Response to Tamino’s ‘More Mathturbation’

I spent a fair amount of time responding to this fool’s diatribes regarding my post on the statistical significance of warming. I took offense at his title ‘More Mathturbation’, which I suspect that he found clever. He also tried to apply Dunning Kruger to myself. Bad move. Let’s see if he posts my response.

Update1: He has, although he doubled down on the gratuitous insults.

Update2: He is now refusing to approve my answers to the objections raised in the discussion. It’s pretty easy to win an argument when you don’t allow answers. LOL. He’s going to regret that one.

I also responded to AlexC over there and reproduced it here. Similar stupidity.

GreenHeretic’s Response to Tamino’s blog posting, ‘MORE MATHTURBATION’

Tamino: If you are going to critique someone else’s blog posting, especially with gratuitous insults, why isn’t it your practice to post something ‘over there’ to alert them? I don’t think much of your ethics.

Did you actually READ my post? Apparently not since you misrepresented why I rejected the Temp=f(CO2) relationship. True, I rejected the original model because of the strong autocorrelation of the errors. However, you are correct that such a deficiency can be ‘compensated’.

In the article I wrote, I rejected pursuing the question down that rabbit hole because CO2 explained no more than a simple time trend model. Real analysts with decades of modeling experience (like myself) understand the importance of that fact.

CO2 has no discernible incremental association with temperature beyond mere correlation over time. Nevertheless, I did waste considerable time exploring, but found nothing worth reporting. That led me to ask the question as to whether an actual trend existed. I am well aware of the dictum, ” It turns out that there isn’t, which is what the article demonstrated and concluded.

You claim that substituting an ARIMA(1,1,0) aka simple change model is not appropriate and say “I’ll bet he learned that in econometrics class.” I learned that in a graduate level advanced regression class in the late 1970s.

When I started analyzing weather in the energy sector in a professional capacity nearly twenty years ago, I validated the application of ARIMA methods for weather. My citation for the appropriateness of analyzing weather data using ARIMA is Daniel Wilks, ‘Statistical Methods in the Atmospheric Sciences’ published by Academic Press in 1995 (First Edition). It’s up to Third Edition today. You can find it easily enough on Amazon. Chapter 8 in my edition is entitled ‘Time Series’ should convince even you that my methodology is accepted by meteorology professionals.

I am not sure what your point was in your discussion of ‘unit root’. If you believe that my analysis has a problem with stationarity, then you should show it, with numbers. Hint: The problem when the dataset fails stationarity is that spurious regression relationships are reported, NOT when no regressions are reported. It’s clear that you have no idea what you are blathering about.

Your point regarding my lack of appropriateness tests for the ARIMA model is actually partially well taken. The ARIMA(1,1,0) shows an annoying negative residual autocorrelation at the fourth lag. A better fit model would have been to add a seasonal term. For other purposes, I would have done that. However, since it didn’t change the outcome (which was to check for statistical significance for the drift term in the ARIMA model), I didn’t include it.

As for your application of the so-called Dunning Kruger phenomenon, I suspect that you should really look in the mirror for the best example of that. You really haven’t a clue what you are talking about. Your multiple insults show a lack of maturity and lack of basic respect for those who disagree with you. Grow up.

—————–
AlexC << However, he first differenced the data. Of course there is no significant trend leftover, because first differencing makes series stationary. This is really all that needs to be said >>

Question, AlexC: Did you PASS intermediate statistics? Had you been in the class that I TA’d, I would have failed you on that piece of your final exam. You don’t even understand the rudiments of an ARIMA model.

When you difference, you don’t eliminate the trend in any way. The trend ‘moves’ from a coefficient to become the constant, aka ‘drift’ in time series vernacular.

Update: AlexC has acknowledged my point on data differencing and trend analysis. Good for him. Unlike Tamino, he has integrity. Even if we disagree, I can respect him.

  • http://GreenHeretic.com/ GreenHeretic

    Tamino’s Response.

    “Response: The fact that you don’t understand why one should test for a unit root tells us a lot. Your further bloviating about the relationship between temperature and CO2 being “mere correlation” reveals astounding ignorance; causation follows from fundamental laws of physics. Your disdain of surface temperature data and overconfidence in satellite data is certainly not founded in sound science; I suspect it’s only because it gave you an excuse to get your silly result. A little understanding has given you a far too high an opinion of your own ability, hence the reference to Dunning-Kruger. As for your post, it’s a fine example of why I coined the term “mathturbation.”

    Tamino should actually try some analysis some time.

    • Kevin O’Neill

      Correlation does not mean causation, but as Tamino points out the causation comes from *physics* – the radiation absorption spectrum of CO2 (and other GHGs) and the laws of thermodynamics.

      This is where not understanding the *science* gets so many statisticians into trouble. They don’t understand that there are *physical* constraints on the data. Temperature cannot of it’s own (over the time frames we’re discussing) follow a random walk – something has to *move* it. Nor can it increase over time without some reason behind the increase.

      One must also consider *all* of the data. It is a very big sign of failure when one has to exclude data for nothing but arbitrary reasons. We have surface temperature data going back decades/centuries/milennia and further. Which theory can explain the earth’s ability to escape ‘snowball earth’ conditions? Which theory can explain glacials and interglacials? Which theory can explain the modern increase in temperatures? Well heck, turns out the GHG theory does all of the above.

      So we start with the physical laws of radiative absorption. What is the physical consequence of adding CO2 to the atmosphere? We raise the temperature of the atmosphere – until we reach an altitude where the opposite effect should start to happen. Voila! Tropospheric warming and stratospheric cooling just from first principles.

      We also look at the distribution of land masses. From first principles we can again deduce that the land should warm quicker than the seas. The northern hemisphere has much more land than the south. Ergo, we should see more warming in the north than the south. In addition, there is a lot of ice/snow in the north that when warmed will melt. This will be a positive reinforcing feedback. Arctic amplification! Does the data support this? Absolutely.

      Now carrying those cards in our pocket we look at a correlation of temperature and CO2. We look at UAH (or RSS). we look at global surface temperature data, we look at the arctic (not fully covered by satellites) and note the dwindling sea ice. What in this picture is amiss? Nothing. Only a science denier – a latter day Inquisitor of the Church of Nay-sayers – could miss the elephant hiding in the room.

      Oh wait – apparently *time* warmed the planet. Interesting theory. Don’t quit your day job.

      • http://GreenHeretic.com/ GreenHeretic

        Tamino has started to refuse to post my answers. He’s going to regret that.

        My answer to him was: If so, where’s the warming? We have seen a 19% increase in CO2 concentrations since 1979; why have we seen no statistically significant warming in the lower troposphere over that period? Einstein said, “No amount of experimentation can ever prove me right; a single experiment can prove me wrong.” THAT is the POWER of statistics over ‘physics’.

        “Consider *all* of the data? You can’t and you don’t need to. Your point is absurd on its face.

        You ask, what is the physical consequence of adding CO2 to the atmosphere? The Deniers answer, you get a little bit of warming. The Warmists answer, you get a lot of warming because the increased temperature cascades due to a feedback. Who is right? The DATA confirms that the Deniers are spot on.

        The arctic is not fully covered by satellites? ROTFLMAO!!! The satellites used for measuring deep atmosphere temperatures are in a POLAR ORBIT.

        • Kevin O’Neill

          UAH has LT coverage from 85S to 85N

          RSS has TLT coverage from 70S to 82.5N

          So much for capitalizing “POLAR ORBIT” – it doesn’t matter. They still don’t have full coverage of the arctic. Much like your ‘solar parallax’ mistake you once again prove you are not only clueless, but you aren’t even familiar with the dataset you claim to analyze. That’s why statisticians – or erstwhile statisticians – make so many simple mistakes. You’re just playing with numbers and have no sense of what they actually mean. Mathturbation indeed.

          For instance, you wrote, “There is no reason to expect any substantive temperature divergence between the surface and the lower troposphere that lies directly above it.” I remarked in the previous post that this is a faulty assumption. You had no answer to that, but in case you don’t believe me, here’s an expert:

          “The new LT trend of +0.114 C/decade (1979-2014) is 0.026 C/decade lower than the previous trend of +0.140 C/decade, but about 0.010 C/decade of that difference is due to lesser sensitivity of the new LT weighting function to direct surface emission by the land surface, which surface thermometer data suggests is warming more rapidly than the deep troposphere.”

          And who wrote that? Dr Roy Spencer – ya know, the guy who puts out the UAH data. Your divergence assumption shot down by the very man that produces the data. Now *there’s* an LOL.

          • Kevin O’Neill

            Apparently GreenHeretic ran into reality and found that his insanity is easily recognizable outside the usual echo chamber he inhabits. When confronted with facts that directly challenge his ‘knowledge’ he’s suddenly silent.

          • http://GreenHeretic.com/ GreenHeretic

            I missed the fact that you had responded.

          • http://GreenHeretic.com/ GreenHeretic

            ~ The UAH dataset covers all but five degrees of latitude north and south. That is trivial. How many surface temperature measuring stations do we have in those far northern and southern latitudes? VERY few. Those regions are very difficult to access. Duh. Moreover, measuring surface temperatures is fraught with difficulties that we do not experience with lower troposphere measurements. But, rely on such measurements from a remote station that is not accessible for most of the year? LOL.

            ~ I see nothing your recitation of Spencer’s trendline that addresses the question of whether it is statistically significant. That is BASIC to empirical science. Without that, you have no evidence of an actual trend. Hint: I’ve been doing this kind of work for decades.

          • Kevin O’Neill

            Do we really need to requote your words? I guess so: “The arctic is not fully covered by satellites? ROTFLMAO!!! The satellites used for measuring deep atmosphere temperatures are in a POLAR ORBIT.

            But, as you now admit, the arctic is NOT fully covered by satellites – which is exactly what I said that you found so funny. But you can’t admit your error. Now your refrain is “the UAH dataset covers all but five degrees of latitude north and south.” Last time I checked, all but 5 degrees N & S still amounts to NOT FULLY COVERED. *I* shall now roll on the floor laughing my ass off.

            Oh, and RSS? Chirping silence on *their* polar coverage. Suddenly they don’t count? Once again I find myself grinning at not only your ignorance, but your unwillingness to even admit it when directly confronted with it. You must be blissful. Just brimming with it.

          • http://GreenHeretic.com/ GreenHeretic

            Do you understand that the proportion of the area within the Arctic Circle that the UAH polar orbiting satellites do not cover is 22% (edit: corrected from 15%) of the total Arctic area? I would call 78% coverage as complete.

            Again, tell us how those five degrees of latitude from 85-90 have been covered over the past several decades on the surface. Hint: they haven’t. There are no statements we can make about that region that have any empirical validity.

            As for RSS, I haven’t looked at that dataset much and have never cited it.

          • Kevin O’Neill

            Keep digging that hole deeper. All you do is show your unfamiliarity with the actual measurement process and the data it generates.

            The TLT computation begins with the 11 scan positions which the MSU produces for each swath across the ground track below. There are 11 positions, labeled 1 thru 11, with #6 being straight down (nadir). There are also 2 more positions at the ends of each swath, one viewing deep space and the other viewing a heated target which is monitored for temperature with two accurate resistance thermometers. The TLT algorithm actually includes only 4 of the 11 positions, throwing out 5, 6, and 7 and using 1, 2, 10 and 11 as a correction for the data from 3, 4, 8 and 9. Thus, the resulting TLT data can not be said to “ provide “complete global coverage”. Also, the data can only be provided between 82.5N and 82.5S, due to the inclination of the orbit. Spencer and Christy calculate a gridded data product including higher latitudes, which they calculate by interpolation, artificially extending beyond the range of available data.”

            Quoted from a letter by Richard Eric Swanson, AAAS, AGU (retired satellite design engineer) and author of

            Swanson, R. E., Evidence of possible sea-ice influence on Microwave Sounding Unit tropospheric temperature trends in polar regions, Geophysical Research Let., doi:10.1029/2003GL017938, (2003)

      • http://GreenHeretic.com/ GreenHeretic

        In response to O’Neill’s point, “Temperature cannot of it’s own (over the time frames we’re discussing) follow a random walk – something has to *move* it.”

        Who claimed that it followed a random walk? Not me.

        As for, “Nor can it increase over time without some reason behind the increase.”

        Did you pass introductory statistics? This is exactly why we test for statistical significance. Had the test showed significance, then you have a point. However, the test fails to show significance. Not even remotely close to any standard used in any field of inquiry. In that instance, your point is foolish ignorance.

        And, “Don’t quit your day job.”

        I work as a professional analyst in the energy sector. That includes extensive work modeling weather for nearly two decades.