3
$\begingroup$

In Poisson distribution, the probability of inter arrival time to be t or less is:

$$ P(X\leq t)= 1 - P(X>t) = 1 - P(0 \mbox{ arrivals in } t) = 1 - e^{-\lambda t} $$

and probability of one arrival in t is:

$$ P(k=1)= \lambda t e^{- \lambda t} $$

I wonder how the exponential distribution can be derived from Poisson to reach:

$$ P(X\leq t)= \lambda e^{- \lambda t} $$

Thanks,

$\endgroup$
  • 2
    $\begingroup$ By $P(X \leq t) = 1 - e^{-\lambda t}$, $t \geq 0$, $X$ is indeed exponential, and its density function is given by $\frac{d}{{dt}}(1 - e^{ - \lambda t} ) = \lambda e^{ - \lambda t} $, $t \geq 0$. $\endgroup$ – Shai Covo Jan 25 '11 at 12:37
  • 1
    $\begingroup$ @Shai: you should move your comment to an aswer $\endgroup$ – leonbloy Jan 25 '11 at 15:38
5
$\begingroup$

Suppose that $N = \{N_t: t \geq 0 \}$ is a Poisson process with rate $\lambda$. Let $X$ be the waiting time until the first occurrence in the process $N$. Then, for any $t > 0$, $$ {\rm P}(X \le t) = 1 - {\rm P}(X > t) = 1 - {\rm P}(N_t = 0) = 1 - e^{ - \lambda t}. $$ Hence, $X$ is an exponential random variable with density function $f_X$ given by $$ f_X {(t)} = \frac{{\rm d}}{{{\rm d}t}}(1 - e^{ - \lambda t} ) = \lambda e^{-\lambda t},\;\; t > 0. $$

$\endgroup$

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.