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.
LLoyd Martin Hendaye’s comment on the moving average creating a large misleading lag is another aspect of note, well said.
The turning point for global climate was the 1990s.*
As precursor conditions for another El Nino as strong as the 1998 one do not seem to exist now or in the near future, the trend of cooling (relative to its high) after it continues. Incidentally, although generally speaking in terms of a global mean, it is of some interest that the U.S. (with some of the relatively more closely monitored temperature stations) has been cooling since then at what, in averages, is so far like a 0.4 degrees Fahrenheit per decade rate as illustrated at http://nextgrandminimum.wordpress.com/2014/01/25/continued-cold-puts-food-supply-at-risk/ .
* (as in my prior comment’s image, http://img220.imagevenue.com/img.php?image=97977_expanded_overview3_122_713lo.jpg )
If security technical analysis worked then every financial analyst would be daft not to use it, even if just to get a 1 or 2% extra return, as tools like moving averages are dead easy to calculate and widely available. Thus if technical analysis worked then it wouldn’t work, because that information would already be reflected in the share price.
Technical and statistical analysis in stock trade is like astrology – no predictive power beyond self-prophecy. In climate science is even less useful. You’re more likely seeing the turn of the AMO, which we can by other means predict happening in this decade, roughly.
rabbit says:
January 30, 2014 at 8:55 am
true that rabbit.
Gail Combs says:
January 30, 2014 at 8:29 am
“Math is hard”
David Dohbro’s article linked in my last comment shows a “sell” point in 2007.
This also seems to be the time at which Arctic sea ice switched from accelerating to decelerating melting.
http://climategrog.wordpress.com/2013/09/16/on-identifying-inter-decadal-variation-in-nh-sea-ice/
There appears to be a “pause” of similar magnitude and extent around 1992, which would have been a poor time to “sell.”
I find it more interesting that there is emerging confirmation (discussed in yesterday’s WUWT) that much of this graph is just a human construction.
According to these types of analysis I should have never bought bit coin @ur momisugly $2, $10, $70
If we have a direct link to something such as perhaps sun activity alone for temperatures then the down trend might be coming, but just as the warmists use ONE single variable to drive their predictions (atmospheric CO2). Climate is changing … constantly … and humans are just beginning to discover some of possible variables. And we do not yet have the equations nor the computing power to model them yet. We are still in the learning phase. AGAIN a shift of barely 1°C (-0.5° to 0.5°) over 174 years, on data based on significantly large chunks of earth surface, FABRICATED for a regional average, with probably 5 or more changes in collection technology, averaged to global scale, on a planet that has normal fluctuations of well over 110°C (-65° to +45°) means what? There’s no way the data sets margin of error is within this range. Equipment, user, technology, location. (yes I have read the HADCRUT error documents) Taken in light of historical planet temperature eras such as ice ages, and heat ages. HADCRUT does nothing but prove the 174 years have been relatively stable in the big picture of this variable planet. Come on, a 1°C variable in a +110°C range over a 510,100,000 km² area, over 174 years. Talk about an insignificant figure. It absolutely floors me how stupid this number is.
from HADCRUT4: It should be noted that the HadCRUT4 uncertainty model only takes in to account uncertainties identified in the construction of HadCRUT4, and other as yet unidentified sources of uncertainty may exist. This model cannot take into account structural uncertainties arising from data set construction methodologies. It is clear that a full description of uncertainties in near-surface temperatures, including those uncertainties arising from differing methodologies, requires that independent studies of near-surface temperatures should be maintained. We recommend that, in addition to the use of HadCRUT4, data set users consider testing the robustness of their results by comparison to other available data sets.
So maybe I will hedge with more coal futures then.
Another Data Set is 34 years of Satellite data that has noise within the equipments margin of error for 34 years running (ZERO IDENTIFIABLE INCREASE!)
Let’s not get overly critical of an attempt to bring more light to a dim subject. Climate is a complex system, with x equations and x+p variables, by definition a chaotic and insoluble problem. On top of that, there are, apparently, lag times with chaotic unknowable intervals depending on which of many buffer systems are operative. That does not mean we have to give up trying new solutions. Even if the light we may bring is not within our perceptive wavelengths, given the current state of our eyes.
