1
As we have seen in section 4 conditional probability density functions are useful to update the information about an event based on the knowledge about some other related event (refer to example 4.7). In this section, we shall analyze the situation where the related event happens to be a random variable that is dependent on the one of interest.
From (4-11), recall that the distribution function of X given an event B is
(11-1)
PILLAI
11. Conditional Density Functions and
Conditional Expected Values
2
Suppose, we let
Substituting (11-2) into (11-1), we get
where we have made use of (7-4). But using (3-28) and (7-7) we can rewrite (11-3) as
To determine, the limiting case we can let and in (11-4).
(11-3)
(11-2)
(11-4)
PILLAI
3
This gives
and hence in the limit
(To remind about the conditional nature on the left hand side, we shall use the subscript X | Y (instead of X) there). Thus
Differentiating (11-7) with respect to x using (8-7), we get
(11-5)
(11-6)
(11-7)
(11-8)
PILLAI
4
It is easy to see that the left side of (11-8) represents a valid probability density function. In fact
and
where we have made use of (7-14). From (11-9) - (11-10), (11-8) indeed represents a valid p.d.f, and we shall refer to it as the conditional p.d.f of the r.v X given Y = y. We may also write
From (11-8) and (11-11), we have
(11-9)
(11-10)
(11-11)
(11-12)
PILLAI
5
and similarly
If the r.vs X and Y are independent, then and (11-12) - (11-13) reduces to
implying that the conditional p.d.fs coincide with their unconditional p.d.fs. This makes sense, since if X and Y are independent r.vs, information about Y shouldn’t be of any help in updating our knowledge about X.
In the case of discrete-type r.vs, (11-12) reduces to
(11-13)
(11-14)
(11-15)
PILLAI
6
Next we shall illustrate the method of obtaining conditional p.d.fs through an example.
Example 11.1: Given
determine and Solution: The joint p.d.f is given to be a constant in the shaded region. This gives
Similarly
and
(11-16)
Fig. 11.1
(11-17)
(11-18)
PILLAI
7
From (11-16) - (11-18), we get
and
We can use (11-12) - (11-13) to derive an important result. From there, we also have
or
But
and using (11-23) in (11-22), we get
(11-19)
(11-20)
(11-21)
(11-22)
(11-23)
PILLAI
8
Equation (11-24) represents the p.d.f version of Bayes’ theorem. To appreciate the full significance of (11-24), one need to look at communication problems where observations can be used to update our knowledge about unknown parameters. We shall illustrate this using a simple example.
Example 11.2: An unknown random phase θ is uniformly distributed in the interval and where n ~ Determine Solution: Initially almost nothing about the r.v θ is known, so that we assume its a-priori p.d.f to be uniform in the interval
(24)
PILLAI
9
In the equation we can think of n as the noise contribution and r as the observation. It is reasonable to assume that θ and n are independent. In that case
~
since it is given that is a constant, behaves like n. Using (11-24), this gives the a-posteriori p.d.f of θ given r to be (see Fig. 11.2 (b))
where
(11-25)
(11-26)
PILLAI
10
Notice that the knowledge about the observation r is reflected in the a-posteriori p.d.f of θ in Fig. 11.2 (b). It is no longer flat as the a-priori p.d.f in Fig. 11.2 (a), and it shows higher probabilities in the neighborhood of
(b) a-posteriori p.d.f of θ
Fig. 11.2
Conditional Mean:
We can use the conditional p.d.fs to define the conditional mean. More generally, applying (6-13) to conditional p.d.fs we get
(a) a-priori p.d.f of θ
PILLAI
11
(11-27)
and using a limiting argument as in (11-2) - (11-8), we get
to be the conditional mean of X given Y = y. Notice that will be a function of y. Also
In a similar manner, the conditional variance of X given Y = y is given by
we shall illustrate these calculations through an example.
(11-28)
(11-29)
(11-30)
PILLAI
12
Example 11.3: Let
Determine and Solution: As Fig. 11.3 shows, in the shaded area, and zero elsewhere. From there
and
This gives
and
(11-31)
(11-32)
(11-33)
Fig. 11.3
PILLAI
13
Hence
It is possible to obtain an interesting generalization of the conditional mean formulas in (11-28) - (11-29). More generally, (11-28) gives
But
(11-34)
(11-35)
(11-36)
(11-37)
PILLAI
14
Obviously, in the right side of (11-37), the inner expectation is with respect to X and the outer expectation is with respect to Y. Letting g( X ) = X in (11-37) we get the interesting identity
where the inner expectation on the right side is with respect to X and the outer one is with respect to Y. Similarly, we have
Using (11-37) and (11-30), we also obtain
(11-38)
(11-39)
(11-40)
PILLAI
15
Conditional mean turns out to be an important concept in
estimation and prediction theory. For example given an
observation about a r.v X, what can we say about a related
r.v Y ? In other words what is the best predicted value of Y
given that X = x ? It turns out that if “best” is meant in the
sense of minimizing the mean square error between Y and
its estimate , then the conditional mean of Y given X = x,
i.e., is the best estimate for Y (see Lecture 16
for more on Mean Square Estimation).
We conclude this lecture with yet another application
of the conditional density formulation.
Example 11.4 : Poisson sum of Bernoulli random variables
Let represent independent, identically
distributed Bernoulli random variables with
16
and N a Poisson random variable with parameter that is
independent of all . Consider the random variables
Show that Y and Z are independent Poisson random variables.
Solution : To determine the joint probability mass function
of Y and Z, consider
(11-41)
PILLAI
(11-42)
17
(11-43)
PILLAI
Thus
and Y and Z are independent random variables.
Thus if a bird lays eggs that follow a Poisson random
variable with parameter , and if each egg survives
(11-44)
18
with probability p, then the number of chicks that survive
also forms a Poisson random variable with parameter
PILLAI