Skip to content

Generating Heavy and Light Tailed Normal Variates

4 messages · Dan Abner, Bert Gunter

Original
Dan Abner
# 
Hi all,

I need to generate heavy and light-tailed normal variates separately for
demonstration purposes. I figure for the heavy-tailed, I will just generate
variates from a t distribution with low degrees of freedom. How does one
generate light-tailed normal variates?

Thanks,

Dan
Bert Gunter
# 
There is no such thing as "heavy and light tailed normal variates."
The normal distribution is normal, period.

Ask this on stats.stackexchange.com. It is about statistics not R, and
a sensible answer heavily depends on the context you have in mind.

Cheers,
Bert




Bert Gunter

"The trouble with having an open mind is that people keep coming along
and sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )
On Fri, Dec 16, 2016 at 6:45 AM, Dan Abner <dan.abner99 at gmail.com> wrote:
Dan Abner
# 
Hi Bert,

Thank you for the response. Let me re-phrase:

What is the most efficient way to generate variates from a unimodal
symmetric distribution that are leptokurtic or platykurtic in R? There does
not appear to be a kurtosis parameter for rnorm().

Thanks all,

Dan

On Fri, Dec 16, 2016 at 10:15 AM, Bert Gunter <bgunter.4567 at gmail.com>
wrote:

  
  


  


      

    

    

      
      

        


  

        

      Bert Gunter
    

    

      
      #
    

  


  

      
Sorry, but you need to do some studying of statistical theory. The
normal/Gaussian distribution has a fixed kurtosis of 3.0. **There is
no kurtosis parameter.**

Again, this is not the place for such discussions.

-- Bert




Bert Gunter

"The trouble with having an open mind is that people keep coming along
and sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )

        
On Fri, Dec 16, 2016 at 8:09 AM, Dan Abner <dan.abner99 at gmail.com> wrote: