Monday, August 25, 2008

Tyee Update

Here's the latest corrected update from DFO on Tyee Steelhead numbers:
Aug.22: 1.45
Aug.23: 2.10
Aug.24: 2.88
Aug.25: 1.46
Total to date: 125.59


Paul Holden said...


A statistic that gives a better picture of the run would be the median, rather than the average. Averages are distorted by very large runs, of which there have been a few over the past decades, but the norm is much lower runs. For example, the median for the decade beginning 2000 is 86, which puts the 2008 steelhead run 55 per cent above the median, while it is 21 per cent above the average shown on the tyee site. However, I cannot reproduce how they get the 110 average for this period. The sum of the years for which there are data on August 27 divided by 5, the number of years is 119.6 because of two very large runs. On the other hand, if they included the years for which there are no data on August 27, but simply add the numbers up to the dates for which data are available, the average is 99, so I cannot understand how the figures are calculated.

In any case, the median is a better comparative measure of the size of the run


North Coast Steelhead Alliance said...

Thanks for that, Paul....good points.
You illustrate the age old numbers game which DFO is very experienced at. Your point of how statistics are presented is almost as important as the stats themselves. And to get even more complicated..and somewhat potentially the fact that the Tyee Index is 'adjusted' by a variety of statistical 'inputs'. Sound familiar? Maybe like the infamous Skeena Management Model and it's overly generous 'inputs'.
We are exploring this aspect of Tyee and might do a post on it in the future.
Thanks again for highlighting these issues.