Tuesday, July 17, 2012

I'm 95% Confident This is a Good Definition of a P Value

by Chris Masterjohn

New post over at Mother Nature Obeyed:


In this post, I explain why I consider it legitimate to read "confidence" that something is not due to chance into a P value. I discuss the differences between Bayesian and frequentist approaches, the agreement between P values derived from a significance test of the null hypothesis and those derived from the construction of a 95% confidence interval, and I use examples that include funny-looking red imps that like to steal things and lie about it.

Enjoy!

Read more about the author, Chris Masterjohn, PhD, here.

5 comments:

  1. I posted my comment on the original blog, hoping it makes some sense. But...

    Regards.

    ReplyDelete
  2. Hey, just got to say that I really enjoy your blog. I recently read about the results of a recent study on HDL cholesterol, and they are quite intriguing. Apparently, recent findings have shown that higher levels of HDL don't actually lower your overall risk of heart attack. Now doctors have to rethink many of the positions they have taken over the last 30 years. Have you been looking into this? What do you think?

    ReplyDelete
  3. The links don't seem to work

    ReplyDelete
    Replies
    1. Hi Anonymous,

      Unfortunately the WAPF site has been getting attacked and is transferring to a new server, so many of the links are temporarily down while the site is being constructed.

      Chris

      Delete
    2. The links should work now. If they don't, try clearing the cache in your browser.

      Chris

      Delete

To create a better user experience for everyone, comments are now moderated. Please allow up to one business day for your comment to post. In order to avoid the appearance of spam, please avoid posting links, especially to commercial destinations, and using all-caps.