Comments on: Just like in the REAL world http://dimpost.wordpress.com/2013/02/22/just-like-in-the-real-world/ It is difficult not to write satire - Juvenal Thu, 23 May 2013 02:33:05 +0000 hourly 1 http://wordpress.com/ By: Clunking Fist http://dimpost.wordpress.com/2013/02/22/just-like-in-the-real-world/#comment-86244 Tue, 05 Mar 2013 07:21:58 +0000 http://dimpost.wordpress.com/?p=14153#comment-86244 (Rhino, I read your comment by email. it seems once the no. of comments increase AND time has elapsed since the first comment, WordPress gets bored and moves on.)
“I can’t respond because I simply cannot tell what you are trying to say. Anyway, I can say that the principle of GIGO applies – that is, Garbage In Garbage Out. Statisticians’ work is limited by the information that that is given to them and the methodology that they employ.”
Even if they employ the best methodology, if the “info given them” is poor, then the results will be poor.
(cross my fingers and press “post comment”)

]]> By: Clunking Fist http://dimpost.wordpress.com/2013/02/22/just-like-in-the-real-world/#comment-86139 Thu, 28 Feb 2013 23:22:43 +0000 http://dimpost.wordpress.com/?p=14153#comment-86139 It doesn’t matter, Brad: your statistical techniques are rendered obsolete by this new “climate” science.

]]> By: bradluen http://dimpost.wordpress.com/2013/02/22/just-like-in-the-real-world/#comment-86128 Thu, 28 Feb 2013 18:01:14 +0000 http://dimpost.wordpress.com/?p=14153#comment-86128 (I’m staying the fuck out of the climate discussion but as a philosophy-of-statistics pedant I note that there is no direct connection between objectivity and noninformative priors. A noninformative prior is not objectively true and is sometimes (pace E.T. Jaynes) demonstrably wrong. At best, inference is objective conditional on a noninformative prior, just as at best inference is objective conditional on an informative prior. This is not to imply that the paper in question should or should have used a noninformative prior because I haven’t read the paper and I don’t care to.)

]]> By: Clunking Fist http://dimpost.wordpress.com/2013/02/22/just-like-in-the-real-world/#comment-86098 Thu, 28 Feb 2013 00:40:46 +0000 http://dimpost.wordpress.com/?p=14153#comment-86098 Here’s a statistician talking about the complexities around the temperature data:
“James Annan has indeed attacked the use of a uniform prior when estimating climate sensitivity. As I recall, he initially tried to do so by way of a comment on the Frame et al (2005) paper, but could not get the journal to publish it. So he had to write a full paper, dealing with other things as well.

The real problem is that very few people involved in climate science have any real understanding of objective Bayesian methods, which require the use of a noninformative prior. Consequently, they (and readers of their papers) can have little understanding of the extent to which the priors they have chosen bias their estimation of climate system parameters. I am doing what I can to to help remedy this, along with one or two others. Unfortunately, one the very few published climate science papers about noninformative priors, which relates to estimating climate sensitivity, is badly wrong.”

Jan 12, 2013 at 10:04 PM | Nic Lewis
http://www.bishop-hill.net/blog/2013/1/12/lewis-on-schmidt-on-climate-sensitivity.html (yes, yes it’s a blog, not quite as good as wikipedia I know)

]]> By: Clunking Fist http://dimpost.wordpress.com/2013/02/22/just-like-in-the-real-world/#comment-86096 Thu, 28 Feb 2013 00:35:00 +0000 http://dimpost.wordpress.com/?p=14153#comment-86096 Hi Rhino, I was working through that Wikipedia list of studies/surveys of scientists’ opinions.
It all looks a bit flawed. Take Naomi Oreskes study: 75% of the papers she reviewed did not disagree with the consensus position in their abstracts. But this seems to include many studies which implicitly accept the position, because their remit was to evaluate impacts or study mitigation proposals.
A possible analogy: An engineer, who sees no need for a motorway that has been approved for her town, will still likely consider quoting for the engineering consultancy work.

The Harris Interactive study, I can’t find the response rate, etc.

I’m getting bored with all these “Christians admit to belief in god” surveys.

So here’s a survey for you, which I made up earlier: we ask loads of Doctors in 1950 “What causes ulcers and what to do about them?”
97.7% said “Caused by stress. Relax, if that doesn’t work, we’ll cut it out!”.
Turns out that it is mostly bacteria, and treatment can comprise antibiotics. So, no need to step down as CEO of Solid Energy just yet.

The consensus once held that the sun revolved around the world, nationalism was healthy, eugenics is scientific & moral, powered flight is impossible, etc.

