Tuesday, April 27, 2010

Good for the Goose, not for the Gander

Neverending Audit finds evidence provided by Michael Mann, of non-reproducibility, non-cooperation, and statistical error from Wegman et al.

Update: This was hashed out at the time, sort of, at CA. Except for the part about Wegman being wrong.
at

4 comments:

  1. JohnMasheyApril 27, 2010 at 9:53 PM

    Oh, the zingers are piling up...
    I'd heaard about Ritson, hadn't seen the comments, had them on the list to track down.

    ReplyDelete
  2. AnonymousApril 28, 2010 at 6:02 AM

    Thanks for the attribution, but I think the hat tip belongs to Eli Rabbett. Quite frankly, I don't know what to make of all this. The only observations that I am willing to share for now are these.

    Wegman does not look a pure maths thing. Physical decisions seems to come to play. So portraying the Wegman report in all its mathematical purity seems a bit farfetched.

    The other observation is that it is quite strange that the mathematical issue relies on this report only.

    From these two observations I contend that it's worth a dig. If it's only a math thing, this will have to be played out once and for all. If it's only a math thing, this won't get us farer than other math things. Which is never very far reaching.

    ReplyDelete
  3. Martin VermeerApril 29, 2010 at 11:11 PM

    Salon had a good story about this, way back when.

    Good to see this not being forgotten.

    ReplyDelete
  4. EliRabettApril 30, 2010 at 8:18 PM

    If you read to the bottom of McIntyre's post (thanks for pointing it out), he basically shifts ground from statistic to weighting of the bristlecone pines which is kind of typical of his modus operendi

    ReplyDelete

Moderation is on. Apologies for any delays.



Err on the side of politesse and understatement please.



Before you speak, ask yourself if what you have to say will improve on silence.