Requiem for Passing Bablok (for most cases)
R mcrPioda-1.3.3 package - New M- and MM-Deming regressions
mcrPioda-1.3.3 release. Rewritten M- and MM-Deming regressions
I would like to report that the recently released mcrPioda-1.3.3 package has refurbished versions of the M-Deming and MM-Deming regression. The new functions are written in C and are much faster that the previous ones. The new release is on the devel branch because on the master branch the legacy version of 2021 is still available.
Bayesian Deming regression, Type II error with 2x2 rounded data
Bayesian Deming robustness with a high percentage of outliers
I just uploaded a video showing the differences between typical method comparison regressions when outliers with leverage are massively present in the data.
Bayesian Deming regression, Type I (alpha) error
Linear heteroscedastic Bayesian Deming regression, a case study
Abstract
Bias with AUC - PBequi, PaBa, Deming, MDeming, MMDeming
Bayesian vs frequentist Deming regression comparison
The glycHem data set
Bayesian Deming regression - Small sample example
Bayesian Deming regression (with heteroscedastic error structure)
Passing Bablok is biased at low data precision (thus almost always)
Bayesian Deming regression - About the sampling method
The basic concept in rstanbdp is to sample a single error term instead of two. The idea comes from the Weighted Deming procedure proposed by Linnet in multiple articles, for example K. Linnet, Clinical Chemistry 44:5, 1024-1031 (1998)