(Mis)understandings in Research Methodology and Chemometrics in Meat Science
The main purpose of this manuscript is to discuss the most common errors in reporting food science data, with special attention to meat science, while offering suggestions that are common and long known in the regular research methodology of any field. Because the quality of data determines the quality of conclusions that are decisive of subsequent actions and the allocation of (often scarce) resources, low quality data can be a barrier to progress in the field rather than paving the way to a better understanding of the important aspects of food (meat) production. For valid conclusions, it is important to define hypotheses for a particular data collection, to collect data correctly, and to choose the right test for analysis. If a professional in meat production needs to optimize or predict a particular production outcome, mathematical modeling is the right choice. On the other hand, if one is looking for structure within the data, principal component analysis (PCA) is one of the valid options. Both approaches have unlimited applications in meat and food science in general, which can also provide various benefits for industrial purposes, such as getting ahead of competitors in the market (by identifying optimal customers, predicting customer acceptance of a meat product, various aspects of business intelligence such as improving effectiveness and efficiency etc.).