3 thoughts on “Daniel on Stan at the NYC Machine Learning Meetup

    • Bob:

      Just read that, I guess better than most but it is almost impossible to know whether to believe a health study if you don’t have access to study records and data or at least a knowledge of the group that were involved – its (currently) all done behind closed doors.

      One of the comments suggested Cochrane and here is my favorite paper from (one of) them (confirming the above concern)

      Key paper:
      Tom Jefferson, et al (of The Cochrane Collaboration). Risk of bias in industry-funded oseltamivir trials: comparison of core reports versus full clinical study reports http://bmjopen.bmj.com/content/4/9/e005253.full

      The conclusion:
      “This approach is not possible when assessing trials reported in journal publications, in which articles necessarily reflect post hoc reporting with a far more sparse level of detail. We suggest that when bias is so limiting as to make meta-analysis results unreliable, either it should not be carried out or a prominent explanation of its clear limitations should be included alongside the meta-analysis.”

  1. Naive question: Is Stan used actively in Machine Learning (motivated by the location of the talk)? Are there any examples or case studies? I’d love to read them.

Leave a Reply to Bob Cancel reply

Your email address will not be published. Required fields are marked *