The Math Forum

Search All of the Math Forum:

Views expressed in these public forums are not endorsed by NCTM or The Math Forum.

Math Forum » Discussions » sci.math.* » sci.stat.math

Notice: We are no longer accepting new posts, but the forums will continue to be readable.

Topic: Almost surely one is able to detect differences . . .
Replies: 0  

Advanced Search

Back to Topic List Back to Topic List  
Luis A. Afonso

Posts: 4,758
From: LIsbon (Portugal)
Registered: 2/16/05
Almost surely one is able to detect differences . . .
Posted: Dec 25, 2012 2:55 PM
  Click to see the message monospaced in plain text Plain Text   Click to reply to this topic Reply

Not surprisingly there are a lot of persons rather uncomfortable with the random event?s nature . . . The anti-NHST people has a handful arguments that unfortunately has some impact on insufficiently learned ones.
Here one of them was chosen: What is the usefulness of a tool that, gathering a sufficiently data, we are always leading to reject a Null Hypotheses? Not to reject is surely synonymous of enough data collected.
They are absolutely right. . . except on a `mince´ detail: the usefulness.

What could be counter claimed?
___We are before the result of a concrete experiment which is depending on all conditions conditioning it. Sample size for a physicist is like a resolution power: if small or large it does disallow to detect little things or allows to. I do not feel surprised if a small sized sample admits/not rejects almost whatever hypotheses; and likely if very large ones are able to see no mater small differences. Anti-NHST people seem it was demanded that a difference (of parameters) must be noticed whatever the number of items sampled. Foolish.
I can state that a sample can carry a lot of information about its parameters if sufficiently large or contrarily do not if small or not random.

Luis A. Afonso

Point your RSS reader here for a feed of the latest messages in this topic.

[Privacy Policy] [Terms of Use]

© The Math Forum at NCTM 1994-2018. All Rights Reserved.