Artificial Groundwater Recharge: Proceedings of a Conference Held at the University of Reading, England, 21-24 September 1970 Book

I have a rather irregular history with statistics. After disliking maths GCSE but getting a very good mark, I avoided A-level maths like the plague. Upon arriving at university as a fresh-faced undergrad, I was disconcerted to discover that the first year of my social science degree included a compulsory statistics module. I passed that, then chose modules with no maths for the remaining two years. My dissertation was entirely qualitative. When I returned to studying as postgrad years later, I’d grudgingly come to accept that statistics are useful. My masters course included two statistics modules, which I appreciated the purpose of without enjoying. Then somehow, during the peculiar derangement of my PhD, I ended up teaching myself to use a fairly complex statistical methodology: multinomial logistic regression. The majority of my PhD research was quantitative. Now I find myself actually teaching statistics to undergrads. My 18 year old self would be amazed and horrified. It’s quite possible that I’m still outgrowing an ingrained dislike of maths that has much more to do with uninspired school teaching than the subject itself. In any case, I have a decent grasp of what stats are and why they’re useful, by social science standards.

So why read this book? Because the undergrads I taught this term, and probably the postgrads I’ll teach next term, appear petrified and confused by quantitative methods. It’s so difficult to tell whether students are really grasping the concepts you explain in lectures, particularly when there’s no exam to test comprehension. These are social science students and their prior exposure to stats seems to have been minimal. When I spotted this book in library, I wondered if it could help me to explain the basics more clearly. And I think it just might. I found it very easy to follow and a helpful reminder. Rowntree’s explanation of the difference between parametric and non-parametric tests is especially lucid and useful. That said, I doubt I'll have time to include such careful and painstaking explanations in my lectures. I’ll definitely recommend the book to students, though. It’s not at all fashionable to suggest students read entire books, but honestly I think this one is much better than an explanatory video, the more trendy teaching medium.

What this book cannot do, of course, is show you how to perform t-tests, correlation analysis, and regression in Excel or a proper stats programme. (I like R and tolerate SPSS.) While use of R or similar enables speedy and convenient quantitative analysis to a degree that was impossible in the era of graphing calculators, it also encourages an air of mystery around statistical techniques generally. The actual theory behind the technique is concealed. This book is brilliant for demystification; it narrates without equations to make clear that stats aren’t some arcane form of computer science. In the absence of basic understanding, it’s pointless to feed your data into a stats programme as you won’t understand the results you get, even if you happen upon a suitable technique for analysis. In a research methods lecture, there is sadly little time to cover explanatory fundamentals as the focus is on applied techniques. Somehow over more than 15 years, my refusal to take A-level maths has evolved into a wish that my students had taken it. Truly academia is fraught with irony.

Be that as it may, if you teach statistics to reluctant students, this book will give you helpful suggestions and food for thought. If you’re a reluctant student, or just wary of statistics, I highly recommend reading it as a short and gentle introduction. If nothing else, statistics are an extraordinary powerful force in the data-saturated world we live in. A basic understanding of their underpinnings and limitations will really help you to make sense of life. As I argued to my students, they can also make you seem like a magician to people who fear statistics. In academia, a clear understanding of stats is essential to enable you criticise other people’s work. Which is surely the whole point of research.