As with an example in COPD, we showed how the five compliance indices can be derived from the same linear mixed effects model (although we preferred a slightly different linear mixed effects model for the LoA method depending on the differences). It is therefore not surprising that the five methods yielded similar results, although the lack of acceptable consistency for some methods was clearer than for others due to the way in which the components of variance are integrated into the expression of the different correspondence indices. The 95% of loA ranged from -12 to 8 breaths per minute, and the TDI was estimated to be 11 breaths per minute, all far from the clinically acceptable difference (CAD) of 5 breaths per minute. The CP was also low at 0.63 based on a CAD of 5. Looking at the variance components of the LoA model (3), we find that the variability of differences between subjects was very low, but both the variability within the subject and the variability due to activities were relatively high and these were the driving force behind the disagreement. Similarly, we observe, based on the variance components of the model (2), that the variability of residual defects and the interaction between the activity device and the activity device were both quite high. We can therefore conclude that the mammary ligament apparatus may be less able to accurately apprehend changes in respiratory rate, as it varies from one activity to another compared to the gold standard. with the square root of the total variance, which gives an estimate of the standard deviation for use in the classical formula of the Bland Altman compliance limits. There are a multitude of methods for assessing continuous concordance in the literature, which differ in complexity and in their underlying assumptions. In this article, we`ve looked at five different methods to analyze the same compliance issue with rewarded and unbalanced data. Some of which are known and often used in the literature, and others that include recent advances in compliance research.
For both the compliance limits and the TDI method, it is important to remember that the calculated limit values are only estimates (just as the CCC is a point estimate) and therefore there is uncertainty about the actual values of these values [44]. Different samples of the total population may produce different limit values and a different DDI. In particular, when the sample size is reduced, the observed concordance limits may be removed from the “true” concordance limits due to the distortion of the finite sample. For this reason, for statistical purposes, it is often recommended to calculate confidence limits around borders, or even to calculate separate prediction intervals [44, 45]. Arch BN, Blair J, McKay A, Gregory JW, Newland P, Gamble C. Measurement of HbA1c in multicenter diabetes studies – blood samples need to be tested locally or sent to a central laboratory: a compliance analysis. Lawsuit. 2016;17 (1): 517. Bland JM, DG Altman. Statistical methods for assessing conformity between clinical measurement methods. Lanzette.
1986;327:307-10. Chen L, Chapman JL, Yee BJ, Wong KK, Grunstein RR, Marshall NS, Miller CB. Correspondence between electronic drowsiness limestone reactions and Epworth paper in obstructive sleep apnea: secondary analysis of a randomized controlled study conducted in a specialized tertiary care clinic. BMJ Open. 2018;8( 3):e019255. Haber M, Gao J, Barnhart HX. Analysis of the concordance between measurement methods from data with repeated measurements consistent with the individual conformity coefficient. J Data Sci. 2010;8( 3):457. Taking into account repeated measurements per subject, we began to adapt the model (2) to COPD data using the lmer function of the R packet lme4 [38, 39]. .
