Almintas2l

## Answered question

2022-07-17

Mathematically prove that a Beta prior distribution is conjugate to a Geometric likelihood function
I have to prove with a simple example and a plot how prior beta distribution is conjugate to the geometric likelihood function. I know the basic definition as
'In Bayesian probability theory, a class of distribution of prior distribution θ is said to be the conjugate to a class of likelihood function $f\left(x|\theta \right)$ if the resulting posterior distribution is of the same class as of $f\left(\theta \right)$.'
But I don't know how to prove it mathematically.

### Answer & Explanation

Kendrick Jacobs

Beginner2022-07-18Added 16 answers

Step 1
Find $f\left(x|\theta \right)$. Using Bayes theorem we know that $f\left(x|\theta \right)=Cf\left(\theta |x\right)f\left(\theta \right)$. C is just a normalisation constant to make it integrate to 1.
$f\left(\theta \right)$ is the PDF of the prior distribution. I.e. beta distribution (with some parameters $\left(\alpha ,\beta \right)$). Here $f\left(\theta \right)={C}^{\prime }{\theta }^{\alpha -1}\left(1-\theta {\right)}^{\beta -1}$
$f\left(\theta |x\right)$ is the likelihood function for $\theta$ given that the data x is distributed by a geometric distribution with parameter $\theta$. Our geometric likelihood function is $f\left(\theta |x\right)=\prod _{i=0}^{n}\left(1-\theta {\right)}^{{x}_{i}}\theta =\left(1-\theta {\right)}^{\sum _{i=0}^{n}{x}_{i}}{\theta }^{n}$.
Step 2
Now were going to find the product of these and we expect it will have the same form as the beta prior but with new parameters ${\alpha }^{\prime },{\beta }^{\prime }$, and we will find the parameters.
So $f\left(\theta |x\right)f\left(\theta \right)={C}^{\prime }{\theta }^{\alpha +n-1}\left(1-\theta {\right)}^{\sum _{i=0}^{n}{x}_{i}+\beta -1}$. We can see the new parameters are ${\alpha }^{\prime }=\alpha +n$, and ${\beta }^{\prime }=\sum _{i=0}^{n}{x}_{i}+\beta$. Mission accomplished.

Do you have a similar question?

Recalculate according to your conditions!

Ask your question.
Get an expert answer.

Let our experts help you. Answer in as fast as 15 minutes.

Didn't find what you were looking for?