How Many Subjects Should be Studied: Sample Size Determination through Hypothesis Testing and Confidence Interval

Waqas Sami; Mohammed O. Al-Rukban; Mohammed Almansour; Tayyaba Waqas; Kamran Afzal; Rehan Asad

Abstract

One of frequently asked question by health researchers is how many individuals will I need to study. Sample size determination is one of the central canons of health research. A study is always better when planned scientifically and determining the sample size for a study is a prime component as it will help to determine optimum number of subjects so that statistically significant results can be detected. If the sample size is larger than what is needed, the study will become cumbersome and ethically exorbitant. On the converse, using too few subjects' will eventually result in wasted time, effort and money etc. Literature is full of examples in which sample size is incorrectly determined for health studies thus resulting in bias conclusions. To ensure the reliability of the results, the significance level and power of study must be fixed before the sample size determination. Sample size determination is very important and always a difficult process to handle. It requires the collaboration of a specialist who has good scientific knowledge in the art and practice of medical statistics. There are numerous situations in which sample size is determined that varies from study to study. This article will focus on the sample size determination for hypothesis testing and confidence interval situations commonly used in health studies.

Keywords: Hypothesis testing · confidence interval · significance level · power of study · effect size · sample size

References

1.Waqas Sami, M. O. AlRukban, Tayyaba Waqas, Rehan Asad, Kamran Afzal. Sample size determination in health research. J Ayub Med Coll Abbottabad 2012; 24:4.
2.Feinstein AR. Principles of medical statistics. Boca Raton 2003, Fla: CRC; 503.
3.Moher D, Dulberg CS, Wells GA. Statistical power, sample size, and their reporting in randomized controlled trials. JAMA 1994; 272:122–124.
4.Naing, NN. Determination of sample size. Malaysian Journal of Medical Science 2003; 10(2): 84-86.
5.Uitenbroek DG. Sample size: SISA— simple interactive statistical analysis. Available at: http://home.clara.net/sisa/samsize.html Accessed March 3, 2003.
6.Armitage P, Berry G, Matthews JNS. 2002, Statistical Methods in Medical Research, 4th ed. Blackwell, Oxford. MAJMAAH J. HEALTH SCIENCES, 2013 – Vol. 1, No. 2
7.Naing L, Winn T and Rusli BN. Sample Size Calculator for Prevalence Studies. 2006. Available at: http://www.kck.usm.my/ppsg/stats_resourc es.htm
8.Bland M. An Introduction to Medical Statistics, 2000, 3rd. ed. Oxford University Press, Oxford.
9.Eng J. Sample size estimation: how many individuals should be studied? Radiology 2003; 227: 309–13.
10.Gerstman BB. Basic Biostatistics: statistics for public health practice: 2008. Jones and Bartlett Publishers, Sudbury, Massachusetts.
11.Van Belle G. Statistical Rules of Thumb. Wiley: 2002, New York, NY.
12.Moher D, Dulberg CS, Wells GA. Statistical Power, Sample Size, and Their Reporting in Randomized Controlled Trials. JAMA 1994; 272:122-124
13.Spiegelhalter DJ, Freedman LS, Parmar MKB. Bayesian approaches to randomized trials. In Bayesian Biostatistics. 1996, New York.
14.Fleiss JL. Statistical methods for rates and proportions. 2nd ed. New York, NY: Wiley, 1981; 45.
15.Casagrande JT, Pike MC, Smith PG. An improved approximate formula for calculating sample sizes for comparing two binomial distributions. Biometrics 1978;34: 483–6.
16.Gardner, MJ., Altman D.G. Statistics with confidence-confidence intervals and statistical guidelines. British Medical Journal 1986; 5:1-13.
17.Daniel WW. Biostatistics: A Foundation for Analysis in the Health Sciences. 1999, 7th edition. New York: John Wiley & Sons.
18.Lwanga, SK., and Lemeshow, S. Sample size determination in health studies: A practical manual. 1991, World Health Organization, Geneva.
19.Chan YH. Randomized Control Trials: The magic number. Singapore Med J 2003; vol 44(4): 172 – 174.
20.Schulz KF, Grimes DA. Sample size calculations in randomized trials: mandatory and mystical. Lancet 2005; 365: 1348–53. How Many Subjects Should Be Studied, Waqas Sami, et al. 48