> David Winsemius
> on Tue, 9 May 2017 14:33:04 -0700 writes:
>> On May 9, 2017, at 2:05 PM, Czarek Kowalski
wrote:
>>
>> I have already posted that in attachement - pdf file.
> I see that now. I failed to scroll to the 3rd page.
from a late reader:
Please, Czare
> On May 10, 2017, at 11:02 AM, Czarek Kowalski wrote:
>
> Previously I had used another language to make calculations based on
> theory. I have calculated using R and I have received another results.
> My theoretical calculation does not take into account the full
> covariance matrix (only 6 el
It's not obvious to me that that marginal distribution of one component of a
multivariate truncated t is the corresponding univariate truncated t.
In fact, I would expect it to differ because of tail-dependence effects, e.g.
> r <- rtmvt(1e5, c(30,0), diag(2), lower=c(29,-Inf), upper=c(31, +Inf)
Previously I had used another language to make calculations based on
theory. I have calculated using R and I have received another results.
My theoretical calculation does not take into account the full
covariance matrix (only 6 elements from diagonal). Code based on
theory:
df = 4; #degrees of
> On May 9, 2017, at 2:33 PM, David Winsemius wrote:
>
>
>> On May 9, 2017, at 2:05 PM, Czarek Kowalski wrote:
>>
>> I have already posted that in attachement - pdf file.
>
> I see that now. I failed to scroll to the 3rd page.
>
>> I am posting
>> plain text here:
>>
>>> library(tmvtnorm)
> On May 9, 2017, at 2:05 PM, Czarek Kowalski wrote:
>
> I have already posted that in attachement - pdf file.
I see that now. I failed to scroll to the 3rd page.
> I am posting
> plain text here:
>
>> library(tmvtnorm)
>> meann = c(55, 40, 50, 35, 45, 30)
>> covv = matrix(c( 1, 1, 0, 2, -1,
I have already posted that in attachement - pdf file. I am posting
plain text here:
> library(tmvtnorm)
> meann = c(55, 40, 50, 35, 45, 30)
> covv = matrix(c( 1, 1, 0, 2, -1, -1,
+ 1, 16, -6, -6, -2, 12,
+ 0, -6, 4, 2, -2, -5,
+ 2, -6, 2,
> On May 9, 2017, at 1:11 PM, Czarek Kowalski wrote:
>
> Of course I have expected the difference between theory and a sample
> of realizations of RV's and result mean should still be a random
> variable. But, for example for 4th element of mean vector: 35.31 -
> 34.69571 = 0.61429. It is quite
Of course I have expected the difference between theory and a sample
of realizations of RV's and result mean should still be a random
variable. But, for example for 4th element of mean vector: 35.31 -
34.69571 = 0.61429. It is quite big difference, nieprawdaĊĵ? I have
expected that the difference wo
> On May 9, 2017, at 10:09 AM, Czarek Kowalski wrote:
>
> Dear Members,
> I am working with 6-dimensional Student-t distribution with 4 degrees
> of freedom truncated to [20; 60]. I have generated 100 000 samples
> from truncated multivariate Student-t distribution using rtmvt
> function from pa
10 matches
Mail list logo
