R help - Dec 2012 - Theoretical confidence regions for any non-symmetric bivariate statistical distributions

Respected R Users,

I looking for help with generating theoretical confidence regions for any
of non-symmetric bivariate statistical distributions (bivariate Chi-squared
distribution<Wishart distribution>, bivariate F-distribution, or any of
the
others). I want to to used it as a benchmark to compare a few strategies
constructing confidence regions for non-symmetric bivariate data.

There is a paper proposed an accumulative function for bivaraite
F-Distribution, but it was basically oriented for "one-tail" testing.
I
understand that it is nonsense to consider two-tails of F or Chi^2
distribution in most cases. But we may still need to know the confidence
intervals of a estimate following the distributions in some situations.
Thereby, please forget the necessity of the question itself.  In one word,
my question is: for two variables x and y, which are following chi^2
distributions (df=4), independently, what is the theoretical confidence
region of the joint distribution of x,y for a given alpha? Since the issues
has already beyond my research area, please let me know if my descriptions
are confusing. Numeric strategies are also welcomed for the issue.

I appropriate your kindly help with the matter.

Best regards,

Zhiqiu

	[[alternative HTML version deleted]]

What does this have to do with R?

Post on a statistical list (like stats.stackexchange.com).

I would urge respondents here to reply privately.

-- Bert

On Wed, Dec 19, 2012 at 1:08 PM, Zhiqiu Hu <zhiqiu.hu@gmail.com> wrote:
> Respected R Users,
>
> I looking for help with generating theoretical confidence regions for any
> of non-symmetric bivariate statistical distributions (bivariate Chi-squared
> distribution<Wishart distribution>, bivariate F-distribution, or any
of the
> others). I want to to used it as a benchmark to compare a few strategies
> constructing confidence regions for non-symmetric bivariate data.
>
> There is a paper proposed an accumulative function for bivaraite
> F-Distribution, but it was basically oriented for "one-tail"
testing. I
> understand that it is nonsense to consider two-tails of F or Chi^2
> distribution in most cases. But we may still need to know the confidence
> intervals of a estimate following the distributions in some situations.
> Thereby, please forget the necessity of the question itself.  In one word,
> my question is: for two variables x and y, which are following chi^2
> distributions (df=4), independently, what is the theoretical confidence
> region of the joint distribution of x,y for a given alpha? Since the issues
> has already beyond my research area, please let me know if my descriptions
> are confusing. Numeric strategies are also welcomed for the issue.
>
> I appropriate your kindly help with the matter.
>
> Best regards,
>
> Zhiqiu
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>


-- 

Bert Gunter
Genentech Nonclinical Biostatistics

Internal Contact Info:
Phone: 467-7374
Website:
http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm

	[[alternative HTML version deleted]]