In terms of high sample size - my guess is that due to the relatively small variation due to paddle versus the relatively huge variation due to the other factors, you'd have a tough time finding enough paddlers to cure this by sample size. Just a hunch. Worked a bit with ecological/environmental data and it too is very 'noisy' - even with monstrous sample sizes. The idea of having each paddler test two paddles and using a difference stat might have merit - I'm not sure. There are probably some underlying assumptions that may/may not be valid - things like the relationship between aspect ratio and performance being a constant relationship across the whole range of values - is it linear? curvilinear? Does this change for each paddler for some unknown reason? People testing different portions of the range might be problematic - some might test two very similar paddles (and those may be high or low in the range), others two very different paddles with regards to aspect ratio. At any rate, it might solve part of the problem but it might introduce 'noise' of a different type. I suppose the original suggestion to use a standard paddle contains some of these same ills. K *************************************************************************** PaddleWise Paddling Mailing List - Any opinions or suggestions expressed here are solely those of the writer(s). You must assume the entire responsibility for reliance upon them. All postings copyright the author. Submissions: PaddleWise_at_PaddleWise.net Subscriptions: PaddleWise-request_at_PaddleWise.net Website: http://www.paddlewise.net/ ***************************************************************************Received on Thu Jun 12 2003 - 07:34:52 PDT
This archive was generated by hypermail 2.4.0 : Thu Aug 21 2025 - 16:31:07 PDT