This question already has an answer here:

so I need to obtain the conditional distribution of a multivariate normal. However, I can only find it for the bivariate case:

$$(x_1|x_2=a) \sim N(\bar{\mu}, \bar{\Sigma})$$ $$\bar{\mu}= \mu_1 + \Sigma_{12}\Sigma_{22}^{-1}(a-\mu_2)$$ $$\bar{\Sigma}= \Sigma_{11}-\Sigma_{12}\Sigma_{22}^{-1}\Sigma_{21}$$

Here is the example given in more depth.

However, how would these formulas look like if I would have 3 or 4 variables instead of 2?

Edit: I would like the conditional for $(x_1| x_2=a,x_3=b)$ given I have mulitvariate distribution with 3 variables.


marked as duplicate by leonbloy, Lee David Chung Lin, Eevee Trainer, Shailesh, Alex Provost Mar 13 at 3:06

This question has been asked before and already has an answer. If those answers do not fully address your question, please ask a new question.


so the question was already answered and I just had issues with my Linear Algebra.

Here is the link:



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