Part I
Introduction and basics
Chapter 1
Basics and terminology
1.1 Introduction
Food issues are becoming increasingly important to consumers, most of whom depend on the food industry and other food workers to provide safe, nutritious and palatable products. These people are the modern-day scientists and other practitioners who work in a wide variety of food-related situations. Many will have a background of science and are engaged in laboratory, production and research activities. Others may work in more integrated areas such as marketing, consumer science and managerial positions in food companies. These food practitioners encounter data interpretation and dissemination tasks on a daily basis. Data come not only from laboratory experiments but also via surveys on consumers, as the users and receivers of the end products. Understanding such diverse information demands an ability to be, at least, aware of the process of analysing data and interpreting results. In this way, communicating information is valid. This knowledge and ability gives undeniable advantages in the increasingly numerate world of food science, but it requires that the practitioners have some experience with statistical methods.
Unfortunately, statistics is a subject that intimidates many. One need only consider some of the terminology used in statistic text titles (e.g. âfearâ and âhateâ; Salkind 2004) to realise this. Even the classical sciences can have problems. Professional food scientists may have received statistical instruction, but application may be limited because of âhang-upsâ over emphasis on the mathematical side. Most undergraduate science students and final-year school pupils may also find it difficult to be motivated with this subject; others with a non-mathematical background may have limited numeracy skills presenting another hurdle in the task.
These issues have been identified in general teaching of statistics, but like other disciplines, application of statistical methods in food science is continually progressing and developing. Statistical analysis was identified, two decades ago, as one subject in a set of âminimum standardsâ for training of food scientists at undergraduate level (Iwaoka et al. 1996). Hartel and Adem (2004) identified the lack of preparedness for the mathematical side of food degrees, and they describe the use of a quantitative skills exercise for food engineering, a route that merits attention for other undergraduate food science courses.
Unfortunately, for the novice, the subject is becoming more sophisticated and complex. Recent years have seen this expansion in the world of food science, in particular in sensory science, with new journals dealing almost exclusively with statistical applications. Research scientists in the food field may be cognizant with such publications and be able to keep abreast of developments. The food scientist in industry may have a problem in this respect and would want to look for an easier route, with a clear guide on the procedures and interpretation, etc. Students and pupils studying food-related science would also be in this situation. Kravchuk et al. (2005) stress the importance of application of statistical knowledge in the teaching of food science disciplines, so as to ensure an ongoing familiarity by continual use.
Some advantages of being conversant with statistics are obvious. An appreciation of the basis of statistical methods will aid making of conclusions and decisions on future work. Other benefits include the increased efficiency achieved by taking a statistical approach to experimentation. Guiding the reader on the path to such knowledge and skills begins with a perusal of the book contents.
What will this book give the reader?
The book will provide the reader with two main aspects of statistical knowledge. One is a workbook of common univariate methods (Part I) with short explanations and implementation with readily available software. Secondly (Part II), the book covers an introduction to more specific applications in a selection of specialised areas of food studies.
1.2 What the book will cover
Chapter 1 introduces the book and gives a summary of how the chapter contents will deal with the various aspects. Accounts of the scope of data analysis in the food field, its importance and the focus of the text lead on to a terminology outline and advice on software and bibliography.
Chapter 2 begins with consideration of data types and defines levels of measurement and other descriptions of data. Sampling, data sources and population distributions are covered.
Chapter 3 introduces the style of the analysis system used with the software and begins with simple analysis for summarising data in graph and table format. Measures including mean, median, mode, standard deviation and standard error are covered, along with various types of graphs. Definitions and application of some of these methods to measures of error, uncertainty and sample character are also given.
Chapters 4â6 cover various aspects of analysis of effects. Firstly, Chapter 4 gives a detailed account of significance testing. Analysis of significant differences, probability and hypothesis testing and its format are described and discussed. The chapter concludes with consideration of types of comparison and factors deciding selection of a test, including assumptions for use of parametric methods. Chapter 5 continues with significance tests themselves, with tests for parametric and non-parametric data, two or more groups, and related and independent groups. Chapter 6 describes effects in the form of relationships as association (cross tabulation) and correlation (coefficients) and their significance. The topic of correlation is then applied in simple regression and prediction.
Chapter 7 concludes cover of basic material by detailing the nature and terminology of experimental design for simple experiments. Stages in the procedure, such as identification of factors and levels, and sources of experimental error and their elimination are explained. Details of design types for different sample, factor, treatment and replication levels are then described.
Chapters 8 and 9 start the applications part of the book. In Chapter 8, sensory and consumer data are described in terms of level of measurement, sources, sampling via surveys, sensory panels and consumer panels. Summary methods and evaluation of error, reliability and validity in these data sources are considered along with checking on assumptions for parametric nature. Specific methods of analysis are then illustrated for a range of consumer tests and survey data, and for specific sensory tests and monitoring of sensory panels.
Chapter 9 uses a similar approach to instrumental data. They are described in terms of level of measurement, sources and sampling via chemical and physical methodologies in food science. Analytical error, repeatability and accuracy are defined followed by use of calibration and reference materials. An account is then given of specific significance analysis methods for laboratory work results and experiments.
Chapter 10 applies experimental design to formulation procedures in food product development. Identification of factors and levels as ingredients for simple designs is given viewed from the formulation aspect. Decisions on the response and its measurement are described along with the issues in objective versus hedonic responses. Examples of some formulation experiments are used to illustrate the analysis methods and their interpretation.
Chapter 11 deals with the application of the basic methods and experimental desig...