[R] fBasics package: dnig
xieyihui at gmail.com
Wed Sep 10 11:14:09 CEST 2008
Raj has mixed up the concept of "density function" with "CDF"
(Cumulative Distribution Function) - the former one doesn't need to be
smaller than 1, while the latter one is certainly no greater than 1.
On Wed, Sep 10, 2008 at 3:55 PM, Uwe Ligges
<ligges at statistik.tu-dortmund.de> wrote:
> Rajdeep Das wrote:
>> I am trying to calculate probability density of normal inverse gaussian
>> distribution. I am using dnig function of fBasics package. However, I am
>> getting following result. The density at x = 0.003042866 is:
>>> dnig(x= 0.003042866, alpha=5.184868, beta= 0.11841, delta= 0.06038513,
>>> mu= -0.0003520626)
>>  6.550251
>> I am not sure why it is 6.550251. Can anyone tell me why density is more
>> than 1? Thank you for your time.
> Without looking closer at the specific distribution: Why shouldn't it be
> more than 1? The density at x=0.25 of a uniform(a=0, b=0.5) distribution is
> 2 - hopefully.
> Uwe Ligges
Yihui Xie <xieyihui at gmail.com>
Phone: +86-(0)10-82509086 Fax: +86-(0)10-82509086
School of Statistics, Room 1037, Mingde Main Building,
Renmin University of China, Beijing, 100872, China
More information about the R-help