Statistics and anecdotes

I have no confidence in an argument when the person making the point quotes statistics without explaining how they were derived or at least cite the source. On the surface, statistics have an air of credibility. People believe that statistics are derived from a rigid, scientific process and therefore must be true. Of course, this isn’t always true. What’s the old joke… 90% of statistics are made up.

When statistics are unavailable, misunderstood or just plain don’t make sense, anecdotes can come to the rescue. While not having the force or scope of scientifically derived statistics, a good story goes a long way in the effort to exchange ideas. Isn’t that really the point of all of this anyway?

Unfortunately, anecdotes don’t come with a well-defined methodology. This makes people sloppy. I think a very basic rule should be: if you’re going to reason by anecdote, at least cite the anecdote. Rule 2 should be: conclusions drawn from anecdote can NEVER be as verifiable as conclusions drawn from statistics so don’t suggest as much.

From CT: “Anyone who’s been following recent discussion of the US economy will be aware that the Bureau of Labor Statistics produces employment statistics from two different surveys, and that the results have diverged radically since 2001… While noting some reasons for the discrepancy, the BLS seems to be sticking with the payroll survey, noting that there are a lot of problems in estimating employment growth from the CPS, and that the payroll data is consistent with data on new claims for unemployment benefits… Allowing for the fact that non-employed people are divided between unemployed and those not in the labour force, the discrepancy could easily be a full percentage point, implying that unemployment is now higher than when the recovery (as measured by output) began. This seems consistent with anecdotal impressions.” (emphasis added)

My question to the CT folks: what are these anecdotes that allow you to ascertain a one percent change in the aggregate unemployment rate? If your so in tune with such aggregate conditions of the economy, why do we need to measure unemployment at all?