Starting out in Statistics

An Introduction for Students of Human Health, Disease, and Psychology

Patricia de Winter, Peter M. B. Cahusac

• Publisher: Wiley-Blackwell
• Year: 2014
• ISBN:
  9781118920558
• Edition: 1
• Topic: Biological Sciences
• Subtopic: Biology
• Index: Biological Sciences

To form a strong grounding in human-related sciences it is essential for students to grasp the fundamental concepts of statistical analysis, rather than simply learning to use statistical software. Although the software is useful, it does not arm a student with the skills necessary to formulate the experimental design and analysis of a research project in later years of study or indeed, if working in research.

This textbook deftly covers a topic that many students find difficult. With an engaging and accessible style it provides the necessary background and tools for students to use statistics confidently and creatively in their studies and future career.

Key features:

• Up-to-date methodology, techniques and current examples relevant to the analysis of large data sets, putting statistics in context
• Strong emphasis on experimental design
• Clear illustrations throughout that support and clarify the text
• A companion website with explanations on how to apply learning to related software packages

This is an introductory book written for undergraduate biomedical and social science students with a focus on human health, interactions, and disease. It is also useful for graduate students in these areas, and for practitioners requiring a modern refresher.

1
Introducing Variables, Populations and Samples – ‘Variability is the Law of Life’

1.1 Aims

William Osler, a Canadian physician once wrote: ‘Variability is the law of life, and as no two faces are the same, so no two bodies are alike, and no two individuals react alike and behave alike under the abnormal conditions which we know as disease’. We could add that neither do individuals behave or react alike in health either, and we could extend this to tissues and cells and indeed any living organism. In short, biological material, whether it is a whole organism or part of one in a cell culture dish, varies. The point of applying statistics to biological data is to try to determine whether this variability is simply inherent, natural variability, or whether it arises as a consequence of what is being tested, the experimental conditions. This is the fundamental aim of using inferential statistics to analyse biological data.

1.2 Biological data vary

Imagine that you are an alien and land on earth. It seems to be quite a pleasant habitable sort of place and you decide it's worth exploring a little further. It doesn't look like your own planet and everything is new and strange to you. Fortunately, your species evolved to breathe oxygen so you can walk about freely and observe the native life. Suddenly a life form appears from behind some immobile living structures, you later learn are called trees, and walks towards you on all fours. It comes up close and sniffs you inquisitively. You have no idea what this creature is, whether it is a particularly large or small specimen, juvenile or mature, or any other information about it at all. You scan it with your Portable Alien information Device (PAiD), which yields no clues – this creature is unknown to your species. You fervently hope that it is a large specimen of its kind because although it seems friendly enough and wags its rear appendage from side to side in an excited manner, you have seen its teeth and suspect that it could make a tasty meal of you if it decided you were an enemy. If larger ones were around, you wouldn't want to be. You are alone on an alien planet with a strange creature in close proximity and no information. Fortunately, your species is well versed in Statistics, so you know that if you gather more information you will be able to make some assumptions about this creature and assess whether it is a threat to you or not. You climb out of its reach high up into a convenient nearby tree and wait.

You currently have a sample size of one. You need to observe more of these creatures. You don't have long to wait. The life form is soon joined by another of a similar size which sniffs it excitedly. Well, two is better than one, but the information you have is still limited. These two could be similarly sized because they are siblings and both juveniles – the parents could be bigger and just around the corner. You decide to stay put. Some time passes and the pair are joined by 30–40 similar creatures making a tremendous noise, all excited and seemingly i...

Table of contents

• Cover
• Titlepage
• Copyright
• Dedication
• Introduction – What's the Point of Statistics?
• Basic Maths for Stats Revision
• Statistical Software Packages
• About the Companion Website
• 1 Introducing Variables, Populations and Samples – ‘Variability is the Law of Life’
• 2 Study Design and Sampling – ‘Design is Everything. Everything!’
• 3 Probability – ‘Probability ... So True in General'
• 4 Summarising Data – ‘Transforming Data into Information’
• 5 Statistical Power – ‘… Find out the Cause of this Effect’
• 6 Comparing Groups using t-Tests and ANOVA – ‘To Compare is not to Prove’
• 7 Relationships between Variables: Regression and Correlation – ‘In Relationships … Concentrate only on what is most Significant and Important’
• 8 Analysis of Categorical Data – ‘If the Shoe Fits …’
• 9 Non-Parametric Tests – ‘An Alternative to other Alternatives'
• 10 Resampling Statistics comes of Age – ‘There's always a Third Way’
• Appendix A: Data Used for Statistical Analyses (Chapters 6,7 and 10)
• Appendix B: Statistical Software Outputs (Chapters 6–9)
• Index
• End User License Agreement