STT 861 Theory of Prob and STT I Lecture Note - 7
2017-10-18
Survival function and its example; transformation of random variables, scale and rate parameters and their examples; Joint probability density and its example; independent continuous random variables.
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 -> This post
- Lecture 08 - 2017.10.25
- Lecture 09 - 2017.11.01
- Lecture 10 - 2017.11.08
- Lecture 11 - 2017.11.15
- Lecture 12 - 2017.11.20
- Lecture 13 - 2017.11.29
- Lecture 14 - 2017.12.06
Lecture 07 - Oct 18 2017
Survival function
Definition: Survival function of a r.v. is 1-CDF.
if is the CDF of .
This is meaningful especially if is a waiting time. Indeed is the chance of survival to “age” .
Example 1
Memoryless property of the exponential distribution. Let . We know the CDF . Then
Important: this characterizes the exponential distribution.
Q: What is (P(Given X survival to age , what is the chance of survival units of time longer))?
A:
This proves that for , the information of how long we have survived tells us nothing about the likelihood of surviving units of time longer (Nothing to do with , the current “age”).
FACT: in a Poisson() process, the waiting time between two jumpers (arrivals) are i.i.d. r.v.’s.
Sketch of proof: Let’s prove first that .
This is the first time that reaches 1.
The event is the same as .
Therefore,
We also see this is the cdf of . We recognize the formula as .
Now, let’s convince ourselves that and and are independent. This is true because has independent increments. This is related to the memoryless property of ’s.
Example of transformation of r.v.’s
Let , let be fixed (not random). Let . Let’s find the distribution of via its CDF.
We recognize, via this survival function, that has the same CDF as .
Example 2
Let . Let . Find ’s law (distribution) via the survival function. (Note: when , )
A:
(Because the exp function is strictly increasing)
We recognize that .
Note: if we have , and we want to create a r.v. , we can take .
Example of scale and rate parameters
We saw that if we multiply an r.v., with parameter by a constant , we get with parameter .
For instance,
This shows that is a scale parameter.
We also say is a rate parameter when is multiplied by .
For instance, is the rate of arrivals of the Poisson r.v. (or process) in a time interval of length 1. But is the average waiting time for the next arrival. It is the scale of the waiting time.
Generally speaking, a r.v. (or its law) has a scale parameter if the CDF of has this form
We also say has a rate parameter if the CDF of has this form
Example 3
We just saw, for ,
so
Also
and is the scale paremeter .
Theorems: if is a scale parameter for , then
( is the special case)
If is a rate parameter for , then
( is the special case)
Then, let have scale parameter , then
is with .
let have rate parameter , then
Theorem: Arbitrary function of random variables.
Let have density . Let be a strictly monotone function (increasing or decreasing). So ’ the derivative basically exists, and the inverse function exists. Let . Then has this density.
Idea of proof:
Start from CDF, of and use chain rule.
Exercise: Use this theorem to check the when .
Definition: (Joint probability density) A pair of r.v. has a joint probability density (a function on ) if
Definition (More like a theorem): if as above is really , then and are independent.
Proof:
It also proves that is the density of and is the density of .
Example 4
Let if , and 0 otherwise. We see
(the places where , and , do match up) See and independent and and .
Example 5
Let when and , =0 otherwise. Then , each of them is i.i.d .
Example 6
Let if , =0 otherwise. Then the area in a 2D surface is a triangle. The constant is 2. We say that is uniform in that triangle. However, and are not independent. Because we have
This is a non-random relation, so and are dependent.
General theorem: For most shapes in we can define the uniform density on that shape if its area is finite, with parameter of . Moreover, if the shape has a center of symmetric then and are independent. When the shape is the rectangle . Then independent and ,
For a circle shape, and are not independent, but and are independent.
are independent.
Exercise: find the density of .
- ← Older-Find the Expectation of a Symmetric Probabiliry Density Function
- Spacemacs Rocks Note Day 1-Newer →