I have been trying to undertsand predictive posterior distribution.The following expression is given here

$p(x^*|x)=\int_\Theta c\times p(x^*,\theta|x)d\theta=\int_\Theta c\times p(x^*|\theta)p(\theta|x)d\theta$

I understand that the conditional probability is defined as

$f(A|B)=\frac{f(A,B)}{f(B)} = \frac{f(B|A)*f(A)}{f(B)}$

Can someone explain how the predictive posterior distribution is written using conditional probability?

  • $\begingroup$ No, I am not able to understand how the expression for predictive posterior distribution is written $\endgroup$
    – Natasha
    Apr 20, 2018 at 17:13
  • 1
    $\begingroup$ What exactly is that you don't understand? The quote gives what you seem to be asking for. $\endgroup$
    – Tim
    Apr 20, 2018 at 18:40

1 Answer 1


You can compute the predictive posterior distribution as

$\begin{aligned} p(x^*|x) &= \int_{\Theta} p(x^*,\theta|x)d\theta \qquad ``\text{marginalizing out" }\theta\\ & = \int_{\Theta}p(x^*|\theta,x)p(\theta|x)d\theta \qquad \text{conditional probability rule: } P(A,B) = P(A|B) P(B)\\ &= \int_{\Theta}p(x^*|\theta)p(\theta|x)d\theta \qquad x^*\text{ is conditionally independent from }x \text{ given }\theta \end{aligned}$

where $p(\theta|x)$ is the posterior distribution of $\theta$.

The posterior predictive distribution will depend only on known quantities (the observed data $x$ and some prior's parameters).


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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