Docstoc

Conditional Probability - PowerPoint

Document Sample
Conditional Probability - PowerPoint Powered By Docstoc
					   Sometimes to calculate the probability of
    an event directly is tedious, while it is
    easier to obtain the probability of the
    complement of this event.

   Example 14. Probability of Employee Selection
     A Congresswoman wants to hire four assistants
    from eight candidates. Five candidates are men,
    and three are women. If every combination of
    candidates is equally likely to be chosen, what is
    the probability that at least one women will be
    hired?
   Example 15. Born the Same Day?
     (A great question for a party!)

    There are 29 students in class Econ390. What
    is the probability that at least two students
    have the same birthday?
Conditional Probability
   Consider a pair of events A and B. Suppose we are
    concerned about the probability of A given that B has
    occurred.

   The idea is that the probability of an event is often
    affected by knowledge of circumstances.

   For example, if we randomly select someone from the
    general population, the probability of getting a male is 0.5,
    but if we know that the selected person frequently
    changes TV channels with a remote control, what is the
    probability in this case?
    Conditional Probability of A given B is denoted
    as P(A l B)
     and defined as
                P(A l B) = P (A ∩ B) / P(B) (Assumes P(B)≠0)

    Similarly,
                 P(B l A) = P (A ∩ B) / P(A) (Assumes P(A)≠0)


    Use relative frequencies to help us understand conditional probability.

    From the definition of condition probability, we can obtain the

      Multiplication Rule of Probability

                  P (A ∩ B) = P(B l A) P(A)
Also,
                  P (A ∩ B) = P(A l B) P(B)
   Example 1. Product Choice
    A hamburger chain found that 75% of all customers
    use mustard, 80% use ketchup, and 65% use both.
    If you are given the information that a randomly
    selected customer uses ketchup, what is the probability
    that she/he also uses mustard?
    Statistical Independence
     Event A and event B are said to be statistically independent
    if and only if
          P(B | A) = P(B) or P(A | B ) =P(A)

    which means the probability of B occurring doesn’t change even
    after given the information that A has occurred.

      If event A and event B are statistically independent, the
     multiplication Rule is
           P (A ∩ B) = P(B | A) P(A) = P(B)P(A)

    There are three ways to test if event A and B are statistically
     independent.
   Example 2. Probability of College Degrees

    Suppose that 48% of all bachelor degrees in a
    particular country are obtained by women and that 17% of
    all bachelor degrees are in business. Also, 6% of all
    bachelor degrees go to women majoring in business. Are
    the events “Bachelor degree holder is a women” and
    “Bachelor degree is in business” statistically independent?
   Statistically Independent Events ≠ Disjoint Events

   A and B independent means the information of A
    occurs or not does not affect the probability of B
    occurring

   If A and B are disjoint, the information of A occurring
    indicates that B does not occur.

   So if A and B are disjoint, they must be statistically
    dependent!

   If A and B are disjoint, P (A ∩ B) =0
   If A and B are independent, P (A ∩ B) =P(A)P(B)
Applying Multiplication Rule
    Example 3. Foul-ups
    A mail-order firm considers three possible foul-ups in filling an
     order:
    A: The wrong item is sent.
    B: The item is lost in transit.
    C: The item is damaged in transit.

     Assume that event A is independent of both B and C, and that
     events B and C are mutually exclusive. The individual event
     probabilities are P(A)=0.02, P(B)=0.01, P(C)=0.04. Find the
     probability that at least one of these foul-ups occurs for a
     randomly chosen order.

  Hint: P(A U B U C)=
P(A) + P(B) + P(C) - P(A ∩ B) – P(A ∩ C) - P(B ∩ C) + P(A ∩ B ∩ C)
    Example 4. On-Job Training
    A corporation provides separate classes in reading
    and practical mathematics for its employees. 40% of
     workers signed up for the reading classes, and 50%
    for the practical mathematics classes. Of those signing up
     for the reading classes, 30% signed up for the
     mathematics classes.

    (1) What is the probability that a randomly selected worker
     signed up for both classes?
    (2) What is the probability that a randomly selected worker
     who signed up for the mathematics classes also signed
     up for the reading classes?
    (3) What is the probability that a randomly chosen worker
     signed up for at least one of these two classes?
    (4) Are the events “Signs up for reading classes” and
     “Signs up for mathematics classes” statistically
     independent?
   Example 5. Loan Default

    A bank classifies borrowers as high-risk or low-risk. Only 15%
    of its loans are made to those in the high-risk category. Of all its
    loans, 5% are in default, and 40% of those in default are to high-
    risk borrowers. What is the probability that a high-risk borrower will
    default?

    A=a loan is made to high-risk category
    B=a loan is in default
    P(A)=0.15, P(B)=0.05, P( A | B )=0.4, P(B | A)=?

				
DOCUMENT INFO