Recently the Wall Street Journal has had several articles about estrogen's link to heart disease in women, highlighting a recent New England Journal of Medicine article showing that it lowers risk of arterial sclerosis. Then last week, the Journal did a story concentrating on how the Women's Health Initiative (WHI) misread the data by focusing on the increased heart attack risk for women over 70, While neglecting the lowered rate of heart attack for women under 60 (since the WHI's 2002 report arguing that estrogen therapy actually raised heart disease--opposite sign to previous findings--hormone sales plummeted 30%). The WHI shot back in a letter to the WSJ, arguing they stand by their interpretation of the data, which they think is somewhat mixed, and in their words, the differences in heart disease between the older and younger (one up, one down!) is not 'statistically significant'. If the difference isn't statistically significant, I can't see how the old cohort can be thought to have a higher than average risk (eg, if the sample estimate for the old is +14%, for the young, -30%, if the difference is noise, the +14% is certainly noise). As Paul Feyerabend argued, there are no definitive tests in science, as people just ignore evidence that goes against them, emphasizing the consistent results.
Estrogen therapy helps women with symptoms of menopause, including hot flashes, bone loss, but also depression, wrinkles, vaginal dryness, and lower sexual desire. Though not mentioned in the WSJ articles, I think it is the latter issues are what really bothers the WHI. Women's groups are fond of coming up with pretexts to desexualize women (eg, concern about silicon breast implants), because a sexual woman elevates the phallocracy, literally. Sure they are against female circumcision, but in general, women's representatives dislike the omnipresent feminine desire to appear attractive to men. I remember a sculpture of a 30-pound overweight naked woman at Northwestern that 'celebrated' the female physique (so much for a female David).
I think most big policy issues in science have a strong political subtext, and you don't have to dig very far to see a group use science to rationalize their 'bigger picture' concern. This is why credibility is so important to science, because you just can't trust a scientific paper, and it often takes too much time to read all the empirical literature in a debate.
Estrogen therapy helps women with symptoms of menopause, including hot flashes, bone loss, but also depression, wrinkles, vaginal dryness, and lower sexual desire. Though not mentioned in the WSJ articles, I think it is the latter issues are what really bothers the WHI. Women's groups are fond of coming up with pretexts to desexualize women (eg, concern about silicon breast implants), because a sexual woman elevates the phallocracy, literally. Sure they are against female circumcision, but in general, women's representatives dislike the omnipresent feminine desire to appear attractive to men. I remember a sculpture of a 30-pound overweight naked woman at Northwestern that 'celebrated' the female physique (so much for a female David).
I think most big policy issues in science have a strong political subtext, and you don't have to dig very far to see a group use science to rationalize their 'bigger picture' concern. This is why credibility is so important to science, because you just can't trust a scientific paper, and it often takes too much time to read all the empirical literature in a debate.
Eric Falkenstein - am 2007-07-24 02:07
ed (guest) meinte am 24. Jul, 08:04:
I haven't read the study, but think your assumptions about the statistics are too hasty.You say "if the sample estimate for the old is +14%, for the young, -30%, if the difference is noise, the +14% is certainly noise," but this is not necessarily true. For example, what if the standard error for the old is 5% and the standard error for the young is 40%? Then the difference between the groups is statistically insignificant, while the 14% is statistically significantly different from zero.
Such a situation may be more likely than you think. One obvious way to get this is if the sample contains a lot more old than young, which seems unlikely. But remember what we are trying to estimate is the *ratio* between the probabilities of heart disease in the treated and untreated groups, or Pt/Pu.
It seems likely that heart disease is much more prevalent in the older group than in the younger, for both treated and untreated. This means that the ratio estimator Pt/Pu will be estimated more precisely for the old than for the young, even if the sample sizes are the same. (This is so even though both Pt and Pu are estaimated more precisely in an absolute terms for the young, because the Pu in the denominator is closer to zero and so the ratio is more sensitive to errors in Pu.) Do the math and I think you'll agree that I am right.
Therefore the idea that the estimated ratios have the statistical properties claimed by the researchers is actually plausible.
Eric Falkenstein antwortete am 24. Jul, 16:08:
The study showed only the -30% number as statistically significant, so that implies the standard error won't save them. As the WHI says in face of the new data:"However, total deaths appeared to be reduced in the hormone group at age 50-59; we couldn't identify any specific reason for this reduction"
But of course, the thought they were wrong was ruled out by assumption.
Raymond Babbitt (guest) meinte am 25. Jul, 18:22:
Certainly ambient estrogen levles correlate highly with heart failure in men, yes?I kid.
