Home Critic's Corner

Discuss a review. Provide constructive feedback. Talk to the industry.

RE: Well, no

Yes you are correct they are not the same - they both meet the .05 significance level but for subtle differences a high number of trials reduces error. Ie more trials is better. A s noted from your link "Thus, for subtle differences, a very large number of trials is necessary to bring down Type 2 error risk to acceptable limits when Type 1 error is limited to .05."

It's quite late here and I am quite tired - it's also been 15 years since I ran these tests in psychology. What doesn't seem to be discussed here beyond the stats is the difference between "reliability" and "validity" - the latter is the most important aspect - without that you could be reliably producing numbers that are backing something that does not relate to valid hypothesis. Or another way you could be reliably getting the same answer over and over and over to the wrong question.

I'm only up to page 5 and will have to look at it tomorrow - midnight in HK.



This post is made possible by the generous support of people like you and our sponsors:
  Amplified Parts  


Follow Ups Full Thread
Follow Ups
  • RE: Well, no - RGA 08:53:27 07/11/12 (0)

FAQ

Post a Message!

Forgot Password?
Moniker (Username):
Password (Optional):
  Remember my Moniker & Password  (What's this?)    Eat Me
E-Mail (Optional):
Subject:
Message:   (Posts are subject to Content Rules)
Optional Link URL:
Optional Link Title:
Optional Image URL:
Upload Image:
E-mail Replies:  Automagically notify you when someone responds.