From the “correlation is not causation” department.
Guest Posting by Ira Glickstein
Since the Death Penalty was restored in the US in 1975, the Number of Executions per Year correlates with UAH Global Temperature Anomaly better than CO2 levels! So, if we want to reduce warming, cut the rate of capital crimes! (See graphic below.)
In the above graphic, the black line indicates US Executions per Year from 1975 to 2013 (Source: http://www.statisticbrain.com/death-penalty-statistics/ NAACP LDF “Death Row, U.S.A., Gallup Poll, Bureau of Justice Statistics”), the blue jagged line indicates monthly UAH Satellite-Based Temperature of the Global Lower Atmosphere from 1979 through 2013 and the red line shows the running centered 13-month average (Source: http://www.drroyspencer.com/2014/02/uah-global-temperature-update-for-january-2014-0-29-deg-c/).
In an earlier WUWT posting I showed that Total US Debt (public and private) as a percentage of US Gross Domestic Product (GDP) correlates with NASA GISS US Annual Mean Temperature Anomaly better than CO2 levels! So, if we want to reduce warming, cut the debt! (See http://wattsupwiththat.com/2011/02/16/forget-co2-us-debt-causes-warming/)
Therefore, based on the (faulty) idea that Correlation Implies Causation, we can solve Global Warming by reducing US debt and US capital crimes :^)
Discover more from Watts Up With That?
Subscribe to get the latest posts sent to your email.
Talk about gallows humor
There might actually be a scientific basis for this correlation – perhaps criminals are more likely to stay indoors and watch TV if the weather is bad. All that lurking in dark shadows etc. must be a real drag if it is rainy and cold 🙂
So that’s why some alarmists want the death penalty for skeptics who won’t accept their science. They want the executions to cause an uptake in global temperatures and put an end to the annoying 17-year pause.
Harry Reid says the Koch brothers are the cause of global warming. So here’s a dilemma: would global temperatures go up or down if the Koch brothers were executed? /sarc
There’s too much lag between capital crimes and executions for the long term chart to have any relevance, but there appears to be seasonal and daily correlation between crime and temperature: http://www.boston.com/community/blogs/crime_punishment/2010/07/heat_wave_has_chilling_effect.html
–AGF
In fact correlation always indicates causation, but most don’t understand the concept. When one attempts to measure or quantify correlation one arrives at some fraction of one, where one is correlation and the fraction is some fraction of correlation: by such a definition correlation is absolute. Significant correlation of the sort that animals and babies learn from is typically better than 99% when a function is measured against time–more like 99.99%–as when we associate a sound with an event which is determined to have produced the sound. The science of statistics attempts to distinguish between correlation and non-correlation.
E.g.: viceroy butterflies mimic foul tasting monarchs. Their numbers are kept much lower than monarch populations by the minority of birds which eat a viceroy before they taste a monarch. That is, some of these birds learn the difference between the two, and the higher the bird population that can make the distinction, the lower the viceroy population. We might say the birds carry out statistical studies of butterfly patterns when fine tuning the correlation. It would be interesting to learn of any studies in animal intelligence that did not involve correlation. –AGF
agfosterjr says: May 9, 2014 at 8:39 pm
There’s too much lag between capital crimes and executions for the long term chart to have any relevance, …
Ice core records show an 800 to 1000 year lag between temperature and CO2 rise, so it’s too early to tell. More funding is needed.
“Therefore, based on the (faulty) idea that Correlation Implies Causation, we can solve Global Warming by reducing US debt and US capital crimes ”
No you have got it wrong, we can reduce US debt and US capital crimes by lowering CO2!
We must bring this to the UN and IPCC’s attention!
In the mean time Agenda 21 marches on. CO2 is only a flimsey excuse anyway.
Read my blog on what is happening to my city and every other city, except ours has been accelerated by our devastating earth quakes.
Roger
http://www.thedemiseofchristchurch.com
agfosterjr says May 9, 2014 at 8:59 pm
=============================================================================
Even the type of correlation you are talking about doesn’t suggest causation. The sound of a bowl breaking may correlate very well with seeing a bowl hit the floor, however we only can say with reasonable certainty that the bowl hitting the floor caused the sound, because we know that the sound happened after the bowl hit the ground, but this is not very obvious in normal situations. So, if we did not know better we might think that the sound caused the bowl to break. The only way we can determine which event cause the other is to know which occurred first. Even 100% correlation does not tell us what event is the cause and what event is the effect.
Executions are scheduled when they are for many political and budgetary reasons and purposes, and are complex therefore. The frequency of capital crime, conviction rates, and the mean incarceration time preceding executions is a function of poverty, opportunity, and annually-variable state budget allocations for expansion of prisons, as well as the responsive utility by states of a propaganda campaign by publicizing ultima ratio deterrent. Political reasons abound too – elections can ride on whether mercy is “popular,” or, alternately, if “law and order” are the will of the majority voting demographic.
More capital crimes occur, with consideration to criminal opportunity and impulse and the incipience of moral and wealth-predicted factors increasing the probability for criminal extremes, when climate-linked markets affect prices and employment levels, but winter “cabin fever” criminality, against family, winter “desperation” crime, linked to unemployment, and summer crime, where opportunity for travel and conditions conducive to homelessness are anti-phasic, inversely-correlated in Schwabe-phase-bound extreme years, while often concomitant sub-annually during climatically-transitional threshold years that are almost always economic restructuring periods, where innovation leads to the marginalization of a “choice” demographic.
Continuing trends toward measured global warmth interspersed with unpredictable oscillations – with predicably cyclical lagged response to precipitation-linked surpluses, indicates greater absolute, but more concentrated and inaccessible budgets with rising population and reduced life expectancy, but a greater need for deterrents if this warming leads to wealth disparity, drought-induced famine leading to increased global CPI with decreased labor value in a context of decreased labor market competition. Warfare increases with imbalance of resource distribution intra- and internationally, as budgets for warfare increase, while impetus for impoverished belligerents to incite violence increases as a response to inauspicious climate and subsequent pauperization.
Tom Trevor says:
May 9, 2014 at 9:22 pm
“Even the type of correlation you are talking about doesn’t suggest causation.”
And:: “Even 100% correlation does not tell us what event is the cause and what event is the effect.”
=================================================================
What you mean to say with these contradictory statements is that while correlation doesn’t distinguish between cause and effect it certainly does indicate cause and effect. –AGF
Watch out for trains.
D’oh! Try this:
agfosterjr says:
“In fact correlation always indicates causation, but most don’t understand the concept.”
Surely a lack of correlation can be used to indicate lack of causation but the presence of correlation can only be used to suggest possible causation.
Cheers
Mark
[Mark: Thanks! I agree, and, considering the IPCC claim that CO2 is the MAJOR cause of Global Warming, I would extend your statement to say lack of STRONG correlation can be used to indicate lack of MAJOR causation. In other words, rising CO2 levels most likely have caused some percentage of the warming of the past century, but the lack of warming for some 17 years in the face of continuing rapid rise in CO2 levels, indicates that CO2 is only a minor cause of warming. I would guess natural processes and cycles are responsible for perhaps 80% of the warming, with CO2 and other human-causation responsible for the remaining 20%. Ira]
scarletmacaw says:
May 9, 2014 at 10:07 pm
================================
Goes to show, 95% correlation doesn’t amount to much. –AGF
Mark Fawcett says:
May 9, 2014 at 10:14 pm
Surely a lack of correlation can be used to indicate lack of causation but the presence of correlation can only be used to suggest possible causation.
================================================================
Unless you quantify this absolute with some fraction you make no sense. Does not “100% correlation” indicate causation? Of course it does. And the phrase “100% correlation” takes for granted that “correlation” =1, i.e., is absolute. And how could you define “a lack of correlation” other than “correlation not equal to unity,” which amounts to saying “correlation not equal to correlation”? In other words, the word correlation is popularly used in the sense of “fraction of correlation” or “measure of correlation,” where the word “correlation” must ultimately and correctly retain its absolute character. –AGF
[AGF: I have two digital clocks, A and B, and they are correlated 100% to an infinitesimal fraction of a second. Does that mean that A CAUSES B (or B CAUSES A)? Nope! Both are tuned to the National Bureau of Standards time signal, C. So C CAUSES A, and C CAUSES B. But A and B have no causal relationship with each other. I could destroy A and it would have no effect on B, and vice-versa. Ira]
From agfosterjr on May 9, 2014 at 8:59 pm:
I take a piss at least once before midnight, the Sun rises in the morning. This has occurred 100% of the time, the correlation is perfect.
Now I just have to deduce the process of causation!
agfosterjr says:
“Unless you quantify this absolute with some fraction you make no sense. Does not “100% correlation” indicate causation? Of course it does. ”
No it doesn’t.
Another example (I do like kadaka’s) – there is a 100% correlation between people who have eaten food and who have died.
Cheers
Mark
Mark Fawcett says:
May 9, 2014 at 10:51 pm
===========================================================
That’s pretty silly. I have eaten food and I’m still alive. “All eaters will die” is better, but the correlation is obvious: all animals eat; all animals die. You simply cannot find a case of correlation (correctly absolute) without causation. –AGF
“That’s pretty silly. I have eaten food and I’m still alive. “All eaters will die” is better, but the correlation is obvious: all animals eat; all animals die. You simply cannot find a case of correlation (correctly absolute) without causation. ”
Whether it’s silly or not is irrelevant. You say yourself “the correlation is obvious: all animals eat; all animals die” – I agree, and it’s a 100% correlation; however, you cannot then conclude that eating is fatal and so you cannot say that eating is the _cause_ of death.
Cheers
Mark
kadaka (KD Knoebel) says:
May 9, 2014 at 10:32 pm
“I take a piss at least once before midnight,…”
==============
There is a high road, and there is a low road, and there is a place for each.
