The best tip for handling data is to enjoy yourself. Data can appear forbidding. But allow it to intimidate you and you’ll get nowhere. Treat it as something to play with and explore and it will often yield secrets and stories with surprising ease. So handle it simply as you’d handle other evidence, without fear or favour. In particular, think of this as an exercise in imagination. Be creative by thinking of the alternative stories that might be consistent with the data and explain it better, then test them against more evidence. ‘What other story could explain this?’ is a handy prompt to think about how this number, this obviously big or bad number, this clear proof of this or that, might be nothing of the sort.

Don’t confuse skepticism about data with cynicism. Skepticism is good; cynicism has simply thrown up its hands and quit. If you believe in data journalism, and you probably do or you wouldn’t be reading this book, then you must believe that data has something far better to offer than the lies and damned lies of caricature or the killer facts of swivel-eyed headlines. Data often give us profound knowledge, if used carefully. We need to be neither cynical nor naive, but alert.

If I tell you that drinking has gone up during the recession, you might tell me it’s because everyone is depressed. If I tell you that drinking is down, you might tell me it’s because everyone is broke. In other words, what the data says makes no difference to the interpretation that you are determined to put on it, namely that things are terrible one way or the other. If it goes up, it’s bad, if it goes down, it’s bad. The point here is that if you believe in data, try to let it speak before you slap on your own mood, beliefs or expectations. There’s so much data about that you will often be able to find confirmation of your prior beliefs if you simply look around a bit. In other words, data journalism, to me at least, adds little value if you are not open-minded. It is only as objective as you strive to make it, and not by virtue of being based on numbers.

Uncertainty is ok. We associate numbers with authority and certainty. Often as not, the answer is that there is no answer, or the answer may be the best we have but still wouldn’t hit a barn door for accuracy. I think we should say these things. If that sounds like a good way of killing stories, I’d argue that it’s a great way of raising new questions. Equally, there can often be more than one legitimate way of cutting the data. Numbers don’t have to be either true or false.

The investigation is a story. The story of how you tried to find out can make great journalism, as you go from one piece of evidence to another — and this applies in spades to the evidence from data, where one number will seldom do. Different sources provide new angles, new ideas, richer understanding. I wonder if we’re too hung up on wanting to be authoritative and tell people the answer — and so we miss a trick by not showing the sleuthing.

The best questions are the old ones: is that really a big number? Where did it come from? Are you sure it counts what you think it counts? These are generally just prompts to think around the data, the stuff at the edges that got squeezed by looking at a single number, the real-life complications, the wide range of other potential comparisons over time, group or geography; in short, context.