Scribd
Upload
3 views2 pages

My Probability Notes

Lecture 3 covers fundamental concepts of probability, including events, combining events, and the additive and complement rules. It explains conditional probability and the distinction between disjoint and independent events, along with Bayes' theorem for flipping conditional probabilities. Key examples illustrate how to calculate probabilities in various scenarios.

Uploaded by

kaliamiranda47
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
3 views2 pages

My Probability Notes

Lecture 3 covers fundamental concepts of probability, including events, combining events, and the additive and complement rules. It explains conditional probability and the distinction between disjoint and independent events, along with Bayes' theorem for flipping conditional probabilities. Key examples illustrate how to calculate probabilities in various scenarios.

Uploaded by

kaliamiranda47
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Lecture 3: Probability

●​ An event is something that either happens or doesn’t happen, or is true or is not true
○​ Can be written as P(A)
●​ Combining events:
○​ P(A and B) is the probability that both events A and B will happen
■​ Both happen together / overlap/intersect
■​ i.e. P(student and employed) = students who also have jobs
○​ (P(A or B) is the probability that either event A or event B will happen (or both)
■​ Everything in either category
■​ i.e. P(student or employed) = people who are students, employed, or both
●​ Additive rule: (P(A or B)
○​ P(A or B) = P(A) + P(B) - P(A and B)
■​ When you add P(A) + P(B), you count the overlap twice, so you remove it
once
■​ i.e. P(student) = 0.4, P(employed) = 0.6, P(student and employed) = 0.2
●​ P(student or employed) = 0.4 + 0.6 - 0.2 = 0.8
●​ Complement rule: P(not A)
○​ Probabilities have to add up to 1 (100%), either something happens or it doesn’t
○​ P(not A) = 1 - P(A)
■​ i.e. P(not loyal) = 1 - P(loyal)
■​ = 1 - 0.136
■​ = 0.864
●​ Conditional probability: P(A if B)
○​ P(A if B) = P(A and B) / P(B)
■​ Meaning: among cases where B happen, what fraction also have A
■​ i.e. P(promoted and high performer) = 0.15, P(high performer) = 0.30
■​ P(promoted if high performer) = 0.15 / 0.30 = 0.5
■​ Translation: 50% of high performers get promoted
○​ Can be rearranged: (P(A and B) = P(A if B)*P(B)
●​ Disjoint events: P(A and B) = 0
○​ Events A and B are disjoint or mutually exclusive if only one of the two events
can happen
○​ A and B cannot happen, they’re mutually exclusive
■​ i.e. P(heads and tails on same coin flip) = 0
■​ You can’t get both on one flip
○​ Disjoint events are never independent
●​ Independence: (P(A if B) = P(A)
○​ Knowing B happened doesn’t change the probability of A
■​ i.e. P(rain) =0.3, P(rain if Tuesday) = 0.3
■​ The day of the week doesn’t affect rain, so they’re independent
○​ If A and B are independent: P(A and B): = P(A) * P(B)
●​ Bayes problem is when you need to “flip” a conditional probability
○​ You’re given P(B if A), you want P(A if B)
○​ Count actual people
■​ Start with 100 people, split by base rate
■​ Apply test accuracy to each group
■​ Add up who tests positive
■​ Calculate fractions that are actually positive

You might also like