STT 861 Theory of Prob and STT I Lecture Note - 11
2017-11-15
Proof of the "Tower" property; discrete conditional distribution; continuous conditional distribution expectation and variance and their examples; linear predictor and mean squared error.
Portal to all the other notes
- Lecture 01 - 2017.09.06
- Lecture 02 - 2017.09.13
- Lecture 03 - 2017.09.20
- Lecture 04 - 2017.09.27
- Lecture 05 - 2017.10.04
- Lecture 06 - 2017.10.11
- Lecture 07 - 2017.10.18
- Lecture 08 - 2017.10.25
- Lecture 09 - 2017.11.01
- Lecture 10 - 2017.11.08
- Lecture 11 - 2017.11.15 -> This post
- Lecture 12 - 2017.11.20
- Lecture 13 - 2017.11.29
- Lecture 14 - 2017.12.06
Lecture 11 - Nov 15 2017
Reinterpretation of last part of item (c) in proof of Theorem 5.2.1 in textbook.
Recall : let , be 2 random variables. Just to make things simple, assume and are discrete, with PMF’s and and joint PMF .
Generally, for a function ,
where .
We want to think of that result in the following way:
-
The meaning of the notation is the value of the function ( g(x) ) where is replaced by the random variable .
-
However, we reinterpret as:
(think of this as a definition.)
Now we reinterpret the formula above like this:
The first line means “An expectation can always be written as the expectation of a conditional expectation”. It is known as the “tower” property of conditional expectation.
The second line means: “when conditioning by , can be considered as known (non-random) and any factor depending on can be pulled out of the conditional expectation”.
Proof the Star ():
(RHS = right hand side) This is the proof of star.
Next, we use star () to compute the unconditional variance by conditional by .
where , .
We will first compute
We have proved
Now we interpret
is also known as .
So we see (expectation of conditional variance).
Finally,
this is the variance of the conditional expectation.
Homework Problem 5.2.5 Part b
takes value with probability , with probability 0.5 and 0.5. .
Q: Find
Example 1
people come into a store in a given day, customer spends dollars. Let be the total $ of sales for the day.
A: Find and .
Assume:
- is independent of all the ’s
- s are i.i.d.
Let’s compute
We know is related to . Therefore we must compute conditional variance
- Conditional variance is
- Conditional expectation is
We have just proved that .
Next,
We proved here , now finally go back to the original formula,
where , where are i.i.d and independent of ’s.
Exercise: Prove the following (using similar method of proof as for the formula).
and therefore,
where .
Also, for and , compute and .
Example 2
let , , therefore, is a certain , where the is the above and each is , i.i.d.
Let , find .
Continuous Case
Example 5.3.2
, .
Let , therefore, .
Let , this is called Beta random variable .
Let’s now try to prove that and are independent.
A: Let . It turns out (Wikipedia) .
Therefore .
This gives us an example where the function is linear as a function of because .
This situation where is linear given is pretty exceptional.
We call the predictor of given . But what is the linear predictor?
Linear Predictor and Mean Squared Error
We would like to predict using a linear function of .
Let be the linear predictor. Consider the error in replacing by .
We can choose and such that .
More systematically, let’s consider what statistic cases might called the mean square error (MSE)
we want to minimize MSE over all possible choices of the 2 values and . It turns out that and best .
Note: this is the closely allied to the question of linear regression. It turns out the MSE fir that pair of is
This says: the uncertainty level on is . The proposition of that variance which is explained by is the variance of is
and what is not explained by is the MSE .
Summary: with as above and , . we see that the amount of variance of explained by is The MSE is the variance of unexplained by .