Discussion about this post

User's avatar
Overcoming Bias Commenter's avatar

and therefore your comment is incorrect: "If docs are especially bad at treating cancer, then we would expect those who use docs more to do worse at cancer. And in fact women, the rich, and the well educated do worse at cancer". These groups have improved survival with regard to cancer mortality. Even if you meant to say that the cancer mortality RRR was higher relative to the other RRR's with regards to the above populations, it does not negate the fact that it is still a risk reduction. Therefore, if your willing to make the speculation that these statistics are explainable by physician use, then you have to conclude that physicians are effective at treating cancer, just not as effective as they are at treating heart disease. You have a very narrow interpretation of your very broad population statistics and fail to recognize the simplest of rules for interpreting statistics. Correlation is not causation. If you really want to study the efficacy of cancer treatment, you first need to study each cancer individually, and second, only an RCT will provide you with direct evidence.

Expand full comment
Overcoming Bias Commenter's avatar

I first glossed this as "Death causes correlations."

Expand full comment
6 more comments...

No posts