analytic variance of a distribution

[n***@nowhere.net]

Hi there,

I am trying to calculate the analytic form of a non-standard
distribution but I am not sure how to do that.

Could someone please explain the method to derive the variance function
for a standard distribution and perhaps I can use the same method to do
a similar derivation for my distribution.

For example, if we consider the log-normal distribution:
P(x)=1/(x*sigma*(2pi^0.5))*exp(-log(x/m)^2/(2*sigma^2)) its variance
is: m^2*w*(w-1) where w=exp(sigma^2)

I am not sure how that is derived and I would appreciate any help or
pointers to some book or online tutorial.

Thank you in advance.

[Johan]

Hi,

Depending on what your distribution looks like you can do different things,
e.g. moment generating functions is one way to go.

/Johan

Post by n***@nowhere.net
Hi there,
I am trying to calculate the analytic form of a non-standard
distribution but I am not sure how to do that.
Could someone please explain the method to derive the variance function
for a standard distribution and perhaps I can use the same method to do
a similar derivation for my distribution.
P(x)=1/(x*sigma*(2pi^0.5))*exp(-log(x/m)^2/(2*sigma^2)) its variance
is: m^2*w*(w-1) where w=exp(sigma^2)
I am not sure how that is derived and I would appreciate any help or
pointers to some book or online tutorial.
Thank you in advance.