National Twitchathon

To: <>
Subject: National Twitchathon
From: <>
Date: Mon, 21 Nov 2005 13:20:47 +1000
I also like the "Modified Dolby System".
Team Score = Team's Total / Average of Past Winning Scores x100
I will try and track down the results (past and present) from the
regional twitchathon events and organise a national result.

I think "Average Winning Score" isn't the best norm.

(a) It doesn't reflect trends very well. If the winning total has been climbing as the locals get more sophisticated, the average might be meaningful for a decade ago, not today.

(b) In a state where someone named (say) Dooley either does or doesn't compete in any given year, with winning results changing yearly from 220+ to 170+, the average is a meaningless figure somewhere between those two "norms". Having seen some thon statistics recently this appears to be a reasonable situation.

(c) You might get the same result from good weather / bad weather years.

I note there are plenty of scientists on this list so they probably know more and better statistics than me, but I'd propose a percentile norm.

Median would not address either (a) or (b) or (c) above - it would probably be similar to the average for (a) and would be randomly in one camp or the other for (b) and (c).

Assuming that trends are upward, let's go for a high percentile mark.

Using the 100th percentile (the best score ever) has merit but that assumes that the historical record in every state has never been burdened with an outlier - one year of tick-happy burglars. (All current state record-holders please forgive and forget this apparent but utterly hypothetical aspersion.)

So I'd suggest 75th percentile or 90th percentile. 75th percentile would make us all look good. 90th percentile would best reflect a rising trend.

Any thoughts? Tim, perhaps you could apply these measures in parallel to your hypothetical historical national thons and publish the outcome. We could all vote for whichever norm makes our own result look best 8^)

On consideration we also need to allow for the variation in the results... The winner is the team which gets the most standard deviations above the norm for his state?
mark(at)  0404 50 99 24

Russell Woodford
Learning Technologies Coordinator
Sacred Heart College Geelong

This email and any attachments may be confidential and if you are not the intended recipient, you must not disclose or use the information in this email. If received in error, please notify us immediately and delete the email and all copies. The College does not guarantee that this email is virus or error free. The attached files are provided, and may only be used, on the basis that the user assumes all responsibility for any loss, damage or consequence resulting directly from the use of the attached files, whether caused by the negligence of the sender or not. The content and opinions in this email are not necessarily those of the College. --------------------------------------------
Birding-Aus is on the Web at
To unsubscribe from this mailing list, send the message:
'unsubscribe birding-aus' (no quotes, no Subject line)

<Prev in Thread] Current Thread [Next in Thread>

The University of NSW School of Computer and Engineering takes no responsibility for the contents of this archive. It is purely a compilation of material sent by many people to the birding-aus mailing list. It has not been checked for accuracy nor its content verified in any way. If you wish to get material removed from the archive or have other queries about the archive e-mail Andrew Taylor at this address: andrewt@cse.unsw.EDU.AU