{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

# lec2 - C260A Lecture 2 Intro to Inference Christopher Lee...

This preview shows pages 1–15. Sign up to view the full content.

C260A Lecture 2: Intro to Inference Christopher Lee September 29, 2009

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

View Full Document
What is the fundamental difference between math and science ? 1
A Diagnostic Test (T) for a Disease (D) T - T + total D + 1 9 10 D - 960 30 990 total 961 39 1000 p ( T + | D + ) = 9 / 10 ; p ( T - | D - ) = 960 / 990 2

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

View Full Document
Why We Need Conditional Probability For any probability claim, we need to know its condi- tions! p ( A | B ) totally different meaning than p ( B | A ) ! Real life has a crucial asymmetry: we go from observ- able variables to hidden variables. Mixing these up is deadly! 3
How can we define observable vs. hidden ? 4

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

View Full Document
An observable is a variable whose value has zero uncertainty. 5
An observable is a measurement whose operational definition yields a unique value with zero uncertainty (by definition). Everything else is hidden (by definition)! 6

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

View Full Document
For each of the following items, state one observable and one hidden parameter associated with it: a six-sided die; a photon; your friend; a completed paper ballot; an email you received; a cryptographic signature. Explain precisely how each “observed parameter” fulfills the operational definition. 7
Conditional Probability as Set Theory The basic set operations are intersection, union and negation . 8

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

View Full Document
p ( C ) | S C | | S | p ( A B ) | S A B | | S | p ( A B ) = | S A B | | S A | | S A | | S | p ( B | A ) p ( A ) 9
Bayes Law p ( H | O ) p ( O ) p ( O | H ) p ( H ) p ( H | O ) = p ( O | H ) p ( H ) p ( O ) posterior = likelihood × prior average likelihood 10

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

View Full Document
Claim: This Equation Captures the Scientific Method p ( H | O ) = p ( O | H ) p ( H ) p ( O ) 11
Hypothesis Testing p ( H | O ) = p ( O | H ) p ( H ) p ( O ) High likelihood high posterior 12

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

View Full Document
Occam’s Razor p ( H | O ) = p ( O | H ) p ( H ) p ( O ) Given two models with equal likelihood, the one with a higher prior will have a higher posterior. What can we say in general about priors of complex hypotheses vs. simple hypotheses?
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern