_1 x 0.50_ + _2 x 0

Document Sample
_1 x 0.50_ + _2 x 0 Powered By Docstoc
					      Economics 105: Statistics
• Any questions?
• Go over GH 4
      Discrete Random Variables
• Take on a limited number of distinct values
• Each outcome has an associated probability
• We can represent the probability distribution function
in 3 ways
    – function ƒ(xi) = P(X = xi)
    – graph
    – table
• Bernoulli distribution
   – graph & table ?
• Cumulative distribution function
        Discrete Random Variable
           Summary Measures
• Expected Value (or mean) of a discrete
   distribution (Weighted Average)
                          N
           m X º E(X) = å X i P( X i )
                          i =1


                                            X     P(X)
  – Example: Toss 2 coins,                   0     0.25
             X = # of heads,                 1     0.50
    compute expected value of X:             2     0.25

    E(X) = (0 x 0.25) + (1 x 0.50) + (2 x 0.25) = 1.0
             Discrete Random Variable
                Summary Measures
                                                                 (continued)
• Variance of a discrete random variable
                                        N
      s X = E[(X - mX ) 2 ] = å[X i - E(X)]2 P(X i )
        2

                                        i=1

• Standard Deviation of a discrete random variable

                          sX = s              2
                                              X

  where:
       E(X) = Expected value of the discrete random variable X
         Xi = the ith outcome of X
       P(Xi) = Probability of the ith occurrence of X
             Discrete Random Variable
                Summary Measures
                                                           (continued)

     – Example: Toss 2 coins, X = # heads,
       compute standard deviation (recall E(X) = 1)

           s=        å[X - E(X)] P(X )
                              i
                                                2
                                                    i


s = (0 -1) 2 (0.25) + (1-1) 2 (0.50) + (2 -1) 2 (0.25) = 0.50 = 0.707

                     Possible number of heads
                     = 0, 1, or 2
   Properties of Expected Values
• E(a + bX) = a + bE(X), where a and b are constants




• If Y = a + bX, then
   var(Y) = var(a + bX) = b2var(X)
                  Example
• Let C = total cost of building a pool
• Let X = days to finish the project
• C = 25,000 + 900X
• X P(X = xi)
  10     .1       Find the mean, std dev, and
  11     .3       variance of the total cost.
  12     .3
  13     .2
  14     .1
   Permutations and Combinations
• Need to count number of outcomes
• Number of orderings
   – x objects must placed in a row
   – can only use each once
   – x! = (x)(x-1)(x-2) … (2)(1) called “x factorial”
• Permutations
   – suppose these x ordered boxes can be filled with n objects
   –n>x
   – What is the number of possible orderings now?
   – Permutations of n objects chosen x at a time = nPx
   – nPx = n(n-1)(n-2) … (n-x+1) = n!/(n-x)!
   Permutations and Combinations
• How many ways to arrange, in order, 2 letters selected
from A through E?
• What if order doesn’t matter?
• Combinations
   nCx   = nPx/x! = n!/ [(n-x)! * x!]
• Eight people (5 men, 3 women) apply for a job. Four
employees are needed. If all combinations are equally
likely to be hired, what is the probability no women will
be hired?
     The Binomial Distribution
                 Probability
                Distributions

  Discrete
 Probability
Distributions

 Bernoulli

 Binomial

 Poisson

 Hypergeometric
         Binomial Distribution
• Binomial distribution is composed of repeated
Bernoulli trials
•Let X1, X2, …, XN be Bernoulli r.v.’s, then B is
                               N
                          B = å Xi
distributed binomially
                                     i =1
•Probability of x successes in N trials is
                              N -x
  P( B = x)= N Cx p (1 - p)
                    x
                                     , x = 0,1,2,..., N
where p is the prob of “success” on a given trial
           Binomial Distribution
• Let B ~ binomial, with p = prob of success, N =
number of trials
• Find E[B] and Var[B] … but first a couple more rules
on the mathematics of expectations with more than 1 r.v.
       Two Random Variables
• Expected Value of the sum of two random variables:

           E(aX + bY) = aE( X ) + bE(Y )
• Variance of the sum of two random variables:

   Var(aX + bY) º s aX+bY = a2s X + b2s Y + 2abs XY
                    2           2       2



• Standard deviation of the sum of two random
  variables:
                s aX +bY = s aX +bY
                             2
           Binomial Distribution
• Let B ~ binomial and now find E[B] and Var[B]
• McCoy’s Tree Service in Mocksville, NC removes
dead trees from commercial and residential properties.
They have found that 40% of their invoices are paid
within 10 working days. A random sample of 7 invoices
is checked. What is the probability that fewer than 2 will
be paid within 10 working days?

				
DOCUMENT INFO
Shared By:
Categories:
Tags:
Stats:
views:238
posted:10/29/2012
language:English
pages:14