0
$\begingroup$

I have a random variable, $X$, that follows a population distribution of the Poisson type, $Po(\lambda)$, with an unknown $\lambda$ parameter. In an experiment, $k=100$ events were measured in a given time interval, each event having a very small probability to happen. I want to estimate the population value of $\lambda$ using the $k$ we found to estimate it, $\hat\lambda=k$. How can I apply the Central Limit Theorem to find the sample distribution of this estimator?

$\endgroup$
2
$\begingroup$

$\hat{k}$ is the number of events in the considered time interval $[0, T]$ i.e., $$ \hat{k} = \sum_{i=1}^{T - \Delta t}I[t_i \le X_i \le t_i+\Delta t] = \sum_{i=1}^nI_i, $$ where $\Delta t = 1/T$, so by the CLT $$ T^{-1/2}\left(\sum^T I_i - \mathbb{E}\sum^T I_i\right) \xrightarrow{D} N(0, \operatorname{var}(I_i)), $$ where $ \operatorname{var}(I_i) = \lambda \Delta t = \lambda/T$. As such, the sample distribution is given by $$ \hat{k} \sim^{approx.} N(\lambda, \lambda). $$

$\endgroup$
  • $\begingroup$ Thanks, V. Vancak $\endgroup$ – Quaerendo May 16 '18 at 8:47

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.