Tipsters:
To me, questions like belie an assumption that if somebody or some group is "on top" they must be reliably (aka significantly) on top. The real question is whether the highest occupation is on top as an outlier - or by virtue of the fact that _somebody_ must be on top. In the first case, this would mean there is something about the profession or the people in it that is different, and we can investigate what the cause is. In the second case the professions really do not differ meaningful - i.e. there is no effect of profession (just random variation around some central value). In which case the question loses its importance. I had minitab do a stem-n-leaf of the data Beth provided below, and you get (using just 2 digits):
1 | 1
1 | 2 3 3
1 | 4
1 | 6 7
1 | 8 9
2 |
2 | 2 2
2 | 4
By eyeball, it's not much of a normal distribution but on the other hand there are no outliers either. The cluster past 200 might be real, though it is difficult to discern what these groups have in common (food batchmakers? physicans, health aids). But we have to be cautious with data like this anyway. I would imagine that how the classification is done could have quite an effect on the shape of the distribution. If you gave me a large population and freedom in the categories I can create and use to classify people, I could come up with a variety of interesting shapes - capitalizing on chance.
Beth Benoit wrote:
Stephen Black addressed this issue recently on TIPS, so maybe an archive search will turn up the answer. In lieu of that, I believe he quoted the Cecil Adams, the genius of information in the inimitable Straight Dope, so I went back to the source. Here it is:From Cecil's Mailbag by the Straight Dope Science Advisory Board
------------------------------------------------------------------------
What occupation has the highest suicide rate?
------------------------------------------------------------------------
Dear Straight Dope:
Do you know which occupation has the highest suicide rate? Is it prison guards, by any chance? Or psychiatrists?
There is an urban legend, recently repeated on Seinfeld, that dentists have the highest suicide rate of any profession. This is false. I recently spoke with a public affairs representative at the American Dental Association. They actually did a study on the subject, and found the rate among dentists is about the same as the population as a whole.
Prison guards seem to be a likely candidate, since they exist in a rather depressing environment. So do psychiatrists, since as a group, they seem to border on insanity. So which is the correct choice? --Richard A. Koris, Washington, DC
SDSTAFF CKDextHavn replies:Well, it hasn't been easy to track this one, and I'm not sure I've got a definitive answer. Let's start by noting that suicide statistics are questionable at best. Many suicides are classified as "accident" to spare the family from publicity. So the statistics are only a rough indication.
I easily found statistics on the Internet about suicides by age, region, gender, and race, but very little about occupation. Actually, since suicide is the second leading cause of death in the U.S. among those age 15 to 24, probably the answer is "student", but I don' t think that's what you're looking for.
I called the library of the Society of Actuaries, thinking they'd know. The librarian said she used to work at a large psychiatric library, and that about 8 years ago, the answer was psychiatrists/psychologists/related. However, she couldnt quote me a source or cite a statistic, except what she says she knew.
A study of 24 states reported data on causes of death by occupation, for people ages 20 to 64, from 1984 to 1988, and came up with physicians, health aides, and "food batchmakers" as the three highest. Food batchmakers are at the top but only by a small (statistically insignificant) margin. Psychiatrists weren't reported separately from other physicians. I'm not sure exactly what the numbers below mean, perhaps suicides per million of active population:
Food batchmakers (241)
Physicians (222) and health aides (excluding nursing) (221)
Lathe and turning machine operators (199)
Biological, life and medical scientists (188)
Social scientists and urban planners (171)
Dentists (165)
Lawyers and Judges (140)
Guards/sales occupations were tied at 139
Tool and die makers (126)
Police, public servants (118)So, I'd say, it's still pretty ambiguous.
--SDSTAFF CKDextHavn Straight Dope Science Advisory Board
--
---------------------------------------------------------------
John W. Kulig
[EMAIL PROTECTED]
Department of Psychology
http://oz.plymouth.edu/~kulig
Plymouth State College
tel: (603) 535-2468
Plymouth NH USA 03264
fax: (603) 535-2412
---------------------------------------------------------------
"What a man often sees he does not wonder at, although he knows
not why it happens; if something occurs which he has not seen before,
he thinks it is a marvel" - Cicero.
