer to UpToDate topic on hypothesis testing and p-values for additional information.