On 16-Jun-2005, Peter wrote:

No, it clearly was never true. Even taking the subset of kayaks you
chose, you calculated a correlation coefficient of 0.79 indicating a
very high level of correlation.

Not high enough and nowhere near the level you claimed without any
proof.

The _fact_ is that at that level, the differences in overall length
between two kayaks are comparable to the differences in overall
length and waterline length in one kayak. Clearly a much higher
level of correlation is required than 0.79. In this case, the
mathematic definition of correlation has to take a back seat
to the more pragmatic need to produce information that is of
some value.


If all kayak types were included the
correlation would be even higher.

Your claim - how about something resembling proof? Your last
guess of 0.95 was based on nothing.

In the particular case of the two kayaks considered by the OP, their
lengths only differed by about 2' but the hull shapes appear to be quite
similar with no obvious difference in overhang. Therefore it's highly
likely that the Biscyne which is longer overall will also have a longer
waterline length.

Even if it does have a longer waterline length, that still does not
guarantee that the speed is higher. Hydrodynamics trumps simple
geometric parameters.

How about offering something of value instead of simply trying
to not-pick? Like offering some data that actually backs up you
ludicrous claim that what I am saying is false.

Mike

Michael Daly wrote:
Like offering some data that actually backs up you
ludicrous claim that what I am saying is false.

You already provided it yourself. After first making the claim that
there was "no correlation" between LOA and LWL, you later provided data
indicating that the correlation was 0.79 which clearly showed your
initial statement to be false. QED.

On 17-Jun-2005, Peter wrote:

You already provided it yourself. After first making the claim that
there was "no correlation" between LOA and LWL, you later provided data
indicating that the correlation was 0.79 which clearly showed your
initial statement to be false. QED

I've already addressed that - the correlation is not sufficient to
allow for prediction of performance. You are ignoring that _fact_.

As a further indicator of the relevance of LOA as an indicator of
performance, let's look at the correlation between the lengths
and the drag for the kayaks already presented.

Correlation coefficient, LOA vs Drag: -0.35
Correlation coefficient, LWL vs Drag: -0.69

Clearly, an intelligent person would not use LOA as an indicator
of performance. This further shows that the correlation between
LOA and LWL is insufficiently high. It also shows that other
factors beyond just length dictate drag, otherwise the coefficient
for LWL vs drag would be higher.

For cranky ol' rick, I'll get to other factors later.

Mike