Monday, August 22, 2011

States are bad sample sets

The variation of the mean of a sample (here the number of bankruptcies each month) is inversely proportional to the square root of the sample size (here the number of people in each state). In English, that means the larger a state's population, the less likely its bankruptcy filing rate will gyrate from month to month. Smaller states--like Vermont and Utah--are more likely to end up on the extremes than larger states.Bob Lawless at Credit Slips

When I look at states, I specifically look at them as bad samples, showing the distortionary effect.

No comments: