What a simple statistical investment tool can tell us about the climate
Guest essay by Eric Worrall
One of the simplest statistical tools used by investors is a moving average plot. If you plot the average share price of a company, or other investment product, with different smoothing periods, on the same graph, a crossover between the different plots can provide early warning of an imminent change in trend – a buy or sell signal.
From Wikipedia:-
“A moving average, as a line by itself, is often overlaid in price charts to indicate price trends. A crossover occurs when a faster moving average (i.e., a shorter period moving average) crosses a slower moving average (i.e. a longer period moving average). In other words, this is when the shorter period moving average line crosses a longer period moving average line. In stock investing, this meeting point is used either to enter (buy or sell) or exit (sell or buy) the market.”
http://en.wikipedia.org/wiki/Moving_average_crossover
The interesting thing about moving averages is they can provide useful, actionable information, without requiring any knowledge of the nature of the underlying commodity.
So what happens if we create a moving average plot of global temperature (in this case Hadcrut4)?
Source: http://www.woodfortrees.org/plot/hadcrut4gl/mean:60/plot/hadcrut4gl/mean:120/plot/hadcrut4gl/mean:240/plot/hadcrut4gl/mean:360
What is immediately apparent is we may be in the early stages of a significant inflection point – it is too early to tell for sure, but the beginning of an inflection which appears to centre on the early 2000s seems very similar to the inflection which occurred in the 1940s, heralding decades of cooling temperatures.
If the numbers I was plotting was the value of an investment, I would interpret the chart as a strong “sell” signal – a warning that a substantial drop could be imminent.
UPDATE: A previous post on WUWT by David Dohbro also comes to the same conclusion, and has a more detailed analysis:
http://wattsupwiththat.com/2013/10/01/if-climate-data-were-a-stock-now-would-be-the-time-to-sell/
Discover more from Watts Up With That?
Subscribe to get the latest posts sent to your email.
“What is immediately apparent is we may be in the early stages of a significant inflection point”
Yes, although this article and HADCRUT4 are not what would particularly show such in isolation, as opposed to in the context of http://img16.imagevenue.com/img.php?image=22187_expanded_overview3_122_176lo.jpg .
Well, one can cite many “buts” but I’ll just say, HadCRUT4… 4 iterations into La La land… not data.
Technical (chart) analysis in stocks is, more often than not, a bunch hooey. There are so many technical indicators, I could probably find any stock and find multiple buy or sell signals at any given time. But, it has some basis in fact in that chart patterns can sometimes be used to interpret the attitudes of a mass of investors towards a particular security and, therefore, predict with some accuracy which direction it will head in the short term.
Removing the human element from technical analysis removes any validity the technique may hold. I.e. there may be a little predictive value to technical analysis when millions of individual decisions are being made by humans, but I doubt there is any predictive value in a system like the climate.
So, this may be a fun thing to look at and write about, but I wouldn’t take it seriously.
The AMO will go negative in the next few years. And then 30 more years of cold.
That’s what climate science should be, ‘removing the human element’ from analysis.
IPCC rates AGW as AAA (triple A rated) déjà vu anyone?
Bloomberg reports that the EU maybe set to fiddle the Carbon trading market, to push up the value of credits. Against EU rules.
I’m in agreement with Matt on this one. Interesting mental masturbation, but not a predictor I’d hang my hat on. Besides, in stocks the act of buying or selling quite demonstrably has a direct effect on the stock value. There’s no such corollary in climate data.
Make energy unaffordable,,,knowing there’s a mini ice age coming…..brilliant, but nasty!
Apply your analysis to US postal stamp rates:
http://en.wikipedia.org/wiki/History_of_United_States_postage_rates
and by your argument you might predict an imminent sharp drop [in fact, overdue]
The striking thig for me is just how trivial the actual change in temperatures has been, and how much exagerration the AGW promoters rely on to make the trivial changes in the last 180 years look scary.
It looks a lot like the AMO long term plot. Meanwhile the shorter term AMO plot is in a definite turn down. Let the countdown begin on how long it takes for this to register with scientists, official agencies, and the longest lag users (policy leaders). Laying out the likely set of cognitive lags is as follows: 10 years for scientists, 20 years for official agencies, and 25 years for policy leaders and their advocacy communities. That still leaves a lot of time for science settled talk and policy misdirection plays.
Disbelieve all prognosticators, witchdoctor, prophets, weather or financial, without doxastic commitment. If they suffer no harm for error, then where is their downside for lying or errors?
You can clearly see a clear deterioration in relative strength. I expect a negative MACD crossover to occur any month now.
If I still had all my technical charting software (from a previous career), I’d plug in the data and see what we get. I’d think that global warming is overbought and we are due for a correction.
The only possible effifacy in financial “technical analysis” is that lots of other people are making the same interpretations of the doodles and will do the same thing at the same time (i.e. sell).
Unfortunately Mother natures doesn’t sit scouring the temperature series for a “double top”, “head and shoulders” or “cup and handle”.
The question is, are you a day trader or do you buy stocks based on fundamentals for long term investments? In climate science, there are fundamental processes that are causing those observable cycles. The IPPC models are designed to show that CO2 is causing the global average temperature to rise and that anthropogenic emissions are the cause of the rise in CO2 concentrations. The problem is that these “CO2 sensitivity” models do not correlate well with either the short term or long term cycles.There are natural fundamental processes driving those cycles. I think we would be better able to predict climate change by studying those fundamental processes that result in the observable short and long term cycles.
Matt nailed it IMHO. There’s no reason at all to think that this sort of analysis is valid for predicting temperatures. Also, even if it had some validity for temperatures, this prediction is based on a sample of just one prior similar pattern. One is too small a sample size.
While technical analysis can offer some insights in markets, mostly by indicating points at which a lot of investors are going to be entering or leaving depending on the subsequent price action, this looks to me like a poor application of a moving average.
For example, just look at the history of the graph shown in the article. The 60-month(?) line has crossed over the 120-month line many times in the past, and nothing could be determined as to the future direction of the longer term lines, or of the shorter-term ones, for that matter. Sometimes they continued up for years, and sometimes they turned lower. This is one moving average, among many, that has zero forecasting power, in my opinion.
We are heading into the downslope of the AMO. That is sufficient reason for temperatures to decline. Chicken bones and sheep entrails are not necessary.
And yes, I have worked as a professional investor in times past.
Lief
“Apply your analysis to US postal stamp rates”
Actually, if you look at the adjusted for inflation, we are sort of dropping right now.
Also, if I turn my head slightly to the side and squint, I think I can see a correlation between adjusted postal rates and sunspots. 🙂
N. N. Taleb, Literary and nontechnical books:
Fooled by Randomness: The Hidden Role of Chance in Life and in the Markets. New York: Random House and Penguin. 2001/2005. ISBN 0-8129-7521-9.
The Black Swan: The Impact of the Highly Improbable. New York: Random House and Penguin. 2007/2010. ISBN 978-1-4000-6351-2. The book was completed in 2010 with the second edition including a long essay “On Robustness and Fragility”.
The Bed of Procrustes: Philosophical and Practical Aphorisms. New York: Random House. 2010. ISBN 978-1-4000-6997-2.
Antifragile: Things That Gain from Disorder. New York: Random House. 2012. ISBN 978-1-4000-6782-4.
https://en.wikipedia.org/wiki/Nassim_Nicholas_Taleb#Finance_career
Tom says it well. The analogy of the herd mentality driving events is an important one. The most obvious example is the traded value of carbon credits.
I for one need to see a temperature plot based on the actual temps, not the down-rated ones in the 30’s and 40’s. What would the interpretation be if ‘the real’ temps were shown? Without fiddling the inflection point might be placed earlier.
My reply on the basic premise is yes, it looks like it is following a cycle and it has started down. My worry is that it should have gone up for 7 or 8 more years before the turndown. The implications are chilling.
The chart shows the 60 cycle of warming and cooling imposed on the warming since 1800. The 60 year cycle is the result of the interaction between the solar cycle and the oceans. Normally I would expect the slight down trend to last to 2030 HOWEVER the Sun is currently behaving much as it did in the Little Ice Age so there is the possibility of a large drop in global temperatures.
Although we have a 400 year record of the 60 year cycle it still came as a shock to the climate ‘experts’. It also shows that Man has little or no effect on the climate.
A significant fall in temperature will show that warming is not the worst thing to happen. We may get climate refugees, but from North America and Northern Europe. Just the kind of people trying to cool the world down!
Moving averages by definition are subject to a “half-span lag” effect, meaning (for example) that a three-unit average will lag one period, a five-unit average will lag two periods, and so on. As “measurements of central tendency” this is true of unweighted geometric and other means as well… the dilemma is, of course, that a long-term arithmetic/geometric mean will increase lag-time accordingly. Though “centered” moving averages correspond with actual inflection points, they do this not by eliminating but accommodating a series’ 1/2-span lag.
Point is, that Moving Averages as trading tools –nevermind math/statistical time-series in general– must always register “behind the curve.” On this basis, regardless of esoteric “technical analysis,” climatological inflection-points depicted in arrears are obsolete: If-and-when smoothed “cross-overs” appear, their cyclical/periodic turn has in fact ALREADY HAPPENED.
Averaging 17-year temperature trends not only lags activity by some eight years, but guarantees that current activity will differ in substance-and-detail. Just as investors cannot buy or sell at yesterday’s prices, or tomorrow’s, no-one is “expert on the future”: Reality deals in optimistic/pessimistic expectations only, and those are up for grabs.
Looks kinda like y=x+sin(x). Hmm?
John Maynard Keynes famously said:
‘the markets can stay irrational longer than you can stay solvent’.
Very much like climate and the Nations that are, sadly, pouring money into ‘CAGW mitigation’.