You need to analyse some data, and you know (or used to know) a bit about statistics, but how do you decide what to do next? Fortunately the correct selection of a statistical test is as much about pattern recognition as it is about mathematics.
As well as covering all the basics in straightforward english rather than mathematical language, Statistics for the Terrified includes a set of rules of thumb which will enable you to select the correct test for your data 90% of the time.
Although the tutorial does cover some quite advanced topics, it approaches everything in a basic, commonsense way. Having gained an understanding at this level, you will be able to approach textbooks (and statisticians!) much more confidently. Statistics for the Terrified is a valuable resource to help you refresh your knowledge, and it will accompany you through your analysis.
Most of what we thoroughly know has been learnt by observation: trial and error. Statistics can't be taught this way within the usual mathematical framework using a selection of data sets - the time required (and the number of prepared analyses) would be far too great. Fortunately however, most of us are not interested in Statistics as an academic discipline. By approaching it as a tool for practical use instead, we can be much more flexible. Mathematical proofs become irrelevant; for example, when learning to ride a bicycle, you don't need to know about angular velocity, frictional forces or gravitational pull - an intuitive understanding of all of them will be impressed on you more or less painfully!
Mathematical proof does not necessarily lead to enlightenment, and much of what we truly understand requires no 'proof' at all, but repeated, varied and directed observation. This can be achieved in statistics teaching by making it into a game, after which it can be at least as interesting as chess and certainly a lot more useful.
We introduce four basic layouts of data which correspond to the most commonly-used tests, and which show you how and why they are appropriate. After completing this section (which includes a quiz on test selection) further sections give more in-depth explanations of the various tests and techniques.
These later sections include a series of challenges and games which you play by changing the data. The data points on our graphs are your game pieces, which may be moved in any direction. You are guided through a number of scenarios, encouraged to experiment and observe changes in the resulting statistics, finally being challenged to generate particular outcomes. Although you may not understand the statistical processes at first, by the end you will have a clear intuitive grasp. By presenting the data simply and graphically, the software makes the results of your actions clear and easily understood.
With the opportunity to experiment in this way, you become experienced in
recognising patterns and exploring strategies without the risk of messing up a
real experiment. It could take up to a decade to gain this amount of experience
in actual research, during which you might make mistakes that really matter.