Nonetheless,the threshold b= 0 “

]]>http://www.meteor.iastate.edu/classes/ge415/papers/Mann_et_al_Nature1998.pdf

From pg 785 of the Nature paper:

“b is a quite rigorous measure of the similarity between two variables,

measuring their correspondence not only in terms of the relative departures

from mean values (as does the correlation coefficient r) but also in terms of the

means and absolute variance of the two series. For comparison, correlation (r)

and squared-correlation (r2) statistics are also determined. The expectation

value for two random series is b ¼ 21. Negative values of b may in fact be

statistically significant for sufficient temporal degrees of freedom. Nonetheless,

the threshold b ¼ 0 defines the simple ‘climatological’ model in which a series

is assigned its long-term mean. In this sense, statistically significant negative

articles values of b might still be considered questionable in their predictive or

reconstructive skill. Owing to the more rigorous ‘match’ between two series

sought by b, highly significant values of b are possible even when r2 is only

marginally significant.”

The formula he was referring to was RE, not r^2-

]]>Tobis – You should believe people who are smarter than you and we are much smarter than you

SMc – 2+2=4

Tobis – Mann is smarter than me and he says 2+2=5

SMc – 2+2=4

]]>Could you possibly do a ‘unilateral joint paper with the team’. Sounds strange but it would be useful if you could set out areas where there is agreement, where there is fundemental disagreement and where here are different interpretations?

Ron

]]>