Confidence intervals for effect sizes (CIES) provide readers with an estimate of the strength of a reported statistic as well as the relative precision of the point estimate. These statistics offer more information and context than null hypothesis statistic testing. Although confidence intervals have been recommended by scholars for many years, these statistics are often not reported. This may be partially due to the complexity of calculating confidence intervals for many statistics. Bootstrap resampling can be used to easily estimate confidence intervals around almost any type of point estimate. The aim of this paper is to demonstrate this methodology using real-world data and to develop several simple principles around this methodology to guide readers in appropriate application Accessed 9,491 times on https://pareonline.net from March 11, 2016 to December 31, 2019. For downloads from January 1, 2020 forward, please click on the PlumX Metrics link to the right.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Banjanovic, Erin S. and Osborne, Jason W.
"Confidence Intervals for Effect Sizes: Applying Bootstrap Resampling,"
Practical Assessment, Research, and Evaluation: Vol. 21
, Article 5.
Available at: https://scholarworks.umass.edu/pare/vol21/iss1/5