Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
142 views

Change of Variable Technique

Let x be a continuously distributed random variable with a probability density function f (x) and let y = y(x) be a monotonic transformation. Describe how the probability density function of y is derived if (x) is known. Take care to distinguish the case where y=y(x), is a positive transformation from the case where it is a negative transformation.

Uploaded by

Gilbert Gb Kichoi
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PDF, TXT or read online on Scribd
142 views

Change of Variable Technique

Let x be a continuously distributed random variable with a probability density function f (x) and let y = y(x) be a monotonic transformation. Describe how the probability density function of y is derived if (x) is known. Take care to distinguish the case where y=y(x), is a positive transformation from the case where it is a negative transformation.

Uploaded by

Gilbert Gb Kichoi
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

CHANGE-OF-VARIABLE TECHNIQUE

1. Let x be a continuous random variable with a probability density function


f (x) and let y = y(x) be a monotonic transformation. Describe how the
probability density function of y is derived if f (x) is known, taking care to
distinguish the case where y = y(x) is a positive transformation from the
case where it is a negative transformation.
The levels of personal bank acounts are distributed normally with a mean
of £690 and a standard deviation of £30. What is the probability that an
individual will have more than £720 if it is known that he has more than
£700?

2. Let x be a continuously distributed random variable with a probability


density function f (x), and let y = y(x) be a monotonic transformation.
Describe how the probability density function of y is derived if (x) is known,
taking care to distinguish the case where y = y(x) is a positive monotonic
transformation from the case where it is a negative transformation.
Let x have the probability density function f (x) = 1; 0x1. Find the prob-
ability density fuction of y = −2 log x.

Answer: We have y = y(x) = −2 log x and x = x(y) = e−y/2 Hence

dx 1 1
= − e− 2 y and, therefore,
dy 2
© ª¯¯ dx ¯¯ 1 − 1 y
g(y) = f x(y) ¯ ¯ = e 2
dy 2

is the pdf of y.

3. Let x ∼ f (x) be a continuous random variable and let y = y(x) be a mono-


tonic transformation. Describe how the probability function of y is derived
if f (x) is known, taking care to distinguish the case where y = y(x) is a
positive transformation from the case where it is a negative transformation.
Find the probability density functions of (a) 2x + 1 and (b) 2x2 + 1.

4. Let x be a continuously distributed random variable with a probability


density function f (x), and let y = y(x) be a monotonic transformation.
Describe how the probability density function of y is derived if f (x) is
known, taking care to distinguish the case where y = y(x) is a positive
transformation from the case where it is a negative transformation.

1
EXERCISES IN STATISTICS

In a statistical model, the time which elapses between the start of a


fire and the beginning of the action which extinguishes it is distributed
according the function
f (t) = ae−at .
√
The costs of the fire damage are deemed to be proportional to t. Find
a distribution from which one might infer the expected cost of the fire
damage. Comment on the adequacy of this model.

5. Let x be a continuous random variable with a probability density function


f (x) and let y = y(x) be a monotonic transformation. Describe how the
probability density function of y is derived if f (x) is known, taking care to
distinguish the case where y = y(x) is a positive transformation from the
case where it is a negative transformation.
The levels of personal bank accounts are distributed normally with a
mean of £690 and a standard deviation of £90. What is the probability
that an individual will have more than £780 if it is known that he has
more than £720?

Answer. Bank accounts are distributed as N (µ = 690, σ = 90). We have to


evaluate
P (x > 780)
P (x > 780|x > 720) = .
P (x > 720)
We begin by finding equivalent events in term of the standard normal variate
z = (x − µ)/σ = (x − 690)/90. We have the following equivalences:
780 − 690
x > 780 ⇐⇒ z > = 1,
90
720 − 690 1
x > 720 ⇐⇒ z > = .
90 3
From tables of the standard normal, we find that
P (z > 1) = 1 − (0.5 + 0.3413)
= 0.1587.
and that
P (z > 13 ) = 1 − (0.5 + 0.1293)
= 0.3707.
Therefore
P (x > 780)
P (x > 780|x > 720) =
P (x > 720)
P (z > 1) 0.1587 1
= 1 = 0.4707 ' 2 .
P (z > 3 )

You might also like