의학연구에서 표본크기 계산 = Sample Size Calculation in Medical Research

다국어 초록 (Multilingual Abstract)

Whenever planning a study design or preparing a research proposal it is highly recommended that investigators decide the optimum sample size that is required to yield an outcome of interest with a predetermined level of precision. This is because that, all else being equal, if a study with less than the optimum sample size would not detect the significance of differences in reality, and similarly, if a study with more than the optimum sample size will be costly. For these reasons, the majority of peer reviewed biomedical journals assess the adequacy of sample size requirements. The calculated sample size is used as a target number of samples to be collected to provide an estimate of the parameter with the desired and predetermined level of accuracy, and the sample size is a major determinant of the probability of detecting diseased animals from the population. There is no single method of calculating sample size for any given study design. In this context, the purpose of this article is to provide a collection of formulas and examples for some typical situations likely to be encountered in veterinary clinical practice and to highlight the importance of performing prospective sample size calculations when planning a research. Specifically, this paper is concerned with the basic principle of sample size calculation, and considerations for methodological applications were illustrated for a given data set. Also included in this paper is factors influencing sample size calculations using a statistically valid techniques. Appropriate methods to consider these factors are presented.

참고문헌 (Reference)

1 박선일, "자료 분석의 기초" 한국임상수의학회 26 (26): 189-199, 2009

2 ICMJE, "Uniform requirements for manuscripts submitted to biomedical journals: writing and editing for biomedical publication"

3 Moher D, "The CONSORT statement: revised recommendations for improving the quality of reports of parallel-group randomized trials" 357 : 1191-1194, 2001

4 McDermott JJ, "Study design and analytic methods for data collected from clusters of animals" 18 : 175-191, 1994

5 Whitley E, "Statistics review 4: Sample size calculations" 6 : 335-341, 2002

6 Evans RB, "Statistics and evidence-based veterinary medicine: answers to 21 common statistical questions that arise from reading scientific manuscripts" 37 : 477-486, 2007

7 Christley RM, "Statistical significance, power and sample size- what does it all mean?" 49 : 263-, 2008

8 Snedecor GW, "Statistical methods" Iowa State Press 1-503, 1989

9 Anonymous, "Statistical guidelines for authors" 15 : 51-, 2008

10 Cochran WG., "Sampling techniques" Wiley & Sons 1-428, 1977

11 Machin D, "Sample size tables for clinical studies" BMJ Books 1-264, 2008

12 Florey C., "Sample size for beginners" 306 : 1181-1184, 1993

13 Lwanga SK, "Sample size determination in health studies - A practical manual" World Health Organization 1-80, 1991

14 Hofmeister EH, "Sample size and statistical power in the small-animal analgesia literature" 48 : 76-79, 2007

15 Dell RB, "Sample Size Determination" 43 : 207-213, 2002

16 Cummings P, "Reporting statistical information in medical journal articles" 157 : 321-324, 2003

17 Diwan VK, "Randomization by group in studying the effect of drug information in primary care" 21 : 124-130, 1992

18 Naing L, "Practical Issues in calculating the sample size for prevalence studies" 1 : 9-14, 2006

19 Fosgate GT, "Modified exact sample size for a binomial proportion with special emphasis on diagnostic test parameter estimation" 24 : 2857-2866, 2005

20 Berry G, "Mid-P confidence intervals: a brief review" 44 : 417-423, 1995

21 Arkin CF, "How many patients are necessary to assess test performance?" 263 : 275-278, 1990

22 Altman DG., "How large a sample?, In Statistics in practice" British MedicalAssociation 6-8, 1982

23 Martin SW, "Evaluating the health status of herds based on tests applied to individuals" 14 : 33-43, 1992

24 Campbell MJ, "Estimating sample sizes for binary, ordered categorical, and continuous outcomes in two group comparisons" 311 : 1145-1148, 1995

25 Daly LE., "Confidence intervals and sample sizes: don't throw out all your old sample size tables" 302 : 333-336, 1991

26 Kojima T, "Changes in the ethos of medical publications as reflected in progressive alterations in the uniform requirements for manuscripts submitted to biomedical journals (1979-2008)" 137 : 1479-1482, 2010

27 Jones SR, "An introduction to power and sample size estimation" 20 : 453-458, 2003

28 Ukoumunne OC, "A comparison of confidence interval methods for the intraclass correlation coefficient in cluster randomized trials" 21 : 3757-3774, 2002