In general, the actual distribution of the T-plan is distorted, particularly when the sample size is small and p deviates significantly from 0.5. This means that the procedure intervals asymmetric confidence intervals for . It should be noted that the exact estimates of the interval “widehat`uptheta” L , “widehat`uptheta` are not equal to the sample average, with the exception of the particular case p – 0.5. On the other hand, the approximate confidence intervals of Chakraborti and Li [24] are equally far removed from UB`s unbiased estimate. Therefore, the interval method is probably inadequate, and the two confidence limits, AL and (largehat, upthetian) are methodically imprecise when one takes into account the probability of unilateral coverage. But the numerical studies of Chakraborti and Li [24] did not cover these fundamental issues. Similarly, Bland and Altman[2] confidence intervals are symmetrical around the estimate. B and therefore the same gap as the intervals between Chakraborti and Li [24]. The limits of compliance can be inferred by the parametric method if the normality of the differences is indicated. or the use of non-parametric percentiles, if these assumptions are not included.

Suppose X1, …, X N is a sample of a population N (μ, 2) of an unknown average μ and variance 2 for N > 1. The sample average “”superline”” and the variance of the S2 sample are defined as “overline value” and “Limits_” “limits_” “_i”_i limits_” Distribution percentile N (μ, 2) is replaced by Bland JM, Altman DG. (1999) Measurement agreement in comparative study of methods. Statistical methods in medical research 8, 135-160. Despite improved data adaptation, the increased difficulty of using curved limit values makes linear limits, from 2.0 to 0.4 × glucose to 1.8 mmol/L, a more practical estimate of the 95% limits for the difference between hair glucose and plasma glucose in this population. The exact interval method should be used in place of approximate methods. Computer algorithms are presented to implement the accuracy of the interval and the sample size calculations proposed for planning percentile research. To compare the Bland Altman measurement systems, the differences between the different measurements of the two different measurement systems are calculated and the average and the standard deviation are calculated. The 95% of “agreement limits” are calculated as the average of the two values minus and plus 1.96 standard deviation.