Your Universal Remote Control Center
RemoteCentral.com
Everything Else Forum - View Post
Up level
Up level
The following page was printed from RemoteCentral.com:

Login:
Pass:
 
 

Original thread:
Post 63 made on Thursday September 12, 2019 at 20:46
djy
RC Moderator
Joined:
Posts:
August 2001
34,746
On September 12, 2019 at 14:33, BizarroTerl said...
Since I apparently wasn't specific enough for you before -
The quote above from YOUR post (#58) you infer there has been no independent verification of the "hockey stick graph".

In post 26 I quoted from wikipedia showing there have been two dozen reconstructions confirming the science and results of Mann's research.

If that's not specific enough then I'm definitely wasting my time and David's rant was accurate.

If you aren't interested in the science and just want to feel you're right (contrary to the consensus of the credible scientific community) just say so. Everyone has a right to have their own opinion.

I think one is missing the point. If I were to produce a study using 'novel statistical techniques' to claim black is white, and then offer my code and data to colleagues for them to produce their own 'independent' research to claim the same, does that prove the research is correct, or could it be there's an error in the data and code biasing the result? This is what independent verification seeks to confirm. One could produce a million reconstructions offering the same conclusion, but if the underlying statistical analysis is wrong then so to are all the conclusions.

Steve McIntyre’s analysis of Mann’s original work suggests it mines for hockey sticks: his inputting random red noise data produced a hockey stick. The 2006 NAS Report says "Mann et al. used a type of principal component analysis that tends to bias the shape of the reconstructions”, i.e. produce hockey sticks from baseball statistics, telephone book numbers, and monte carlo random numbers.”

Whether this was wilful, careless or incompetent we don't know for Mann has consistently refused to offer his r2 regression numbers for review; even to the extent of being prepared to lose his eight year libel suit against Tim Ball1.

Yes, I'm interested in the science (can one not tell?), but it needs to be open to scrutiny not locked away in a drawer. Indeed, this is true for all research but particularly so for work underpinning demands for such profound political change.

As I said, there is no doubt Mann is well educated, but competent? I reserve judgement until he allows independent verification of the data and code for his hockey stick graph.

[1] [Link: principia-scientific.org]

Last edited by djy on September 13, 2019 02:39.


Hosting Services by ipHouse