Although IUPAC has recommended a probabilistic approach to determining limit of detection (LOD) based on false-positive and false-negative rates for more than 20 years, the LOD definition for ion-selective electrodes (ISEs) long predates these recommendations and conflicts substantively with them. Although it is well known that the ISE LOD definition does not follow best practice, it continues to be used due to simplicity and a lack of available methods for estimating LOD for nonlinear sensors. Here, we use ISEs as a model system for estimation of LOD for nonlinear sensors that is consistent with broad IUPAC recommendations and justified using statistical theory. Using freely available software, the new approach and updated definition is demonstrated through theory, simulation, and an environmental application. The results show that the current LOD definition for ISEs performs substantially worse than the proposed definition when assessed against IUPAC recommendations, including ignoring sensor noise and LOD uncertainty, leading to bias of an order of magnitude or more. Further, the environmental application shows that the new definition, which includes estimates of LOD uncertainty, allows more objective assessment of sensor response and fitness for purpose. The growing demand for ultrasensitive sensors that operate in complex matrices has pushed the boundaries of traditional calibration approaches. These sensors often operate near their limit of detection (LOD), with additional challenges created if their response is nonlinear. These challenges are amplified when assessing new sensors, since they may be less reproducible and noisier than benchmark techniques.
A new software package, ISEtools, is introduced for use within the popular open-source programming language R that allows Bayesian statistical data analysis techniques to be implemented in a straightforward manner. Incorporating all collected data simultaneously, this Bayesian approach naturally accommodates sensor arrays and provides improved limit of detection estimates, including providing appropriate uncertainty estimates. Utilising >1500 lines of code, ISEtools provides a set of three core functions—, , and — for analysing ion-selective electrode data using the Nikolskii–Eisenman equation. The functions call, fit, and extract results from Bayesian models, automatically determining data structures, applying appropriate models, and returning results in an easily interpretable manner and with publication-ready figures. Importantly, while advanced statistical and computationally intensive methods are employed, the functions are designed to be accessible to non-specialists. Here we describe basic features of the package, demonstrated through a worked environmental application.
In the field of life testing, it is very important to study the reliability of any component under testing. One of the most important subjects is the “stress-strength reliability” term which always refers to the quantity P X > Y in any statistical literature. It resamples a system with random strength (X) that is subjected to a random strength (Y) such that a system fails in case the stress exceeds the strength. In this study, we consider stress-strength reliability where the strength (X) follows Rayleigh-half-normal distribution and stress ( Y 1 , Y 2 , Y 3 , and Y 4 ) follows Rayleigh-half-normal distribution, exponential distribution, Rayleigh distribution, and half-normal distribution, respectively. This effort comprises determining the general formulations of the reliabilities of a system. Also, the maximum likelihood estimation approach and method of moment (MOM) will be utilized to estimate the parameters. Finally, reliability has been attained utilizing various values of stress and strength parameters.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.