Of Notes
Expected Values
Table of Contents
An expected value of some function
For discrete cases its given by the weighted sum:
and for a continuous its simply integration;
However both can be approximated easily by saying:
For some
Multivariable Expectations
If we are considering functions like
When we have a joint distribution
When we have some conditional
which we can derive from the definition of conditional probability
Operations
Linearity: an expected value of the sum of two random variables is the sum of their expected values:
When calculating the expectation of some transformed variable like a square, you just square the variable not the probability inside the sum.
Angle Bracket Notation
Some common uses:
- Mean of a random variable:
- Moments of a distribution:
, e.g. the variance is - Thermal averages in statistical mechanics:
for some observable - Averages over ensembles in simulation:
, matching the approximation above