5
$\begingroup$

What are the probability density function and cumulative distribution function of a compound triangular distribution with uniformly distributed mode, both supported on $(-a, a)$? I.e.,

$$ m \sim \mathrm{Unif}(-a, a) \\ X \sim \mathrm{Triang}(-a, a, m) $$

Does it have a name?

It is not a Wigner semicircle distribution and it is close to a scaled, shifted beta distribution with $\alpha = \beta \approx 1.75$, but I'm interested in whether it has a simple closed form.

$\endgroup$
  • 2
    $\begingroup$ Yes, the PDF and CDF have closed forms. Indeed, for $a=1$ (which loses no generality, since $a$ is a scale parameter) its cf can be written in terms of cosine and sine integrals as $${4 t^2}\psi(t)={e^{-i t} \left(2 \left(1+e^{2 i t}\right) \text{Ci}(2 t)+4 e^{i t} \text{Si}(2 t) \sin (t)+\log \left(-\frac{i}{t}\right) \\ -\log \left(-\frac{2 i}{t}\right)+\log (2 i t)-\log (4 i t)-2 (\log (t)+\gamma )-2 e^{2 i t} (\log (t)+\gamma +\log (2))\right)}$$ From that you can extract the moments. $\endgroup$ – whuber Dec 9 '16 at 17:08
5
$\begingroup$

Given: $X \sim \text{Triangular}(-a,m,a)$ with pdf $f(x)$:


(source: tri.org.au)

where parameter $m$, instead of being fixed, is itself a random variable. In particular, $M \sim \text{Uniform}(-a,a)$, with pdf $g(m)$:


(source: tri.org.au)

Then, we seek the parameter mixture distribution $E_{g }\big[\;f (x \; \big | \;M =m )\big]$, which has pdf say $h(x)$:


(source: tri.org.au)

where I am using the Expect function from the mathStatica package for Mathematica to automate the calculation. The domain of support is, of course, $(-a,a)$.

To illustrate, here is a plot of the pdf $h(x)$, as parameter $a$ varies:


(source: tri.org.au)

The cdf $P_h(X<x)$ is:


(source: tri.org.au)

Comparison to semi-circle distribution

The following diagram compares the pdf of the exact solution $h(x)$ to the semicircle pdf that the OP refers to. The pdf $h(x)$ is somewhat more peaked than the semi-circle:


(source: tri.org.au)

Comparison to POWER semi-circle distribution

While the functional form is different, one can approximate the pdf $h(x)$ extremely well with a power semi-circle distribution of form:

$$ \phi(x) = k \left(a^2-x^2\right)^{3/4}$$

where $k = \frac{\Gamma \left(\frac{9}{4}\right)}{\left(\sqrt{\pi } a^{5/2}\right) \Gamma \left(\frac{7}{4}\right)}$

The fit is so good that one can barely see any perceptible difference:


(source: tri.org.au)

| cite | improve this answer | |
$\endgroup$
  • 2
    $\begingroup$ +1. Note that the "power semi-circle distribution" is a shifted rescaled Beta$(7/4,7/4)$ distribution. $\endgroup$ – whuber Dec 9 '16 at 23:26

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.