Continuous families: summary
01 Theory
Theory 2
Uniform:
- All times
equally likely. Exponential:
- Measures wait time until first arrival.
Erlang:
- Measures wait time until
arrival. Normal:
Link to original
- Limiting distribution of large sums.
Normal distribution
02 Theory
Theory 1
Normal distribution
A variable
has a normal distribution, written or “ is Gaussian ,” when it has PDF given by: The standard normal is
and its PDF is usually denoted by : The standard normal CDF is usually denoted by
:
- To show that
is a valid probability density, we must show that .
- This calculation is not trivial; it requires a double integral in polar coordinates!
- There is no explicit antiderivative of
- A computer is needed for numerical calculations.
- A chart of approximate values of
is provided for exams.
- To check that
:
- Observe that
is an odd function, i.e. symmetric about the -axis. - One must then simply verify that the improper integral converges.
- To check that
:
- Since
, we find:
- Use integration by parts to compute that
. (Select and .)
General and standard normals
Assume that
and are constants. Define . Then: That is,
has the distribution type . Derivation of PDF of
Suppose that
. Then: Differentiate to find
: From this fact we can infer that
Link to originaland whenever .
03 Illustration
Example - Basic generalized normal calculation
Basic generalized normal calculation
Suppose
. Find . Solution
First write
as a linear transformation of : Then:
Look in a table to find that
and therefore: Link to original
Example - Gaussian: interval of
Gaussian: interval of 2/3
Find the number
such that . Solution
First convert the question:
Solve for
so that this value is : Use a
Link to originaltable to conclude .
Example - Heights of American males
Heights of American males
Suppose that the height of an American male in inches follows the normal distribution
. (a) What percent of American males are over 6 feet, 2 inches tall?
(b) What percent of those over 6 feet tall are also over 6 feet, 5 inches tall?
Solution
(a) Let
be a random variable measuring the height of American males in inches, so . Thus , and: (b) We seek
as the answer. Compute as follows: Link to original
Example - Variance of normal from CDF table
Variance of normal from CDF table
Suppose
, and suppose you know . Find the approximate value of
using a table. Solution
So
and thus . Then: so
. Looking in the chart of
Link to originalfor the nearest inverse of 0.8, we obtain , hence .