Re: Monte Carlo NEWS – 1971. JASA
- From: "Luis A. Afonso" <licas_@xxxxxxxxxxx>
- Date: Tue, 31 Jul 2007 17:47:56 EDT
David Winsemius, you know very well and teach fully Jack Tomsky that is elementary the following:
THE MOST IMPORTANT THING
______Hypotheses Tests are unable to fully account if H0 is TRUE or NOT TRUE..
We accept (fail to reject) H0 BUT WE NEVER KNOW IF THE HYPOTHESES IS TRUE.
______If we reject H0 is not because Ha (alternative) is true but merely because the test statistics shows a value not compatible with Ho true. The vale falls inside the REJECTION INTERVAL.
To have doubts in this matter only could be originated from insufficiently leaned persons.
The example:
_____How many flips should be performed in order to state a coin is FAIR is currently asked to students to answer, here in Portugal, since the first lesson on Hypotheses Tests, Elementary Level.
I am sure that this problem or equivalent ones (which are quite simple to find), are used in your Country.
____________
Luis
.
- Follow-Ups:
- Re: Monte Carlo NEWS – 1971. JASA
- From: Jack Tomsky
- Re: Monte Carlo NEWS – 1971. JASA
- Next by Date: Re: Unbiased MLE estimators
- Next by thread: Re: Monte Carlo NEWS – 1971. JASA
- Index(es):