# Chap07 - Chapter 7 Discrete Probability Distributions 1 1...

This preview shows pages 1–12. Sign up to view the full content.

1 Chapter 7 Discrete Probability Distributions

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

View Full Document
2 1. Counting 1. Permutations 2. The binomial coefficient 2. Binomial Distribution 3. Expectations 1. Linearity 2. Additivity of means 3. Additivity of independent variances 4. Cumulative Distribution Function (cdf)
3 Permutations and Combinations • For any set {x 1 , …, x n } of n objects, there are exactly n! = n(n – 1)(n – 2)…(3)(2)(1) (linear) orderings of the objects. Each such ordering is a permutation . Incidentally, 0! = 1 (check your calculator) You can check your calculations using the Eviews command: show @fact(n) e.g. show @fact(6) returns 720

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

View Full Document
4 Notice that permutations do not intrinsically involve “orderings”. n! is the number of ways that n objects can paired up in a one-to-one fashion with n categories, slots, other objects, etc. E.g., In a ballroom dance class with 5 men and 5 women, there are exactly 5! (= 120) ways to pair up the dancers. But talk of “orderings” and “lists” is very intuitively appealing, so we’ll often do it.
5 How many ways are there to create an ordered list of length k from our set of n objects (assume k < n)? n(n – 1)(n – 2)…(n – k + 1)

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

View Full Document
6 Notice also that a little algebra shows that: So there are n!/(n – k)! ways to form an k- length sequence using a set of n objects. You can check your work on Eviews using the command: show @fact(n)[email protected](n-k) e.g., show @fact(7)[email protected](7-5) returns 2520. )! ( ! ) 1 ( ) 2 )( 1 ( k n n k n n n n - = + - - -
7 The binomial coefficient The term is known as the binomial coefficient , aka a combination . It is often written as , and pronounced “n choose k” It expresses: the number of ways that you can select k distinct unordered objects from a set of n objects . Let’s see how this is so in two ways. )! ( ! ! k n k n - k n

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

View Full Document
8 First way: Select k objects . The number of ways of selecting k objects is: But since we don’t care about the order of these k objects, any list containing the same k objects should be “identified” For any k objects, we can form k! lists, so we have: ways of choosing k out of n objects ) 1 ( ) 2 )( 1 ( + - - - k n n n n = + - - - ! ) 1 ( ) 2 )( 1 ( k k n n n n = - - + - - - )! ( )! ( ! ) 1 ( ) 2 )( 1 ( k n k n k k n n n n = - )! ( ! ! k n k n k n
9 Second way: select them all . Start by selecting all n objects in order (you will only keep the first k). There are n! ways of doing this. We don’t care about the ordering of the first k objects, or about the ordering of the last (n – k) objects. We only care about which objects are among the first k (and which are in the remaining (n – k)). So again, we have ways of choosing k out of n objects without = - )! ( ! ! k n k n k n

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

View Full Document
Notice that we can cancel out many elements. E.g., calculating is not hard, and you can always eliminate the denominator: 5 15 5 15 ! 10 ! 5 ! 15 = ) 11 )( 13 )( = ) 11 )( 13 )( 7 ( 3 = 003 , 3 =
11 Notice also that: - = k n n k n ))! ( ( )! ( !

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.

## This note was uploaded on 01/20/2011 for the course ECON 15A taught by Professor Shirey during the Winter '08 term at UC Irvine.

### Page1 / 93

Chap07 - Chapter 7 Discrete Probability Distributions 1 1...

This preview shows document pages 1 - 12. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online