Discovering Statistics Using IBM SPSS Statistics 5th Edition

Book Preface

Many behavioural and social science students (and researchers for that matter) despise statistics. Most of us have a non-mathematical background, which makes understanding complex statistical equations very difficult. Nevertheless, the evil goat-warriors of Satan force our non-mathematical brains to apply themselves to what is the very complex task of becoming a statistics expert. The end result, as you might expect, can be quite messy. The one weapon that we have is the computer, which allows us to neatly circumvent the considerable disability of not understanding mathematics. Computer programs such as IBM SPSS Statistics, SAS, R, JASP and the like provide an opportunity to teach statistics at a conceptual level without getting too bogged down in equations. The computer to a goat-warrior of Satan is like catnip to a cat: it makes them rub their heads along the ground and purr and dribble ceaselessly. The only downside of the computer is that it makes it really easy to make a complete idiot of yourself if you don’t understand what you’re doing. Using a computer without any statistical knowledge at all can be a dangerous thing. Hence this book.
My first aim is to strike a balance between theory and practice: I want to use the computer as a tool for teaching statistical concepts in the hope that you will gain a better understanding of both theory and practice. If you want theory and you like equations then there are certainly more technical books. However, if you want a stats book that also discusses digital rectal stimulation, then you have just spent your money wisely.
Too many books create the impression that there is a ‘right’ and ‘wrong’ way to do statistics. Data analysis is more subjective than is often made out. Therefore, although I make recommendations, within the limits imposed by the senseless destruction of rainforests, I hope to give you enough background in theory to enable you to make your own decisions about how best to conduct your analysis.
A second (ridiculously ambitious) aim is to make this the only statistics book that you’ll ever need to buy (sort of). It’s a book that I hope will become your friend from your first year at university right through to your professorship. The start of the book is aimed at first-year undergraduates (Chapters 1–10), and then we move onto second-year undergraduate-level material (Chapters 6, 9 and 11–16) before a dramatic climax that should keep postgraduates tickled (Chapters 17–21). There should be something for everyone in each chapter, and to help you gauge the difficulty of material, I flag the level of each section within each chapter (more on that later).
My final and most important aim is to make the learning process fun. I have a sticky history with maths. This extract is from my school report at the age of 11:
Image 3

The ‘27=’ in the report is to say that I came equal 27th with another student out of a class of 29. That’s pretty much bottom of the class. The 43 is my exam mark as a percentage. Oh dear. Four years later (at 15), this was my school report:
Image 4

The catalyst of this remarkable change was a good teacher: my brother, Paul. I owe my life as an academic to Paul’s ability to teach me stuff in an engaging way – something my maths teachers failed to do. Paul’s a great teacher because he cares about bringing out the best in people, and he was able to make things interesting and relevant to me. Everyone should have a brother Paul to teach them stuff when they’re throwing their maths book at their bedroom wall, and I will attempt to be yours.
I strongly believe that people appreciate the human touch, and so I inject a lot of my own personality and sense of humour (or lack of) into Discovering Statistics Using … books. Many of the examples in this book, although inspired by some of the craziness that you find in the real world, are designed to reflect topics that play on the minds of the average student (i.e., sex, drugs, rock and roll, celebrity, people doing crazy stuff). There are also some examples that are there simply because they made me laugh. So, the examples are light-hearted (some have said ‘smutty’, but I prefer ‘light-hearted’) and by the end, for better or worse, I think you will have some idea of what goes on in my head on a daily basis. I apologize to those who think it’s crass, hate it, or think that I’m undermining the seriousness of science, but, come on, what’s not funny about a man putting an eel up his anus?
I never believe that I meet my aims, but previous editions have certainly been popular. I enjoy the rare luxury of having complete strangers emailing me to tell me how wonderful I am. (Admittedly, there are also emails accusing me of all sorts of unpleasant things, but I’ve usually got over them after a couple of months.) With every new edition, I fear that the changes I make will ruin my previous hard work. Let’s see what you’re going to get and what’s different this time around.

What do you get for your money?

This book takes you on a journey (I try my best to make it a pleasant one) not just of statistics but also of the weird and wonderful contents of the world and my brain. It’s full of daft examples, bad jokes, and smut. Aside from the smut, I have been forced, reluctantly, to include some academic content. It contains everything I know about statistics (actually, more than I know …). It also has these features:•Everything you’ll ever need to know: I want this book to be good value for money, so it guides you from complete ignorance (Chapter 1 tells you the basics of doing research) to being an expert in multilevel linear modelling (Chapter 21). Of course, no book can contain everything, but I think this one has a fair crack. It’s pretty good for developing your biceps also.•Stupid faces: You’ll notice that the book is riddled with ‘characters’, some of them my own. You can find out more about the pedagogic function of these ‘characters’ in the next section.•Data sets: There are about 132 data files associated with this book on the companion website. Not unusual in itself for a statistics book, but my data sets contain more sperm (not literally) than other books. I’ll let you judge for yourself whether this is a good thing.•My life story: Each chapter is book-ended by a chronological story from my life. Does this help you to learn about statistics? Probably not, but it might provide light relief between chapters.•SPSS tips: SPSS does confusing things sometimes. In each chapter, there are boxes containing tips, hints and pitfalls related to SPSS.•Self-test questions: Given how much students hate tests, I thought that the best way to commit commercial suicide was to liberally scatter tests throughout each chapter. These range from simple questions to test what you have just learned to going back to a technique that you read about several chapters before and applying it in a new context. All of these questions have answers so that you can check on your progress.•Online resources: The website contains an insane amount of additional material, which no one reads, but it is described in the section about the online resources so that you know what you’re ignoring.•Digital stimulation: No, not the aforementioned type of digital stimulation, but brain stimulation. Many of the features on the website will be accessible from tablets and smartphones, so that when you’re bored in the cinema you can read about the fascinating world of heteroscedasticity instead.•Reporting your analysis: Every chapter has a guide to writing up your analysis. How one writes up an analysis varies a bit from one discipline to another, but my guides should get you heading in the right direction.•Glossary: Writing the glossary was so horribly painful that it made me stick a vacuum cleaner into my ear to suck out my own brain. You can find my brain in the bottom of the vacuum cleaner in my house.•Real-world data: Students like to have ‘real data’ to play with. The trouble is that real research can be quite boring. I trawled the world for examples of research on really fascinating topics (in my opinion). I then stalked the authors of the research until they gave me their data. Every chapter has a real research example