[R] Generating a bivariate joint t distribution in R

[David Winsemius]

On Apr 2, 2013, at 11:07 PM, Jorge I Velez wrote:

> Dear Miao,
> 
> Check
> 
> require(MASS)
> ?mvrnorm
> 

Also package mvtnorm has both Normal and t versions of its p,q, r funtions

> for some ideas.
> 
> HTH,
> Jorge.-
> 
> 
> On Wed, Apr 3, 2013 at 4:57 PM, jpm miao <> wrote:
> 
>> Hi,
>> 
>>   I conduct a panel data estimation and obtain estimators for two of the
>> coefficients beta1 and beta2. R tells me the mean and covariance of the
>> distribution of (beta1, beta2). Now I would like to find the distribution
>> of the quotient beta1/beta2, and one way to do it is to simulate via the
>> joint distribution (beta1,  beta2), where both beta1 and beta2 follow t
>> distribution.
>> 
>>   How could we generate a joint t distrubuition in R?
>> 
>>   Thanks
>> 
>> Miao
> 


David Winsemius
Alameda, CA, USA