Image:LogDirichletDensity-alpha 0.3 to alpha 2.0.gif

From Wikipedia, the free encyclopedia

[edit] Summary

We illustrate the log of the density function:

\log (f(x_1,\dots, x_{K-1}; \alpha_1,\dots, \alpha_K)) = \log(\frac{1}{\mathrm{B}(\alpha)} \prod_{i=1}^K x_i^{\alpha_i - 1})
=  + \sum_{i=1}^K \alpha_i \log(x_i) - \sum_{i=1}^K \log(x_i) - \sum_{i=1}^K  \log(\Gamma(\alpha_i)) + \log(\Gamma(\sum_{i=1}^K \alpha_i))

for K = 3. In other words, we have two parameters x1,x2 varying on the two axes, and an implicit x3 = 1 − x1x2.

The picture illustrates the case where α1 = α2 = α3 = α and we vary over time the parameter α from 0.3 to 2.0.

[edit] Maple Code

The animated plot was generated using Maple 11, with the following code:


restart; 

with(plots);

B := (a1, a2, a3) -> (GAMMA(1.0*a1) * GAMMA(1.0*a2) * GAMMA(1.0*a3)) / GAMMA(1.0*a1+1.0*a2+1.0*a3);

f := (x1, x2, a1, a2, a3) ->  (x1^(a1-1)) * (x2^(a2-1)) * ( (1-x1-x2)^(a3-1)) /B(a1,a2,a3) ;

plotsetup(gif, plotoutput=`LogDirichletDensity-alpha_0.3_to_alpha_2.0.gif`); 

animate ( plot3d,  [eval(log(f(x1, x2, a1, a2, a3)), {a1=a, a2=a, a3=a}), x1=0.00..1, x2=0.00..1, 
axes=BOXED, grid=[25,25],gridstyle=triangular,orientation=[-135, 60], shading=zhue, contours=20, style=surfacecontour, view=-3..2 ],
a=0.3..2.0, frames=100);



[edit] Licensing

File history

Click on a date/time to view the file as it appeared at that time.

Date/TimeDimensionsUserComment
current04:10, 28 October 2007512×512 (3.35 MB)Ipeirotis (Talk | contribs) (== Summary == We illustrate the log of the density function: <math>\log (f(x_1,\dots, x_{K-1}; \alpha_1,\dots, \alpha_K)) = \log(\frac{1}{\mathrm{B}(\alpha)} \prod_{i=1}^K x_i^{\alpha_i - 1}) </math> for <math>K=3</math>. In other words, we have two par)

The following pages on the English Wikipedia link to this file (pages on other projects are not listed):