Carkeet A. Exact parametric confidence intervals for Bland Altman compliance limits. Optom Vis Sci. 2015; 92:e71-80. After clicking on calculation, the program indicates the total number of cases required in the study. The calculation may take some time. 3. Bland JM, DG Altman. Comparison of agreed statistical measurement methods. Anesthesiology 2012;116:182-185. Calculates the sample size required for a comparative study of methods using the Bland Altman diagram. Kupper LL, Hafner KB.

What are the sample size formulas? In Stat. 1989;43:101–5. The exact interval should be preferred to approximate methods. Computer algorithms are presented in order to implement the precision and sample size calculations proposed for percentile research planning. Beal SL. Determination of sample size for confidence intervals on the population mean and on the difference between two population means. Biometrics. 1989;45:969-77. Carkeet A, Goh YT.

Trust and coverage for Bland Altman compliance limits and their approximate confidence intervals. Stat Methods Med Res. 2018;27:1559-74. Obviously, the sample size rules do not depend on the mean μ and are reduced to the sample size methods of Kupper and Hafner [27], since θ = μ if p = 0.5 is. Accuracy assessments of the expected width and probability of coverage depend on the thresholds δ and ω as a function of the relative size δ/σ or ω/σ. As a result, additional SAS/IML and R computer programs are presented to facilitate the necessary calculations. Due to the prospective nature of research forecasting, the general guidelines suggest that typical sources, such as published results or expert opinions, can provide plausible and reasonable values for the essential characteristics of future studies. To illustrate these data, the blood pressure statistics of Bland and Altman [2] are taken into account as parameters μ = – 16.29 and σ = 19.61. With δ = ω = (0.7) σ = 9.805 and 1 – γ = 0.9, the optimal sample sizes for an accurate estimate of the 95% range of the 97.5th percentile 183 and 207 are among the expected width or probability of reliability criteria. For ease of application, system requirements are integrated into the user specification sections of the SAS/IML (Additional Files 1, 2, and 3) and R (Additional Files 4, 5, and 6) programs. The delineation indicates the theoretical correlations between different key sizes to obtain exact confidence intervals. In addition, apparently accurate approximation methods with the same equivalence appear from the principal evaluators as undesirable confidence limits.

It is established that the optimal sample size has a minimum for the median or mean and increases when the percentile approaches the extremes. Although the practical implementation of the exact interval at Carkeet [19] is well represented, the explanation of the differences between the exact and approximate methods has mainly focused on the relative dimensions and symmetric/asymmetric limits of the resulting confidence limits. On the other hand, Bland-Altman breakpoints are generally considered a pair of measurement-related correspondence in comparative studies. As a result, Carkeet [19] and Carkeet and Goh [20] focused on comparing approximate confidence intervals for the upper and lower limits of chords as a couple and precise bilateral tolerance intervals for normal distribution. . . .