Mark Fawcett says:
May 9, 2014 at 11:04 pm
===============================
I could have said the correlation/causation is obvious. And it is. I never said eating is the cause of death. Rather be-cause you are human, whether you eat or not, you will die. That is the correct cause and effect indicated by the correlation. And just be-cause we may not be able to immediately determine the cause and effect indicated by some correlation doesn’t mean there is none. Darwin and Wegener can tell you all about that. –AGF
agfosterjr:
At several places in this thread (e.g. here) you have asserted
OK, if you think that then I point out
(a) All purchased bridges were sold by their owners
And
(b) I offer a bridge for you to buy.
The fallacy of your claim is demonstrated by both of the examples in the above article by Ira Glickstein.
There are two issues of relevance (i.e. correlation and coherence) because they can each and both provide information pertaining to causality.
Correlation is a mathematical relationship between two parameters. If the correlation is known over the length of the data sets, then their correlation indicates the magnitude of a change in one parameter that is expected when the other parameter changes by a known magnitude.
Correlation does NOT indicate a causal relation between two parameters.
But
Absence of correlation indicates absence of a direct a causal relation between two parameters.
Coherence of two parameters indicates that when one parameter changes then the other parameter changes later.
Coherence can disprove that change of one parameter causes change in the other; i.e. if change in parameter A follows change in parameter B then the change of A cannot be the cause of the change of B (because a cause cannot occur after its effect).
So,
1.
absence of correlation indicates absence of a direct causal relationship
and
2.
when there is a direct causal relationship then coherence indicates which of the two parameters is causal.
Furthermore, coherence in the absence of correlation is strongly suggestive that both parameters are affected by another parameter (or other parameters).
For example, leaves fall off trees soon after children return to school following their summer break.
The coherence is great; i.e. both effects occur each year.
But the effects do not correlate; i.e. the number of returning children is not indicative of the number of falling leaves.
In this example, the time of year is the additional parameter which causes children to return to school and the leaves to fall off trees.
So, if it is known that there is a causal relationship between two parameters. The coherence between the parameters indicates which is causal.
Richard
From u.k.(us) on May 9, 2014 at 11:07 pm:
This place is Friday Funny. I’ll get to Scotland before you do.
“I could have said the correlation/causation is obvious. And it is. I never said eating is the cause of death.”
Indeed, but the position that if A and B are 100% correlated there must exist a causal relationship between them is demonstrably false because the logical conclusion from that position coupled with the example of food/death is that eating kills you, or that a pre midnight wazz causes the sun to rise.
However, as with all correlations if you take the position that a correlation (of any fraction up-to and including 1) has three possible explanations (it’s coincidence, it’s a causal relationship or it’s a unknown common cause) then the example arguably falls into the 1st category.
I always work on the understanding that when we say there is a causal relationship between A and B that means a _direct_ relationship; i.e. Change A and B will change (assuming that’s the direction of cause and effect). A system where there is an underlying common cause C means that A and B are not causally linked, they are merely separate indicators of C.
This may all come across as a tad pedantic / semantic but it’s crucial when studying / identifying correlations is the cornerstone or foundation of new research, as is often the case. If you take the position that 100% correlation must mean a causal link between two variables, when you don’t have wider / prior knowledge of the system then you are doomed to risk repeating the many similar mistakes of the past.
However, high degrees of correlation can be used as indicators for further investigation but the fact still remains that any amount of correlation may be coincidence (nature is a bugger sometimes), indicative of a causal link or, quite commonly but not exclusively, a pointer to underlying common causes.
Cheers
Mark
richardscourtney says:
May 9, 2014 at 11:37 pm
agfosterjr:
“At several places in this thread (e.g. here) you have asserted
In fact correlation always indicates causation, but most don’t understand the concept.”
===============================================================
Wrong. I have only made the assertion once. All other instances have been others’ quotation of the same. But the assertion stands.
“Correlation is a mathematical relationship between two parameters. If the correlation is known over the length of the data sets, then their correlation indicates the magnitude of a change in one parameter that is expected when the other parameter changes by a known magnitude.”
========================
This idiosyncratic definition deprives us of any word for the traditional definition.
“Correlation does NOT indicate a causal relation between two parameters.”
========================
You’re claiming that a function is not a cause. That’s absurd.
“But the effects do not correlate; i.e. the number of returning children is not indicative of the number of falling leaves.”
========================
Here you’re introducing and mixing parameters. Inexcusable. E.g., it’s night time in my zone and it’s time to sleep. But the time zone is not indicative of the number of hours I intend to sleep.
====================================================================
Mark Fawcett says:
May 10, 2014 at 12:03 am
“I could have said the correlation/causation is obvious. And it is. I never said eating is the cause of death.”
Indeed, but the position that if A and B are 100% correlated there must exist a causal relationship between them is demonstrably false because the logical conclusion from that position coupled with the example of food/death is that eating kills you, or that a pre midnight wazz causes the sun to rise.
===================================================================
The ability to come up with ridiculous causes in no way undermines the claim that correlation equates to causality. Try instead to come up with [perfect] correlation which does not demand causality. Your attempts so far have failed. Too much fuzzy thinking around here, and I’m gonna call it a night before mine gets fuzzy too.
–AGF