If $(x_1,\cdots, x_n)$ is a sample from a Poisson(θ) distribution, where $θ ∈ (0,∞)$ is unknown, then determine the $MLE$ of $θ$.

my attempt:

so the probability density of poisson is

$$p_{\theta}(x) = \frac{\theta^x e^{-\theta}}{x!}$$

the likelihood is given by

$L(\theta | \bar{x}) = \prod_{i=1}^{n} \frac{\theta^{x_i}e^{-\theta}}{x_i!} = e^{-n\theta} \left(\prod_{i=1}^{n} \frac{1}{x_i!} \right) \theta^{\sum_{i=1}^{n}x_i}$

How do I do the factorial ?

For some reason in the solution their answer is just $e^{-n\theta} \theta^{\sum_{i=1}^{n}x_i}$ ?


1 Answer 1


The factorial part is a (positive) constant (with respect to the parameter $\theta$), so when maximising the likelihood with respect to $\theta$, it can be ignored. (It is still technically part of the likelihood though.)

It's like if you wanted to find $\theta$ to maximise a function $5f(\theta)$, it's the same as just finding the maximiser of $f(\theta)$ (since $5$ is a positive constant).

(Remember, when we find maximum likelihood estimators, we maximise the likelihood or log-likelihood with respect to the parameter $\theta$, and treat the $x_i$ as constants.)


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.