Standard Normal Distribution

A continuous r.v. is said to have the standard normal distribution if its PDF is given by

We write this as since, as we could obtain has mean and variance

The corresponding CDF is

Normal Distribution

If , then

is said to have the normal distribution with mean and variance , for any real and with . We denote this by

And the PDF of Normal distribution is

Moments

Non-central

Central

OrderNon-central momentCentral moment
10
2
30
4
50
6
70
8

Log Normal

Let be a standard normal variable, and let and be two real numbers, with . Then, the distribution of the random variable

is called the log-normal distribution with parameters and . We can also write

Multivariate Normal

A -dimensional random vector is said to have a Multivariate Normal (MVN) distribution if every linear combination of the has a Normal distribution. That is, we require

to have a Normal distribution for any constants . If is a constant, we also consider it to have a Normal distribution with variance . An important special case is ; this distribution is called the Bivariate Normal (BVN)

If is MVN, then the marginal distribution of is Normal, since we can take to be and all other to be . However, the converse is false: it is possible to have Normally distributed r.v.s. such that is not Multivariate Normal.

If and are Multivariate Normal random vectors with independent of , then the concatenated random vector is Multivariate Normal

To specify an MVN random vector , we need the parameters as follows:

  • the mean vector where
  • the covariance matrix, which is the matrix of covariances between components, arranged so that the entry is

Bivariate Normal

Let be BVN with marginals and . By the definition of Multivariate Normal, any of the form

will be Bivariate Normal, where i.i.d. . The means are already . Setting the variance qual to gives

Setting the covariance of and equal to gives . There are more unknowns than equations here, and we just need one solution. To simplify, let’s look for a solution with , then we have

Let , we get

By the changes of variables, we have the Jacobian

which has absolute determinant , therefore

Properties

Any Linear Transformation of Multi-variate Normal is Multi-variate Normal