Hacker News new | past | comments | ask | show | jobs | submit login

Title is slightly misleading because the study didn't go on for 15 years, they used an existing database with 15 years of information.

I also hate the use of the word 'link' because it seems to imply causality in many people's minds. This is a correlational study - a finding either way is good for suggesting a hypothesis, but we cannot infer (in this case a lack of) cause and effect. There could easily be gigantic unknown confounding variables.

There could also be a very small minority of people very sensitive to radiation that can easily be brushed aside as outliers in these kinds of studies.

I am even more interested in any wifi studies now that I am constantly near wifi. But my guess is that wifi radiation is orders of magnitude less powerful than cellphone radiation so it won't be as great of a concern.




Lack of correlation isn't "proof" of lack of causation, but it's damned strong evidence. Yes, in theory a precisely calibrated confounding variable could be precisely canceling the real effect, but until you've got some sort of actual evidence of such a factor you're in blatent violation of Occam's Razor.

I'm really starting to loathe the thoughtless chants of "correlations doesn't imply causation"; it used to signal a deep understanding of science, now it tends to signal quite the opposite.


No, it is not strong evidence. It is only evidence of a correlation which is meaningless.

You shouldn't loath those thoughtless chants, you should embrace them. The first thing someone should say when presented with "linkage" is think, that is meaningless on its own.

The real problem is that there are so many scientists (people with the ability to conduct statistical analysis) and so much data, that every possible correlation is being discovered. Even correlations that have nothing to do with anything.

The best examples come from Finance, where the data has been more attainable, and where the rewards for finding real causality have been available longer and allowed for advanced computations on super computers before we all had excel (or put more useful statistical tool here).

One of the go to papers on Motley Fool's completely loosing stock selection strategy is here:

http://papers.ssrn.com/sol3/papers.cfm?abstract_id=158409

There are lots of papers and examples in finance where people tried to find causality, but really only found correlation. Doing so is the best way to loose a ton of money.

It is also the best way to get people to do stuff you do/don't want them to do and it is the best way to stop progress.

So, don't make assumptions about causality, you should provide real evidence of causality beyond correlation if you write the word linkage.


Lack of correlation, wtvanfest. Important word! Lack of correlation is evidence of lack of causation. It isn't absolute proof but it is good evidence. After all, "lack of correlation is evidence of lack of causation" is the contrapositive(ish) of "Causation is evidence of correlation". If that's not true then all hope is lost of ever learning anything.

Sorry, but that's exactly the sort of thoughtless repetition I'm talking about. You're in such a hurry to chant the mantra and wave your scienciness around you didn't even take the time to notice it was the precise opposite of the conversation at hand. Which is precisely what my complaint was in the first place.


Here is an article explaining why lack of correlation does not imply lack of causation: http://blog.cholesterol-and-health.com/2011/01/lack-of-corre...

Ignorance is excusable, but the insulting tone you take on is not. Please stop ruining Hacker News.


Correlation does not imply causation, but lack of correlation certainly does imply lack of causation.


Not always. For instance, the temperature in my fridge is a pleasant four degrees celsius constantly, but the compressor keeps on switching on and off.

In the absence of a feedback loop, though... yes.


Eh, that's just a lack of detail. With a sufficiently precise thermometer, you'd see the temperature rising when the compressor is off, and falling when it's on.


Yes, but in real life our data usually isn't infinitely accurate.


Right, but that just means that you're only able to disprove correlation to within a certain accuracy. Correlation below the detection threshold could still exist, and could still be due to causation. Correlation above the detection threshold does not exist, and rules out causation above the detection threshold.


This link helps explain why lack of correlation does not imply lack of causation: http://blog.cholesterol-and-health.com/2011/01/lack-of-corre...


That explains why lack of detection of correlation does not imply lack of causation. But all of the possible failures that it outlines are failures in detection, not an actual lack of correlation. It's a subtle distinction, but I think it's an important one.


That is a good point - the most accurate statement would be: lack of correlation cannot imply there is no relation.

I think we risk oversimplification by referring to it solely as a failure of detection. The first 3 points of the article mean we could probably adjust the experiment right now (or should have before the experiment began). The 4th point, while technically a failure of detection, could be due to unknown confounders (or as Rumsfeld would say - unknown unknowns). So it could be a failure in detection or a failure in knowledge.


My terminology may not be the best. But to put it simply, if you do an experiment and that experiment says that there is no correlation, then to within the limits of your knowledge that there is no correlation, you can also say that there is no causation. Whether those limits are based on your experimental design, external factors, or what have you, is a separate (but completely interesting) question.


I think the key to terminology here is to make the statement in a negative fashion: knowledge is always limited so we can never be certain there is no relation.

It is interesting in this case to try to make the claim that because there is no correlation of cancer to proximity of cell phone use that cell phones probably don't cause cancer in nearby locations in the body. I think we have enough knowledge to make that case, but I might just be arrogant.


> There could also be a very small minority of people very sensitive to radiation that can easily be brushed aside as outliers in these kinds of studies.

There could be pixies inhabiting the space between Earth and Mars whose existence can easily be brushed aside as noise in all of the sensors of all of the telescopes we have pointed in that direction.

Russell's Teapot is usually used when debating with religious people but it is equally valid whenever someone keeps proposing a theory based on no stronger evidence than "Well, we haven't looked everywhere, now have we?"

http://en.wikipedia.org/wiki/Russell%27s_teapot




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: