by Jose Mar 9, 2006 at 08:06 PM

The key assumption in one case is that the numbers are consistent, in
the other that they are accurate.


Systematic and random error are two totally different beasts.

Jose



I do understand what you are saying: I learned the important distinction
between "precision" and "accuracy" many years ago as an undergrad science
student.

The BTS conclusion depends upon the accuracy of the "hours flown"
estimate. The Nall Study's validity depends more upon the precision
(using a method that can repeatedly reproduce the same result within a
small margin of error) of the estimating technique than on its absolute
accuracy. Thus even if the hours flown estimate is "systematically"
misestimated (i.e. is inaccurate) it would not invalidate the conclusions
of the trend analysis conclusion. Yes?

But this is really splitting hairs. The BTS study showed subsidies so
large that even if there was huge sampling error or other statistical
mis-steps that resulted in a vast underestimation of hours flown (and
therefore exaggerated GA subsides), the conclusion is still valid: that
GA is very heavily subsidized relative to other modes of transportation.


Just looking at the raw revenue number from the funding sources also makes
this quite obvious. (I'd repost the BTS data, but I've been yelled at
already for reposting the stuff....)