I can't tell you how many times I've used that line in interviews recently.
So it was refreshing to see someone else - Steven Pearlstein - use it today in the Washington Post. (* Actually, either he or the copy desk butchered the quote, leaving out the "not." Surely they meant well, but the quote and the point makes no sense without it, and indeed, is NOT what the standard line is. I've added it in the following excerpt with a * and hope the Post corrects this soon.)
"I should acknowledge that I have no idea who should and should not get routine mammograms. But I know enough about statistics to say that the issue is not settled just because you know of someone in her 40s whose breast cancer was detected by a mammogram and cured. As economists and medical researchers are fond of saying, the plural of anecdote is *(not) data. ...
As is often the case in such matters, those raising the most fuss were those with greatest financial interest in mammography (the radiologists and the makers of mammography machines) and the disease groups (in this case, the American Cancer Society), which tend to resist recognizing limits on how much time, money and attention is devoted to their cause.
"How many mothers, sisters, aunts, grandmothers, daughters and friends are we willing to lose to breast cancer while the debate goes on about the limitations of mammography?" Otis Brawley, chief medical officer of the American Cancer Society, asked in an op-ed article in Thursday's Washington Post. Dr. Brawley cleverly didn't answer his own question, but the clear implication of his question was that the only acceptable number should be zero. And it is that very attitude, applied across the board to every patient and every disease, which goes a long way in explaining why ours is the most expensive, and one of the least effective, health-care systems in the industrialized world."