Sample Size Considerations in the Design of Orthopaedic Risk-Factor Studies

Abstract

Objective Sample size calculations play a central role in risk-factor study design because sample size affects study interpretability, costs, hospital resources and staff time. We demonstrate the consequences of using misclassified control groups on the power of risk association tests, with the intent of showing that control groups with even small misclassification rates can reduce the power of association tests. So, sample size calculations that ignore misclassifications may underpower studies.

Study Design This was a simulation study using study designs from published orthopaedic risk-factor studies. The approach was to use their designs but simulate the data to include known proportions of misclassified affected subjects in the control group. The simulated data were used to calculate the power of a risk-association test. We calculated powers for several study designs and misclassification rates and compared them to a reference model.

Results Treating unlabelled data as disease-negative only always reduced statistical power compared with the reference power, and power loss increased with increasing misclassification rate. For this study, power could be improved back to 80% by increasing the sample size by a factor of 1.1 to 1.4.

Conclusion Researchers should use caution in calculating sample sizes for risk-factor studies and consider adjustments for estimated misclassification rates.

Keywords

risk factor - case–control - power - sample size - veterinary orthopaedics

Publication History

Received: 25 September 2023

Accepted: 31 October 2023

Article published online:
09 January 2024

• References

• 1 Halpern SD, Karlawish JH, Berlin JA. The continuing unethical conduct of underpowered clinical trials. JAMA 2002; 288 (03) 358-362
• 2 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 (02) 76-79
• 3 Waxman AS, Robinson DA, Evans RB, Hulse DA, Innes JF, Conzemius MG. Relationship between objective and subjective assessment of limb function in normal dogs with an experimentally induced lameness. Vet Surg 2008; 37 (03) 241-246
• 4 Arthur EG, Arthur GL, Keeler MR, Bryan JN. . Risk of osteosarcoma in dogs after open fracture fixation. Vet Surg 2016; 45 (01) 30-35
• 5 Wylie CE, Collins SN, Verheyen KL, Newton JR. Risk factors for equine laminitis: a case-control study conducted in veterinary-registered horses and ponies in Great Britain between 2009 and 2011. Vet J 2013; 1 (198) 1
• 6 Bekker J, Davis J. Learning from positive and unlabeled data: a survey. Mach Learn 2020; 109: 719-760
• 7 Baird AE, Carter SD, Innes JF, Ollier WE, Short AD. Genetic basis of cranial cruciate ligament rupture (CCLR) in dogs. Connect Tissue Res 2014; 55 (04) 275-281
• 8 Healey E, Murphy RJ, Hayward JJ. et al. Genetic mapping of distal femoral, stifle, and tibial radiographic morphology in dogs with cranial cruciate ligament disease. PLoS One 2019; 14 (10) e0223094