st: RE: Re: statalist-digest V4 #3783

["Nick Cox" <n.j.cox@durham.ac.uk>]

There is no problem except one of understanding. A density is not a
probability and so may easily exceed 1. 

Consider x that is uniform on [0, 0.5]. The density must integrate to 1
over this interval and clearly must also be constant. No calculus is
needed in this example as 

area under density function = 1 = Constant density of ? * length of
support of 0.5. 

which can be solved to get a density of 2. 

Nick 
n.j.cox@durham.ac.uk 

Katja Hillmann

I used the command kdensity in order to calculate the density of 
fractions (e.g. number of longterm unemployed on total unemployment). 
Thus I try to calculate the denisty of values less than 1. However, the 
values of the densities Stata provided are all greater than 1. Where is 
the problem? Does Stata have problems in calculating distributions of 
variables within an intervall of 0 and 1?


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/