Sie sind auf Seite 1von 26

STAT 342 Statistical Methods for Engineers

Discrete Random Variable


Random Variable is a quantitative variable whose value depends on chance

Probability Distribution and Probability Histogram

Probability Distribution A listing of the possible value and corresponding probabilities of a


discrete random variable, or a formula for the probabilities.

Probability Histogram A graph of the probability distribution that displays the possible
value of a discrete random variable on the horizontal axis and the probabilities of those
values on the vertical axis. The probability of each value is represented by a vertical bar
whose height equals the probability.
Probability Distribution
• Pattern of distribution of probabilities over all possible events

• Can be used to determine likelihood of occurrence of all possible outcomes

Variable described by probability distribution is called random variable

Classifications of Probability Distributions

• Discrete probability distribution is associated with random variable that can take on only a finite
number of values

• Continuous probability distribution is associated with random variable that can take on infinite
number of values
Probability Distribution
➢ The probability distribution is a complete probabilistic description of a random variable.

➢ All other statistical concepts (expectation, variance, etc) are derived from it.

➢ Once we know the probability distribution of a random variable, we know everything we can learn
about it from statistics.

• Probability function
– One form the probability distribution of a discrete random variable may be expressed in.

– Expresses the probability that X takes the value x as a function of x (as we saw before):

PX x   P( X  x)
Probability Distribution
• The probability function, properties
PX x   0 for each x  P x   1
X
x
1.0
Cumulative Probability Distribution (cdf) Cumulative normal
0.8 density function
The cdf is a function which describes the probability that
a random variable does not exceed a value.
0.6 Normal probability

FX  x   P X  x    f ( xi ) F 50.00%
density function

xi  x 0.4

The relationship between the cdf and the probability 2.28%


0.2
function:
FX x   P X  x    PX  X  y 
68.27%

0 -3s -2s -s m s 2s 3s
y x
Probability Distribution

x
F ( x)   f ( x)dx
0 , -


F ( x)   f ( x)dx  1
-

d ( F ( x))
f ( x) 
dx
Probability Distribution and Probability Mass Functions
For a discrete random variable X with possible values x1, x2, …..xn, a probability
mass function is a function such that:
f  xi   0
N

 f (x )  1
i 1
i

f  xi   P ( X  xi )

For a discrete random variable X, the cumulative distribution function, F(x)


satisfies the following properties
FX  x   P X  x    f ( xi )
xi  x

0  F ( x)  1
If x  y , then F ( x )  F ( y )
Expected Value
If a random variable x can have any of the values x1, x2 , x3 ,…, xn, and the corresponding probabilities of

these values occurring are P(x1), P(x2), P(x3), …, P(xn),

then the expected value of x is given by

E( x)  x1  P( x1 )  x2  P( x2 )   xn  P( xn ).
Mean and Variance of a Discrete Random Variable

Mean m  E  X    xf ( x)
x

Variance s  V ( X )  E ( X - m )   x - m  f ( x)   x 2 f ( x) - m 2
2 2 2

x x

Standard Deviation s  s2

s  V ( X )   x - m  f ( x)   x 2 f ( x) - 2m  xf ( x) m 2  f ( x)
2 2

x x x x

s 2  V ( X )   x 2 f ( x) - 2m 2  m 2   x 2 f ( x) - m 2
x x
Mean and Variance of a Discrete Random Variable
It is possible to calculate expectations and variances of functions of random variables

E g  X    g x P X  x 
x

V g  X    g x  - E g x  P X  x 
2

Linear functions
If a and b are constants and X is a random variable
It can be shown that:
E aX  b   aE X   b
V aX  b  a V  X 
2
Discrete Uniform Distribution
A random variable X has a discrete uniform distribution if each of the n values
in its range, say, x1, x2, …, xn, has equal probability, then,
1
f ( xi ) 
n
Discrete Uniform Distribution
 1
PDF  , a xb
f ( x)   b - a
 0, otherwise
 0, xa
x -a
CDF F ( x)   , x  [ a, b)
b - a
 1, xb
ba
Mean m  E( X ) 
2

