Sample size calculations for the design of health studies: a review of key concepts for non-statisticians
Alistair Merrifield A C and Wayne Smith B
+ Author Affiliations
- Author Affiliations
A Centre for Epidemiology and Evidence, NSW Ministry of Health
B Environmental Health Branch, NSW Ministry of Health
C Corresponding author. Email: amerr@doh.health.nsw.gov.au
NSW Public Health Bulletin 23(8) 142-147 https://doi.org/10.1071/NB11017
Published: 21 September 2012
Abstract
Sample size calculations before conducting a health study or clinical trial are important to provide evidence that the proposed study is capable of detecting real associations between study factors. This review aims to clarify statistical issues related to the calculation of sample sizes and is illustrated with an example of a recent study design to improve health outcomes related to water and sewage in NSW Aboriginal communities. The effect of power, significance level and effect size on sample size are discussed. Calculations of sample sizes for individual-based studies are modified for more complex trial designs by multiplying individual-based estimates by an inflationary factor.
References
[1] Whitley E, Ball J. Statistics review 4: Sample size calculations. Crit Care 2002; 6 335–41.| Statistics review 4: Sample size calculations.Crossref | GoogleScholarGoogle Scholar |
[2] Kirby A, Gebski V, Keech AC. Determining the sample size in a clinical trial. Med J Aust 2002; 177 256–7.
[3] Campbell MK, Thomson S, Ramsay CR, MacLennan GS, Grimshaw JM. Sample size calculator for cluster randomised trials. Comput Biol Med 2004; 34 113–25.
| Sample size calculator for cluster randomised trials.Crossref | GoogleScholarGoogle Scholar |
[4] Wittes J. Sample size calculations for randomised controlled trials. Epidemiol Rev 2002; 24 39–53.
| Sample size calculations for randomised controlled trials.Crossref | GoogleScholarGoogle Scholar |
[5] Campbell MJ, Julious SA, Altman DG. Estimating sample sizes for binary, ordered categorical, and continuous outcomes in two group comparisons. BMJ 1995; 311 1145–8.
| Estimating sample sizes for binary, ordered categorical, and continuous outcomes in two group comparisons.Crossref | GoogleScholarGoogle Scholar | 1:STN:280:DyaK28%2FkvVymug%3D%3D&md5=f544488e7eae9a83d4c9bba9617ff358CAS |
[6] Closing the gap: 10 years of Housing for Health in NSW. An evaluation of a healthy housing intervention. Aboriginal Environmental Health Unit, NSW Health. 2010. Available from: http://www.health.nsw.gov.au/pubs/2010/pdf/housing_health_010210.pdf (Cited 12 August 2011).
[7] Eldridge SM, Ashby D, Kerry S. Sample size for cluster randomised trials: effect of coefficient of variation of cluster size and analysis method. Int J Epidemiol 2006; 35 1292–300.
| Sample size for cluster randomised trials: effect of coefficient of variation of cluster size and analysis method.Crossref | GoogleScholarGoogle Scholar |
[8] Bland JM, Kerry SM. Statistics notes: trials randomised in clusters. BMJ 1997; 315 600
| Statistics notes: trials randomised in clusters.Crossref | GoogleScholarGoogle Scholar | 1:STN:280:DyaK2svkvVKgtA%3D%3D&md5=8b38f1237f4868473f820274de912652CAS |
[9] Kerry SM, Bland JM. Statistics notes: sample size in cluster randomisation. BMJ 1998; 316 549
| Statistics notes: sample size in cluster randomisation.Crossref | GoogleScholarGoogle Scholar | 1:STN:280:DyaK1c7mt1entg%3D%3D&md5=d35d444fa35ceacee97f36ca07b6e1fcCAS |
[10] Kerry SM, Bland JM. Statistics notes: analysis of a trial randomised in clusters. BMJ 1998; 316 54
| Statistics notes: analysis of a trial randomised in clusters.Crossref | GoogleScholarGoogle Scholar | 1:STN:280:DyaK1c7htlWjsw%3D%3D&md5=47db8005e60f73cf5b39182f72e01735CAS |
[11] Kerry SM, Bland JM. Statistics notes: the intracluster correlation coefficient in cluster randomisation. BMJ 1998; 316 1455
| Statistics notes: the intracluster correlation coefficient in cluster randomisation.Crossref | GoogleScholarGoogle Scholar | 1:STN:280:DyaK1c3jvFKisQ%3D%3D&md5=f09d7349ab21f74c596e18c9e2cded3cCAS |
[12] Knox SA, Chrondros P. Observed intra-cluster correlation coefficients in a cluster survey sample of patient encounters in general practice in Australia. BMC Med Res Methodol 2004; 4 30
| Observed intra-cluster correlation coefficients in a cluster survey sample of patient encounters in general practice in Australia.Crossref | GoogleScholarGoogle Scholar |
[13] Mickey RM, Goodwin GD. The magnitude and variability of design effects for community intervention studies. Am J Epidemiol 1993; 137 9–18.
| 1:STN:280:DyaK3s7mslagsQ%3D%3D&md5=b71c7409b642a817236bd61a3229f114CAS |
[14] Ridout MS, Demétrio CG, Firth D. Estimating intraclass correlation for binary data. Biometrics 1999; 55 137–48.
| Estimating intraclass correlation for binary data.Crossref | GoogleScholarGoogle Scholar | 1:STN:280:DC%2BD3M3ntV2qtQ%3D%3D&md5=8302250fb3a75f4fa24a7c83fcfcdf63CAS |
