American Journal of Orthodontics and Dentofacial Orthopedics
Online onlySample size estimation: An overview with applications to orthodontic clinical trial designs
Section snippets
Key factors in determining sample size
Before we proceed with sample calculations we must define the following13, 14: (1) the research question, (2) the principal outcome measure of the trial (ie, continuous or categorical), (3) the type of analysis and study design that will be used, (4) the expected proportion or mean value of the selected outcome in the comparison or control group, (5) the minimum clinically important difference between treatment arms that we would like to detect, (6) the variance (for continuous outcomes), and
Sample calculations for clinical trials: Parallel arm designs
First we will conduct a sample calculations for a trial with qualitative outcomes, a 1:1 allocation ratio, and a 2-sided test.
We are interested in conducting a trial to compare failures of lingual retainers bonded with chemically cured or a light-cured adhesive, and to determine whether there is a difference at the 0.05 statistical level with 90% power. The procedure for sample calculation for such a study will be as follows.
- 1.
We must decide what is an acceptable difference to be observed that is
The Altman nomogram
Altman17 created an easy-to-use nomogram for quick sample calculations for continuous outcomes for equal-size 2-arm trials. In Figure 3, on the left vertical line, is the effect size (standardized difference) for which the sample size is required at the prespecified significance level (shown on the diagonal line in the center) and power level (on the right vertical axis). The effect size in terms of the standardized difference is defined as the ratio of the minimum difference to be detected to
Other trial designs
In certain situations, it is possible to evaluate 2 or more interventions or parameters simultaneously in a single trial. This can be accomplished with a factorial design, which takes the form of 2 × 2 in the simplest form. The advantages of the factorial design are related to the fact that 2 or more parameters can be assessed at the same time, thus creating a more efficient trial in terms of resources, including sample size, compared with separate trials that assess each parameter. However,
Conclusions
- 1.
Sample calculations are an important part of solid clinical trial methodology.
- 2.
Sample calculations should balance scientific validity with feasibility.
- 3.
Important differences between intervention arms might go undetected only because sample size and power are low.
- 4.
Sample calculations make certain assumptions, and information from previous studies or pilots are helpful for reliable sample calculations.
- 5.
Trial design characteristics such as clustering and pairing should be considered during sample size
References (39)
- et al.
Assessing the quality of reports of randomized clinical trials: is blinding necessary?
Control Clin Trials
(1996) - et al.
An assessment of quality characteristics of randomised control trials published in dental journals
J Dent
(2010) - et al.
CONSORT 2010 explanation and elaboration: updated guidelines for reporting parallel group randomised trials
BMJ
(2010) - et al.
Systematic reviews in health care: assessing the quality of controlled clinical trials
BMJ
(2001) - et al.
Statistics notes: absence of evidence is not evidence of absence
BMJ
(1995) Clinical trials: a practical approach
(1983)- et al.
Reporting of sample size calculation in randomised controlled trials: review
BMJ
(2009) - et al.
The reporting of statistical inferences in selected prosthodontic journals
J Prosthodont
(1992) - et al.
The reporting of randomized controlled trials in prosthodontics
Int J Prosthodont
(2002) - et al.
The power of tests to detect differences between periodontal treatments in published studies
J Clin Periodontol
(1992)
Equivalence and superiority testing in regeneration clinical trials
J Periodontol
Reported methodological quality of split-mouth studies
J Clin Periodontol
Clinical trials: a practical approach
Sample size tables for clinical trials
The randomized clinical trial: bias in analysis
Circulation
Essential medical statistics
Statistics review 4: sample size calculations
Crit Care
Randomized clinical trials: design, practice and reporting
Cited by (0)
The authors report no commercial, proprietary, or financial interest in the products or companies described in this article.