But things are different in Spain. At least, if one trusts results from a big model vs. simple results. http://www.sciencedirect.com/science/article/pii/S0301211507000255 …pic.twitter.com/YADGpxiyXP
Controlling for smoking status and gestational age is pretty dubious.
-
-
I understand controlling for smoking status. But gestational age is a stupid variable to control for.
-
Both are problematic as they are likely effects of group differences. Controlling for them controls for the cause.
-
I agree. But I can imagine why someone would think controlling for smoking is justifiable. Gestational age? I can't see any reason.
-
They think environmental effects (e.g. stress, pollution) cause preterm births, presumably.
-
Yes. Of course genes can cause enviro effects, so controlling for smoking is wrong. But you can't make that argument for gestational age.
-
You can. They think outside factors cause lower gestational age in LIMs, which cause earlier term birth, so we have to control for these.
-
But, to me, it is not at all obvious that gestational age is "environment" the way smoking is. It's much more of a stretch. (1/2)
-
Anyway, we agree. If nothing else, it's a good example of the partialling fallacy. (2/2)
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.