copyright © 2011 pearson education, inc. random variables chapter 9

Copyright © 2011 Pearson Education, Inc.

Random Variables

Chapter 9

9.1 Random Variables

Will the price of a stock go up or down?

Need language to describe processes that show random behavior (such as stock returns)

“Random variables” are the main components of this language


3 of 33


Definition of a Random Variable

Describes the uncertain outcomes of a random process

Denoted by X

Defined by listing all possible outcomes and their associated probabilities


4 of 33


Suppose a day trader buys one share of IBM

Let X represent the change in price of IBM

She pays $100 today, and the price tomorrow can be either $105, $100 or $95


5 of 33


How X is Defined


6 of 33


Two Types: Discrete vs. Continuous

Discrete – A random variable that takes on one of a list of possible values (counts)

Continuous – A random variable that takes on any value in an interval


7 of 33


Graphs of Random Variables

Show the probability distribution for a random variable

Show probabilities, not relative frequencies from data


8 of 33


Graph of X = Change in Price of IBM


9 of 33


Random Variables as Models

A random variable is a statistical model

A random variable represents a simplified or idealized view of reality

Data affect the choice of probability distribution for a random variable


10 of 33

9.2 Properties of Random Variables

Parameters

Characteristics of a random variable, such as its mean or standard deviation

Denoted typically by Greek letters


11 of 33


Mean (µ) of a Random Variable

Weighted sum of possible values with probabilities as weights


12 of 33

kk xpxxpxxpx ...2211


Mean (µ) of X (Change in Price of IBM)

The day trader expects on average to make 10 cents on every share of IBM she buys.


13 of 33

10$.

11.0580.0009.05

550055

ppp


Mean (µ) as the Balancing Point


14 of 33


Mean (µ) of a Random Variable

Is a special case of the more general concept of an expected value, E(X)


15 of 33

kk xpxxpxxpxXE ...2211


Variance (σ2) and Standard Deviation (σ)

The variance of X is the expected value of the squared deviation from µ


16 of 33

kk xpxxpxxpx

XE

XVar

22

221

21

2

2

...


Calculating the Variance (σ2 ) for X


17 of 33


Calculating the Variance (σ2 ) for X


18 of 33

99.4

11.010.0580.010.0009.010.05 222

2

XVar


The Standard Deviation (σ ) for X


19 of 33

23.2$99.4

XVarXSD

4M Example 9.1: COMPUTER SHIPMENTS & QUALITY

Motivation

CheapO Computers shipped two servers to its biggest client. Four refurbished computers were mistakenly restocked among 11 new systems. If the client receives two new systems, the profit for the company is $10,000; if the client receives one new system, the profit is $9,600. If the client receives two refurbished systems, the company loses $800. What are the expected value and standard deviation of CheapO’s profits?


20 of 33


Method

Identify the relevant random variable, X, which is the amount of profit earned on this order. Determine the associated probabilities for its values using a tree diagram. Compute µ and σ.


21 of 33


Mechanics – Tree Diagram


22 of 33


Mechanics – Probabilities for X


23 of 33


Mechanics – Compute µ and σ

E(X) = µ = $9,215

Var(X) = σ2 = 6,116,340 $2

SD(X) = σ = $2,473


24 of 33


Message

This is a very profitable deal on average. The large standard deviation is a reminder that profits are wiped out if the client receives two refurbished systems.


25 of 33

9.3 Properties of Expected Values

Adding or Subtracting a Constant (c)

Changes the expected value by a fixed amount: E(X ± c) = E(X) ± c

Does not change the variance or standard deviation: Var(X ± c) = Var(X)

SD(X ± c) = SD(X)


26 of 33


Multiplying by a Constant (c)

Changes the mean and standard deviation by a factor of c: E(cX) = c E(X)

SD(cX) = |c| SD(X)

Changes the variance by a factor of c2:Var(cX) = c2 Var(X)


27 of 33


Rules for Expected Values (a and b are constants)

E(a + bX) = a + bE(X) SD(a + b X) = |b|SD(X) Var(a + bX) = b2Var(X)


28 of 33

9.4 Comparing Random Variables

May require transforming random variables into new ones that have a common scale

May require adjusting if the results from the mean and standard deviation are mixed


29 of 33


The Sharpe Ratio

Popular in finance Is the ratio of an investment’s net expected

gain to its standard deviation


30 of 33

frXS


The Sharpe Ratio – An Example

S(Disney) = 0.0253S(McDonald’s) = 0.0171Disney is preferred to McDonald’s


31 of 33

Best Practices

Use random variables to represent uncertain outcomes.

Draw the random variable.

Recognize that random variables represent models.

Keep track of the units of a random variable.


32 of 33

Pitfalls

Do not confuse with µ or s with σ.

Do not mix up X with x.

Do not forget to square constants in variances.


33 of 33

x

copyright © 2011 pearson education, inc. random variables chapter 9

Documents