2.8. Model Bias Statistical Test

Thierry Delatour; Florian Becker; Julius Krause; Roman Romero; Robin Gruna; Thomas Längle; Alexandre Panchaud

Improve Research Reproducibility A Bio-protocol resource

Home
Protocols

Concise Method

2.8. Model Bias Statistical Test

TD Thierry Delatour

FB Florian Becker

JK Julius Krause

RR Roman Romero

RG Robin Gruna

TL Thomas Längle

AP Alexandre Panchaud

This method is extracted from research article: Foods, Dec 2021

Handheld Spectral Sensing Devices Should Not Mislead Consumers as Far as Non-Authentic Food Is Concerned: A Case Study with Adulteration of Milk Powder

DOI: 10.3390/foods11010075

Ask a question

Favorite

Models were tested for bias using the Elliptical Joint Confidence Region (EJCR) significance test for the true intercept ( $a$ ) and slope ( $b$ ) of the univariate linear regression of predicted versus reference values (6):

in this equation $\hat{a}$ and $\hat{b}$ are the estimated intercept and slope of the univariate regression, respectively; $a$ and $b$ are the coordinate axes variables, $F$ is Fisher–Snedecor statistic for 2 and N-2 degrees of freedom at 1-α confidence level (95%); and $MSE$ is the mean squared error, determined as:

where ${\hat{y}}_{i}$ refers to the response values as predicted by the univariate regression.

Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

Do you have any questions about this protocol?

Post your question to gather feedback from the community. We will also invite the authors of this article to respond.

Post a Question

0 Q&A

Share your protocol with your peers.

Submit a Preprint Protocol