Validity_Existence - Hi Sarah, I was delighted to find that...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Hi Sarah, I was delighted to find that you are thinking about the two topics, validity and existence. Regarding, Do we "seek out" curve properties to test the existence of a curve? When there is a problem with a basic statistical theorem like the Central Limit Theorem, or an important inequality, http://en.wikipedia.org/wiki/Chebyshev %27s_inequality, it usually is due to there being a property of a curve that does not exist (either it is ill-defined or is, in essence, infinite). Validity, on the other hand, refers to the match-up between models and curves. This match-up is tantamount to the model's adequate representation of reality. Both invalidity and non-existence require checking. However, validity and goodness-of-fit are close to synonyms. Non-existence issues almost always point to big-time conceptual issues, such as the need to control for the size of an at-risk group by procedures more sophisticated than the mere division of a count of bad event occurrences by a count of at-risk group size. Looking forward to continuing this Friday.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/04/2011 for the course PB HLTH 140 taught by Professor Tarter during the Fall '10 term at University of California, Berkeley.

Page1 / 2

Validity_Existence - Hi Sarah, I was delighted to find that...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online