Sample Size Agreement

12. Stockl D, Cabaleiro DR, Uytfanghe KV, Thienpont LM. Interpretation of comparative studies of methods using the Bland-Altman diagram: reflection on the importance of sample size by integrating confidence limits and predefined error limits into the graph. Clin Chem 2004;50:2216-2218. MedCalc uses the method of Lu et al. (2016) to calculate the sample size. Given the symmetry of the confidence interval estimate of LOA with μ and μ symmetry (μ ≥ 0) and the sample size estimates of these two situations, we will only discuss the situation if μ ≥ 0. According to the principle of statistical inference of the Bland Altman conformity limits, we can separate the total Type I error (α) into two parts, both α/2. Similarly, we can separate the type II error (β) into two parts. One is the first type II error (β1) of the upper limit of LOAs and the other is the second type II error (β2) of the lower limit value of LOAs (Figure 1). [13]. Two methods are considered consistent when a predefined maximum difference (Δ) is greater than the upper limit of conformity and -Δ below the lower limit of conformity.

To show that two methods match, it is necessary to define an appropriate sample size to have a high probability (power) that Δ is outside the 95 IC of the compliance limits. If you know exactly how you want to assess compliance limits, you can determine the sample size. Calculates the sample size required for a comparative method study using the Bland Altman diagram. In equation (6), tinv (1− β/2,n-1,t1-α/2,n-1) with respect to the sample size(s), we must use an iterative method to calculate the sample size. We first replace the non-central distribution quantil with the standard distribution quantil to get the initial value (n0), and then iterate step by step until n achieves a stable value. Hahn and Meeker [18] defined a tolerance interval, which is an interval that can be said to contain at least a certain proportion p of the population with some degree of confidence, 100 (1-α) % and provided the estimate of the sample size over the tolerance interval. We can see that their estimate of sample size is based on the desired accuracy, without taking into account Type II (β) errors or performance, and only the frequently asked question: „What is the size of a sample I need to get a confidence interval?“ Although our confidence interval for LOA is similar to their tolerance interval, the theories and methods for estimating sample size are completely different. Our method of estimating sample size is derived not only at the predetermined level of α, but also at β 19. McAlinden C, Khadka J, Pesudov K.

Statistical methods for conducting compliance studies (comparison of clinical trials) and precision studies (reproducibility or reproducibility) in optometry and ophthalmology. Ophthalmic Physiol Opt 2011;31:330-338. The standard error of the 95% limit is approximately rooted (3 s2/n), s being the standard deviation of the differences between the measurements with the two methods and n the sample size. The confidence interval is the estimate of the limit value, d plus or minus 1.96 s, plus or minus 1.96 standard error. Based on the principle of statistical infetency and the mathematical theory of distribution, we deduced the formula for calculating the sample size for the Bland Altman method under different parameters. . . .