]]> By: rhinocratesBrett Davidson http://dimpost.wordpress.com/2013/02/22/just-like-in-the-real-world/#comment-86054 Wed, 27 Feb 2013 04:58:24 +0000 http://dimpost.wordpress.com/?p=14153#comment-86054 Jesus tap-dancing Christ in a sidecar, I fucking HATE WordPress. This is my third or forth attempt.

Yes, as you see, that is my name. Wonderful. Wonderful WordPress morons – you’re shits. You just need to know that. So much for confidentiality.

Anyway…

Sorry, you show no sense of syntax, so I can’t reply and I can only guess at what you mean to say.

I’m not a climate scientist, simply a statistician, but I can see from here that you have a co-linearity problem, the wrong r value, and have used strange propaganda reasons to move from one proxy to another when it suits your purpose, and have attempted to hide the fact that you did it. But all good, it’s for the cause.

I’m sorry, but this sentence shows no syntax.

I’m not a climate scientist, simply a statistician, but I can see from here that you have a co-linearity problem, the wrong r value, and have used strange propaganda reasons to move from one proxy to another when it suits your purpose, and have attempted to hide the fact that you did it. But all good, it’s for the cause.

I can’t respond because I simply cannot tell what you are trying to say. Anyway, I can say that the principle of GIGO applies – that is, Garbage In Garbage Out. Statisticians’ work is limited by the information that that is given to them and the methodology that they employ.

That’s it. I’m unlikely to post again because fucking WordPress is so unreliable.

]]> By: Clunking Fist http://dimpost.wordpress.com/2013/02/22/just-like-in-the-real-world/#comment-86047 Wed, 27 Feb 2013 02:24:10 +0000 http://dimpost.wordpress.com/?p=14153#comment-86047 Eh? I did think I’d already hit “post” but thought I must’ve dreamt it, so pushed “post” again. WordPress? Free cloud services: not free of bugs…

]]> By: Clunking Fist http://dimpost.wordpress.com/2013/02/22/just-like-in-the-real-world/#comment-86046 Wed, 27 Feb 2013 02:22:43 +0000 http://dimpost.wordpress.com/?p=14153#comment-86046 “You are a”n artifact from a recycled word document? I have no idea what that was, except perhaps Cthulhu’s pet hate: a lack of edit function?

“As you’re not a dentist, I won’t let you near my teeth.”
Not even close, how about:
As you’re not a statistician, I won’t let you near my statistics.
Or:
As you’re a computer programmer (not a climate scientist), I won’t let you near my climate computer model. But feel free to enjoy the climate.
Or:
I’m not a dentist, but I do clean and floss my own teeth. I’m also licenced to masticate.
Howsabout:
I’m not a climate scientist, simply a statistician, but I can see from here that you have a co-linearity problem, the wrong r value, and have used strange propaganda reasons to move from one proxy to another when it suits your purpose, and have attempted to hide the fact that you did it. But all good, it’s for the cause.

(I shall have a look at your 97% data later.)

]]> By: Clunking Fist http://dimpost.wordpress.com/2013/02/22/just-like-in-the-real-world/#comment-86045 Wed, 27 Feb 2013 02:12:22 +0000 http://dimpost.wordpress.com/?p=14153#comment-86045 “You are a”n artifact from a recycled word document? I have no idea what that was, except perhaps Cthulhu’s pet hate: a lack of edit function?

“As you’re not a dentist, I won’t let you near my teeth.”
Not even close, how about:
As you’re not a statistician, I won’t let you near my statistics.
Or:
As you’re a computer programmer (not a climate scientist), I won’t let you near my climate computer model. But feel free to enjoy the climate.
Or:
I’m not a dentist, but I do clean and floss my own teeth. I’m also licenced to masticate.
Howsabout:
I’m not a climate scientist, simply a statistician, but I can see from here that you have a co-linearity problem, the wrong r value, and have used strange propaganda reasons to move from one proxy to another when it suits your purpose, and have attempted to hide the fact that you did it and got angry with me when I pointed it out. But all good: it’s for the cause! (Please delete my email, by the way: I would’t want someone to see this using Freedom of Information/Offical Information Acts.)

]]> By: Rhinocrates http://dimpost.wordpress.com/2013/02/22/just-like-in-the-real-world/#comment-86044 Wed, 27 Feb 2013 01:43:23 +0000 http://dimpost.wordpress.com/?p=14153#comment-86044 As I’m not a politician, I couldn’t possibly be allowed to vote, either, eh?

As you’re not a dentist, I won’t let you near my teeth.

You are a

The rest, please… a good ad hominem would should clearly how you choose to argue.

Our result is based simply on the close agreement between the shape of the observed temperature rise and the known greenhouse gas increase.

Spherical cow. It deliberately leaves out factors such as oceanic absorption of heat, ENSO, etc, “Simpler” is not “truer”.

]]>