What the Luck? by Gary Smith

What the Luck? by Gary Smith

Author:Gary Smith [SMITH, GARY]
Language: eng
Format: epub
Tags: SOC027000 MAT029000 PSY032000
ISBN: 9781468313918
Publisher: The Overlook Press
Published: 2016-09-05T23:00:00+00:00


Observational Data

In a 1973 letter to the prestigious New England Journal of Medicine, a doctor named Sanders Frank reported that 20 of his male patients had diagonal creases in their earlobes and also had many of the risk factors (such as high cholesterol levels, high blood pressure, and heavy cigarette usage) associated with heart disease. For instance, the average cholesterol level for his patients with noticeable earlobe creases was 257 (mg per 100 ml), compared to an average of 215 for healthy middle-aged men.

Before you rush to look in a mirror, one very big problem with this report is that these are observational data, not any sort of clinical trial. Anecdotes aren’t evidence and data is not the plural of anecdote.

Dr. Frank observed earlobe creases in 20 of his patients and also noticed that they have elevated risk factors. So? Most people don’t like going to the doctor unless they think they have a serious health problem. Dr. Frank specialized in respiratory medicine, and high cholesterol, blood pressure, and cigarette usage are all associated with respiratory problems. Perhaps these patients came to Dr. Frank because cholesterol, blood pressure, and cigarettes were affecting their breathing. Any trait they happen to share (balding, beady eyes, big thumbs) will seem to explain these elevated risk factors, even if they are completely unrelated.

Subsequent studies investigating the relationship between earlobe creases and heart disease have been inconclusive, perhaps because of the ambiguities in defining earlobe creases. The most reasonable explanation may be that as people age, they tend to develop earlobe creases and are also increasingly at risk for heart disease, but neither necessarily causes the other. Instead of poking around their ears, we can ask their age.

Over and over, statisticians say that correlation is not causation, yet many are unpersuaded. If we see a correlation, we assume there must be a reason. Maybe so, maybe not. If A is correlated with B, it may be that A is causing B, that B is causing A, or that something else is causing both A and B. Or maybe it is just a fluke, like the coincidental correlation between the number of people who drowned by falling into a swimming pool and the number of films Nicolas Cage appeared in. There is a web site “Spurious Correlations” that has this one and hundreds of other hilarious flukey correlations.

No one takes the correlations at this web site seriously (at least, I hope not), but other correlations are more subtle and do get taken seriously. Data from six large medical studies found that people with low cholesterol levels were more likely to die of colon cancer; however, a later study concluded that the low cholesterol levels may have been caused by colon cancer that was in its early stages and therefore had not yet been detected. It wasn’t that A caused B, it was that B caused A.

For centuries, residents of New Hebrides believed that body lice made a person healthy. This folk wisdom was based on the observation that healthy people often had lice and unhealthy people usually did not.



Download



Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.