Amy Horn


What Are Limits Of Agreement

Compliance limitations include both systematic errors (bias) and random errors (precision) and provide a useful measure for comparing likely differences between different results measured using two methods. If one method is a reference method, compliance limits can be used as a measure of the total error of a measurement method (Krouwer, 2002). In order to improve the introduction of appropriate techniques for estimating intervals and designing research, this paper has two objectives. The first is to assess the statistical characteristics of interval estimation methods for normal percentiles. Theoretical justifications are presented to shed light on statistical links between different filming sizes in order to obtain precise confidence intervals. In addition, comprehensive empirical assessments are made available to show that seemingly accurate estimation methods, with equidistant estimates, present problematic confidence limits. The second objective is to provide sample size methods for accurate estimates of the interval of normal percentiles. The required accuracy of a confidence interval is assessed based on the size of the expected width and the probability of reliability of the width of the interval within a specified threshold. Given the general availability of SAS and R statistical software packages, computer algorithms are designed to facilitate the implementation of the proposed confidence interval and sample size calculations.

Choudhary PK, Nagaraja HN. Measuring compliance in method comparison studies – an audit. In: Balakrishnan N, Kannan N, Nagaraja HN, editor. Investment and selection progress, multiple comparisons and reliability. Boston: Birkhauser; 2004: 215-44 Barnhart HX, Haber MJ, Lin LI. An overview of the assessment of compliance with ongoing measures. J Biopharm Stat. 2007;17:529-69. – BAL – z p N1.2 – t1 – α/2 (b1.2) and – BAU – z p N1.2 – t1 – α/2 () b1/2. In the particular case of α – 0.05, the general expressions are reduced to the confidence intervals for the two points of agreement of Bland and Altman [2]: the Bland-Altman plots were also used to examine a possible link between the differences between the measures and the actual value (i.e.

proportional distortion).

Comments are closed.