On the left, odds ratios and confidence intervals from a logistic model predicting autism in the children of mothers exposed to environmental hazards On the right, the headline based on the study This is a bit nutspic.twitter.com/SF93TYw6UU
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
Meh I don't think it really justifies more research per se. I demonstrated today that marriage was a significant risk factor for diabetes as opposed to divorce, separation, never marriage, or being widowed. Consistent negative effect until I controlled properly for confounding
You can't control properly for confounding: https://www.ncbi.nlm.nih.gov/pubmed/14499048/ … That study looks at interventions so that they can construct non-randomised studies from randomised data to nail the comparison, but the same problems apply to observational data.
That's not what that paper shows and is incorrect. You can indeed control properly for confounding, although it is obviously a complex issue
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.