lect10v1

# lect10v1 - Stat 104 Quantitative Methods for Economists...

This preview shows pages 1–6. Sign up to view the full content.

Stat 104: Quantitative Methods for Economists Class 10: Introduction to Probability, Part III 1

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

View Full Document
Bayes’ Theorem s One important point about conditional probability is that (usually) P(A|B) does not equal P(B|A). s Some books make a big deal out of this but its not that fancy a concept. s The usual example concerns drug testing; it’s a good example to study since it focuses us on why its important to understand what one is conditioning on. 2
Urine or You’re Out s Suppose the Incredibly Rapid Rooter Plumbing Company wants to drug test their employees. s They purchase a test with the following characteristic : 3 P(test + | actual drug user) = 98%.

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

View Full Document
What do we want to condition on? s You always condition on what you know , so for an employer’s legal department, they need to know P(actual drug user | test +). s That is, what is the chance the test will be correct ? s Just because P(A|B) is near 100% doesn’t imply P(B|A) has to be near 100%. s That is, P(test+|Druggie)=.98 doesn’t mean P(Druggie|test+) = 0.98 4
s Suppose also that P(test - | non drug user) = 90% and that Rapid Rooter also has good reason to suspect that 10% of his employees are drug users. s Using the multiplication rule we can create the usual 2x2 table. 5

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 24

lect10v1 - Stat 104 Quantitative Methods for Economists...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online