(b - a ) 2
Variance s  V ( X ) 
2

12
Discrete Uniform Distribution

 Probability distribution function

f(x)

2,000 3,000 4,000 5,000 6.000


Lease operating cost, $
Discrete Uniform Distribution

 Cumulative distribution function

100

80
Cum % Less Than
or Equal To 60

40

20

0
0 1,000 2,000 3,000 4,000 5,000 6,000
Lease Operating Cost, $
Binomial Distribution
• A random experiment consists of Bernoulli trials such that
– Number of trials is discrete

– The trials are independent

– Each trial results in only one of two possible outcomes— “success” and “failure”

– Probability (p) of each outcome remains constant from one trial to the next

The random variable X that equals the number of trials that result in a success is a binomial
random variable with parameters 0<p<1 and n=1,2, …. The probability mass function of X is:

n n- x
f ( x)    p (1 - p )
x
x  0,1,........, n
 x
Bernoulli trials --independent trials with constant probability p of a success
Binomial Distribution

Figure 3-8 Binomial distributions for selected values of n and p.


Binomial Distribution
If X is a binomial variable with
parameters p and n,

Mean
m  E ( X )  np
Variance

s  V ( X )  npq
2

q 1 - p
Geometric and Negative Binomial Distribution
In a series of Bernoulli trials, the random variable X that equals the number of trials
until the first success is Geometric random variable with parameter 0<p<1, and

x -1
f ( x)  (1 - p ) p, x  1,2,....
➢ Repeated binomial trials

➢ Continue until first success

➢ Find probability that first success comes on nth trial

➢ Probability of success on each trial = p

m  E( X ) 
1 (1 - p ) q
Mean Variance s 2
 2
 2
p p p
Geometric Distribution is a probability distribution to determine the probability that success will
occur on the nth trial of a binomial experiment.
Geometric and Negative Binomial Distribution
In a series of Bernoulli trials, the random variable X that equals the number of trials
until r success occur is Negative Binomial random variable with parameter 0<p<1,
and r=1, 2, 3, …., and

 x - 1
f ( x)   (1 - p ) x - r p r , x  r , r  1, r  2,....
 r - 1

r
Mean m  E( X ) 
p

r (1 - p ) rq
Variance s 2
 2
 2
p p
Hypergeometric Distribution
In a set of N objects contains:
K objects classified as success & N-K objects classified as failure
A sample of size n objects is selected randomly (with replacement) from the N objects
where K  N and n  N.
The random variable X that equals the number of success in the sample is a
hypergeometric random variable and

 K  N - K 
  
 x  n - x 
f ( x)  , x  max{0, n  K - N }to min{K , n}
N
 
n
 N -n
Mean m  E ( X )  np Variance s 2
 np (1 - p ) 
 N -1 
Hypergeometric Distribution

Figure 3-12. Hypergeometric distributions for selected values of parameters N, K, and n.


Hypergeometric Distribution
Example 3-27
Hypergeometric Distribution
Example 3-27
Poisson Distribution
Given an interval of real numbers, assume events occur at random throughout the interval. If
the interval can be portioned into subintervals of small enough length such that:
1) The probability of more than one event in a subinterval is zero
(The probability of two successes in a small enough interval is 0%.)
2) The probability of one event in a subinterval is the same for all subintervals and
proportional to the length of the subinterval.
(The probability of a success is the same for any two intervals which share the same length.)
3) Successes are independent of successes in other intervals.

The random variable X that equals the number of events in the interval is a Poisson
random variable with parameter 0   , and the probability mass function of X is
e - T (  T ) x
f ( X  x)  x  0,1,2,....
x!
Poisson Distribution

Mean m  E ( X )  T

Variance s 2  V ( X )  T

Figure 3-14 Poisson distributions for λ = 0.1, 2, 5.


Poisson Distribution

Das könnte Ihnen auch gefallen