Sample size estimation: an overview with applications to orthodontic clinical trial designs

Pandis, Nikolaos; Polychronopoulou, Argy; Eliades, Theodore (2011). Sample size estimation: an overview with applications to orthodontic clinical trial designs. American journal of orthodontics and dentofacial orthopedics, 140(4), e141-6. St. Louis, Mo.: Mosby 10.1016/j.ajodo.2011.04.021

Full text not available from this repository. (Request a copy)

Proper sample size estimation is an important part of clinical trial methodology and closely related to the precision and power of the trial's results. Trials with sufficient sample sizes are scientifically and ethically justified and more credible compared with trials with insufficient sizes. Planning clinical trials with inadequate sample sizes might be considered as a waste of time and resources, as well as unethical, since patients might be enrolled in a study in which the expected results will not be trusted and are unlikely to have an impact on clinical practice. Because of the low emphasis of sample size calculation in clinical trials in orthodontics, it is the objective of this article to introduce the orthodontic clinician to the importance and the general principles of sample size calculations for randomized controlled trials to serve as guidance for study designs and as a tool for quality assessment when reviewing published clinical trials in our specialty. Examples of calculations are shown for 2-arm parallel trials applicable to orthodontics. The working examples are analyzed, and the implications of design or inherent complexities in each category are discussed.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > School of Dental Medicine > Department of Orthodontics

UniBE Contributor:

Pandis, Nikolaos

ISSN:

0889-5406

Publisher:

Mosby

Language:

English

Submitter:

Eveline Carmen Schuler

Date Deposited:

04 Oct 2013 14:16

Last Modified:

25 Jan 2017 12:16

Publisher DOI:

10.1016/j.ajodo.2011.04.021

PubMed ID:

21967951

Web of Science ID:

000295874800001

URI:

https://boris.unibe.ch/id/eprint/4413 (FactScience: 208614)

Actions (login required)

Edit item Edit item
Provide Feedback