Walter Laqueur, co-chair of the International Research Council at the Center for Strategic and International Studies and one of the world's leading experts on terrorism, has posted a short item on terrorism statistics at The Free West. He makes the point that any statistics on terrorism reported in the media must be viewed with great caution and, indeed, skepticism. "It is not that these statistics are wholly useless, but they are bound to be incomplete and quite often they are offered by institutions or individuals peddling their own agendas." This observation seems obvious, but such statistics have been thrown around more often in recent years, so it is good to be reminded.

Some facts about terrorism are clearly beyond dispute; terrorist attacks are not usually carried out by babies or by elderly people. But to know why, no elaborate data base is needed. Or the fact that terrorism occurs only in democracies or very ineffective dictatorships; the reasons are utterly obvious. But the moment the theory builders get more ambitious, great caution is advisable . . .

Mr Laqueur rightly rejects the old canard "figures speak for themselves" in connection with terrorism statistics. Whenever I hear that said in connection with any statistic, red flags jump out all over the place. In my experience, it is almost always the case that the person saying that has overlooked some salient related facts–or has a hidden agenda.

Speaking as a professional statistician, I would say the opposite is closer to the truth: As a general rule, figures never speak for themselves. Be very skeptical whenever you hear someone say, "The numbers speak for themselves". Numbers only make sense when placed in a context or other interpretive framework.