[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums

Calculating confidence values

Posted By: Maik Stiebler
Date: Tuesday, 1 September 2009, at 11:48 a.m.

In Response To: Calculating confidence values (Timothy Chow)

If you start collecting data and then halfway through get an idea about what to do next which you hadn't planned at first, then all your statistical significance figures will be suspect.

That's true. However, once you have taken the Bayesian route, statistical significance is not a very important concept anymore. It should be acceptable practice in Bayesian inference to do a set of rollout trials, update your prior, and, depending on whether you are happy with your new state of information as represented by the posterior, add some more trials or not. It does kill significance in the frequentist sense, but if you do more trials, the new posterior you get after updating with the second set of trials should still be the best representation of all the information you have.

That said, there are certainly pitfalls in the Bayesian approach as well.

Messages In This Thread

 

Post Response
Your Name:
Your E-Mail Address:
Subject:
Message:

If necessary, enter your password below:

Password:
 

 

[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums is maintained by Stick with WebBBS 5.12.