Damned Lies and Statistics - 2

15. The media often fail to question activists' generalizations.
16. Good statistics meet four standards. First, good statistics are based on more than guessing. Second, they are based on clear, reasonable definitions. Third, they are based on clear, reasonable measures and finally, they are based on good samples.
17. One good sign of good statistics is that we're given more than a number; we're told something about the definitions, measurement, and sampling behind the figure - about how the number emerged. When that information remains concealed, we have every reason to be skeptical.
18. Never overestimate the understanding of an innumerate public.
19. When we discover a difference between two groups (e.g that black and white have different arrest rates), it is easy to assume that the obvious differences between the groups (races) causes other differences (e.g., in arrest rates). It is always possible that something else, some other variable (such as class) actually causes the difference. This is an important issue in philosophy: apparent relationships between two variables that are actually caused by a third variable are called spurious.
20. Another flawed method of emphasizing a problem's importance is to focus on some narrowly defined population where the problem is relatively concentrated.
21. One interesting way of claiming authority in recent years has been to publish collections of social problems statistics in small, specialized reference books. The titles of these volumes often emphasize the factual nature of the contents, even though the books frequently promote a particular ideology or the interests of a specific group.

Confronting the Inevitable

As a pratical matter, it is virtually impossible for citizens in comptemporary society to avoid statistics about social problems. Statitics arise in all sorts of ways, and in almost every case the people promoting statistics want to persuade us. Activists use stats to convince us that social problmes are serious and deserve our attention and concern. Charities use stats to encourage donations. Politicians use stats to persuade us that they understand society's problems and that they deserve our support. The media use stats to make their reporting more dramatic, more convincing, more compelling. Corporations use stats to promote their products and improve their profits. Researchers use stats to document their findings and support their conclusions. Those with whom we agree use stats to reassure us that we're on the right side, while our opponents use stats to try and convince us that we are wrong. Stats are on of the standard types of evidence used by people in our Society. It is not possible to ignore stats, to pretend they don't exist. That sor of head-in-the-sand approach would be too costly. Without stats, we limit our ability to htink thoughtfully about our society; without stats, we have no accurate ways of juding how big a problme may be, whether it is gettin gworse, or how well the policies designed to address that problems actually work.

No comments:

Post a Comment