Sample size and statistical power consideration for diagnostic test research

  • Kim, Eu Tteum (School of Veterinary Medicine and Institute of Veterinary Science, Kangwon National University) ;
  • Park, Choi Kyu (National Veterinary Research and Quarantine Service) ;
  • Pak, Son Il (School of Veterinary Medicine and Institute of Veterinary Science, Kangwon National University)
  • Accepted : 2008.09.19
  • Published : 2008.12.01

Abstract

Although power analysis is of important tool of research, investigators in veterinary medicine are unaware of the concepts of the statistical power. Two types of error occur in classical hypothesis testing and, those errors should be avoided, if possible. Since power is highly dependent on the sample size, whenever declaring non-statistically significant result they should consider the potential for committing a Type II error in their studies, which refers to the probability of falsely stating that two treatments are equivalent despite true difference between them. Also, sample size determination is one of the most important tasks facing the researcher when planning a diagnostic study, and provides valuable information on the characteristics of a test performance. This type of analysis forms the basis for proper interpretation of test results. The aim of this article was to re-evaluate some selected studies on diagnostic test reported in the domestic veterinary publications to determine the power and necessary sample size for inequality testing to ensure the desired power. Power calculations were illustrated using real-life examples of comparison of a new test and a reference test for detecting antibodies of various animal diseases. Factors affecting to the power were also discussed.

Acknowledgement

Supported by : Ministry of Food, Agriculture, Forestry and Fisheries

References

  1. Jun M, Kim D, An S, Lee J, Min W. Application of monoclonal antibody to develop diagnostic techniques for infectious bovine rhinotracheitis virus. II. Diagnosis of infectious bovine rhinotracheitis by using monoclonal antibody. Korean J Vet Res 1989, 29, 27-35
  2. Suh M, Joo H, Maass D. Development of diagnostic kit (Test-MT) for the microplate latex agglutination test of toxoplasmosis in animal. Korean J Vet Res 1995, 35, 583-593
  3. Park C, Lyoo Y, Lee C, Jung J. Comparison between indirect immunofluorescent antibody (IFA) test and enzyme-linked immunosorbent assay (ELlSA) for the detection of antibody to porcine reproductive and respiratory syndrome virus (PRRSV). Korean J Vet Res 1998, 38, 314-318
  4. Borm GF, Houben RM, Welsiog PM, Zielhuis GA. An investigation of clinical studies suggests those with multiple objectives should have at least 90'% power for each endpoint. J Clin Epidemiol 2006, 59, 1-6 https://doi.org/10.1016/j.jclinepi.2005.03.020
  5. Breau RH, Carnat TA, Gaboury I. Inadequate statistical power of negative clinical trials in urological literature. J Urol 2006, 176, 263-266 https://doi.org/10.1016/S0022-5347(06)00505-2
  6. Shringi S, Shringi SN. Comparotive efficacy of standard AGID. CCIE and competitive ELISA for detecting bluetongue virus antibodies in indigenous breeds of sheep and goots in Rajasthan, India. J Vet Sci 2005, 6, 71-79
  7. Cho D, Kim Y, Wee S, Cho M, Kweon C, Kang Y, Park Y, Cho S. Development of competitive enzyme linked immunosorbent assay for detection of Coxiella burnetti antibody in animal. Korean J Vet Res 2000, 40, 81-85
  8. Dwyer AJ. Matchmaking and McNemar in the comparison of diagnostic modalities. Radiology 1991, 178, 328-330 https://doi.org/10.1148/radiology.178.2.1987587
  9. Han M, Park K, Kwon Y, Kim J. Comparison of serological methods for detection of avian influenza virus antibodies. Korean J Vet Res 2002, 42, 73-80 (in Korean).
  10. Jacobson RH. Validation of serological assays for diagnosis infectious diseases. Rev Sci Tech 1998, 17, 469-526 https://doi.org/10.20506/rst.17.2.1119
  11. Roush WB. Tour PR. The power of tests for biocquivalencc in feed experiments with poultry. J Anim Sci 2004, 82 (Suppl), E110-118
  12. Cohen J. Statistical power analysis for the behavioral sciences. 2nd ed. pp. 52-56. Lawrence Erlbaum Associates Pub, HilIsdale, NJ, 1988
  13. Connor RJ. Sample size for testing differences in proportions for the paired-sample design. Biometrics 1987, 43, 207-211 https://doi.org/10.2307/2531961
  14. Lenth RV. Statistical powcr calculations. J Anim Sci 2007, 85, E24-29 https://doi.org/10.2527/jas.2006-449
  15. Malik M, Hnatkova K, Batehvarov V, Gang Y, Smetana P, Camm AJ. Sample size, power calculations, and their implications for the cost of thorough studies of drug induced QT interval prolongation. Pacing Clin Elcctrophysiol 2004, 27, 1659-1669 https://doi.org/10.1111/j.1540-8159.2004.00701.x
  16. Houle TT, Penzien DB, Houle CK. Statistical power and sample size estimation for headache research: an overview and power calculation tools. Headache 2005, 45, 414-418 https://doi.org/10.1111/j.1526-4610.2005.05092.x
  17. Huang W, LaBerge JM, Lu Y, Clidden DV. Research publications in vascular and interventional radiology: rsearch topics, study designs, and statistical methods. J Vasc lnterv Radiol 2002, 13, 247-255 https://doi.org/10.1016/S1051-0443(07)61717-5
  18. Lirn Y, Lee D, Park J, Yang K, Kim S, Kim K, Hyun K, Kim W, Lee Y. Enzyme-linked immunosorbet assay for detection of bovine antibody to Brucella abortus. Korean J Vet Res 1993, 33, 131-135
  19. Cho Y, Kang S, Choi E, Jeong W, Yoon Y, Hwang W. Development of indirect fluorescent antibody test and the prevalence of the antibody titer for Neospora caninum of domestic animal in Korea. Korean J Vet Res 1998, 38, 595-599
  20. Hofmeister EH. King J, Read MR. Budsberg SC. Sample size and statistical power in the small-animal analgesia literature. J Small Anim Pract 2007, 48, 76-79 https://doi.org/10.1111/j.1748-5827.2006.00234.x