Uniform distribution

A continuous random variable X has a uniform distribution over (a, b) if the pdf is given by

 1
b  a a xb

f ( x)  
 0 elsewhere


Verify that f ( x) is a p.d.f.
Construct the cumulative distribution function F ( x)

ba (b  a)2
Show that E[ X ]  and Var ( X )  E[ X 2 ]  (  )2 
2 12

Exponential distribution

An Exponential random variable measures waiting time to the first occurrence of some event A,
where A occurs according to a Poisson process ( i.e.: the number of occurrences of A in any
time period or interval has a Poisson distribution.)

Define  and Y as follows:

 = average number of occurrences in 1 unit of time

Y = number of occurrences in x units of time

E (Y )  average number of occurrences in x units of time   x

Hence Y is a Poisson random variable with average rate   x

e x (x) y
P(Y  y)  for y  0,1, 2,.......
y!

Let us take some interval [0, x )

The probability that no events occur in this interval is

1
i.e: P(waiting longer than time x for the next event to occur)
P( X  x)  e x if X ~ Exp( )

Thus if events occur in time according to a Poisson process then the time to the next event follows
an exponential distribution.

Exponential distribution is often useful to model length of life of a component, waiting time to the
arrival of the next customer etc.

Poisson distribution
Suppose we want the probability distribution of the number of motor accidents at an intersection in
a week. We could think of the time period of 1 week being split up into n sub-intervals (each of
which are so small such that at most 1 accident occurs in it with probability p different from zero.
Thus
P(no accident occurs in subinterval)= 1  p
P(one accident occurring in sub-interval) = p
P(more than one accident occurring in the sub-interval ) = 0

- Total no of accidents in a week = total no. of subintervals that contain one accident
- If accidents are regarded as independent from interval to interval, the total number of
accidents ~Binomial.
- There is no unique way of choosing n and p
Therefore we can divide the week into a larger number of sub-intervals so that the probability p of
an accident in a shorter sub-interval is smaller

n
Letting   np and taking the limit as n   of the binomial probability p( x)    p x q n  x , we can
 x
derive the probability mass function as
 e   x
 x! x  0,1, 2,....

p( x)  
 0 elsewhere



2
Example 1
Suppose that the number of customers arriving at the bank follows a Poisson distribution with an
average of   10 per hour. Find
i) P(more than 2 customers arriving per hour)
ii) P(at least 2 customers arriving per hour)
iii) P(6 customers arriving in 24 minutes)

Example 2:
There are two entrances to a parking lot. Cars arrive independently at both entrances according to
a Poisson distribution. At entrance 1they arrive at a rate of 4 per 5 minutes and at entrance II they
arrive at a rate of 3 per 5 minutes. What is the probability that 3 cars arrive at the parking lot in a 5
minute period.

Note If X ~ P( ) and Y ~ P( ) and X and Y are independent then ( X  Y ) ~ P(   )

Show that if X is a discrete random variable that follows a Poisson distribution with parameter 
then
E[ X ]  
and
Var[ X ]   (Exercise for student. NB: Use Var[X] = E[X2] - (E[X])2 where E[X2]=E[X(X-1)]+E[X]

Exponential continued…..
A continuous random variable (c.r.v) has an exponential distribution if it has for some  , a pdf
(  >0)
 e   x x0

f ( x)  
 0 elsewhere

Exercise: Verify that f(x) is a p.d.f.
1
Show that E[ X ] 


3
and
1
Var[ X ] 
2

Example 1:
Suppose that X has an exponential probability density function with parameter  .
Show that if a  0 and b  0 that
P( X  a  b | X  a)  P( X  b)

Example 2
The lifetime in hours , X , of a certain electronic component is an exponential distribution with
mean time to failure 100 hours. Three of these components operate independently in a piece of
equipment. The equipment fails if at least two components fail. Find the probability that the
equipment operates for at least 200 hours without failure.

Example 3
A textile producer has established that an old spinning machine stops randomly due to thread
breakages at an average rate of 5 stoppages per hour. It is assumed that the number of
stoppages per hour follows a Poisson distribution.
1. State if the following statements are true/ false?
a) If Y = waiting time (in minutes) between stoppages on the spinning machine, then
 5 
Y ~ EXP   .
 60 
b) The variance of the number of stoppages within a 2-hour period is 10.

2. A stoppage has just occurred. Calculate the probability that the next stoppage will occur within
the next 10 minutes.

3. Calculate the probability of the machine experiencing 12 stoppages in a 3-hour period,.

Example 4
Let X have an exponential distribution.
(i)
4
 ce  x x  a (a  0;   0)

f ( x)  
 0 elsewhere

Find the value of c that makes f(x) a p.d.f.
(ii)
ke  x 0 xa

g ( x)  
 0 elsewhere

Find the value of k that makes g(x) a p.d.f.

(iii)
me  x a xb

h( x )  
 0 elsewhere

Find the value of m that makes h(x) a p.d.f.
(iv) Find the mean and variance of these distributions