You do voodoo.
@Old’un says:
Kim at 8.24am
>>‘so, will the next big El Nino be a dead cat bounce?’
>Definitely!
It is dead and bouncing because it froze to death.
Well, Antarctic sea ice is getting ready for a new record high minimum later next month.
This suggests that, to prop up the “market”, government-funded temperature gauges be put up closer to artificial heat sources than before …
I think we’ve all seen this pattern. Even has a name, it’s called some sort of decadal oscillation, PDO, I believe. There are high and low points starting with a high in 1878, and 33 years later a low in 1911 and 33 years after that a high in 1944 and a low 33 years after that in 1977 and a high 33 years after that in 2010 and so, it’s easy to predict a drop in the next 29 years. Well is that really going to happen? Very interesting that 33 year breaking point. OK I fudged a little to make ’em all 33 years, but it’s real close.
I’m not sure, but, I think Mr. Worrall was “taking the piss”.
Great comments everyone, in either case.
I think earth-caused solar eclipses are quite common, as well. Here on earth, we just call that “night”.
it is too early to tell for sure,
Yes it is.
True, true. The short-term cycle (period 60, 66, 68, or 70 years => take your pick or give a best estimate) is most likely peaking out 1996-2015 ….
Above, one writer used Temp ~ A + B * ( sin C (time))
Rather, we seem to be either in a long-term 1000-800 year cycle PLUS a short term cycle of 60-70 years.
But is the long-term cycle as we rise from the Little Ice Age peaking now (2000-2010)? Or will it actually peak as the Modern Warming Period in 2060-2070 AFTER the little drop “everybody” expects in 2025-2035?
Or ….
Instead of a two-period temperature cycle – one of 0.1 degree short-cycle on top of a 0.8 degree long cycle, do we have a sum of three of four different periods of 0.1 to 0.15 each?
Assume a 68 year PDO cycle of 0.15 degrees. 3x 68 =
Assume a different cycle of 0.15 at 60 years.
Assume a third at 0.15 degrees of 200 years.
In 1000 years, you have 5x 200-year beats plus
At 1020 years you have 15x 68-year cycles plus
At 1020 you ALSO have 17x 60-year cycles.
Sure, it’s curve fitting. But if the curve fits, you may be convinced!
Can’t be any sillier than the other things they do with graphs and numbers in Climate Science — just about as meaningful too.
Note to Eric Worrall ==> Careful not to bite down with tongue in cheek.
OT a bit, but I believe it is relevant.
The AGW social movement’s credibility in the public square is not completely different from that of a stock investment. Stocks rise based on perceptions of value, both now and in the future. Much of the news is based on things that have happened in the past, but much of the value is based on bets about how the stock will perform in the future. In other words, there is a valuation model that is employed by decision makers. AGW is similar to this. In the heady days of Sen. Wirth’s stage mananged roll out of AGW, it was the early adopters who paid serious attention. They profited the most, in terms of social capital. Now AGW is a huge industry, funded by tax payers and insurance premiums. But what does AGW have to show for the many billions given over to its promoters? Not much. Think of a highly touted stock coming out of no where, with a really hot compelling story. Eventually the investment community wants to see results or the price will fall.
hunter says: @ur momisugly January 30, 2014 at 11:58 am
what does AGW have to show for the many billions given over to its promoters?
>>>>>>>>>>>>>
A bunch of very healthy bank accounts (in the Caymans) belonging the political hanger-ons who took the money and ran. Al Gore leading the pack.
The Climate SELL moment is when Warren Buffet dumps the solar companies he bought in Antelope Valley CA.
If it happens just before 2016 you know which way the
riggedelections are going to go.To Gail,
So we should be charting solar company stocks to predict how the 2016 elections will go? They will fall this year if congressional elections don’t favor the administration and the new congress defunds solar subsidies.
Takes climate astrology to a new level.