Distribution summaries Flashcards
What is expectation
If X is a random variable with a range space R,
E [π] = β π₯π(π₯) where x is a set of the real numbers
The expectation is the probability-weighted sum over all possible outcomes of the random variable. Values with high probability contribute more to the sum than values with low probability, hence the informal interpretation of the expectation as a βtypical valueβ.
What is a moment
the Rβth moment, of a random variable X is E[X^R]
- X can be discrete or continuous
- E[X^R] may not exist
- E[X^R] has some useful information to summarise our distribution of our random variable X
when r = 1 we get our expectation
when r = 2, the value is useful to get Variance and SD of X
When r = 3, the value is useful to get our skewness
when r = 4, the value is useful to get kurtosis
What is a central moment
The Rβth central moment of our random variable X, is E[(x- mu]^R]
where mu = E[X]
What is the 1st central moment of a random variable X?
0
What is the formula for variance
The second central moment, or
E[(x-mu)^2]
What is the definition of variance
the spread of the distribution around the centre, which we have defined as the expectation
What is the Rβth standardised central moment?
E[((X-mu)/sigma)^R]
when R = 3, the skewness is defined
for symmetric distributions skew[x] = 0
What is the skewness of a random variable X?
the 3rd central standardised moment of X
In terms of probability distributions, what is a quantile
A quantile is a value in the range space of the random variable corresponding to a given exceedant probability
let q be the set of whole numbers greater than one,The π-quantiles of a random variable π is the set of quantiles of π given by {π₯1/π,π₯2/π,β¦,π₯(πβ1)/π}.
The π-quantiles are the cut-points that divide the range space of π into π interva
let q be the set of whole numbers greater than one,The π-quantiles of a random variable π is the set of quantiles of π given by {π₯1/π,π₯2/π,β¦,π₯(πβ1)/π}.
The π-quantiles are the cut-points that divide the range space of π into π interva