Re: poisson distribution



"miki lo" <myartsev@xxxxxxxxx> writes:

> I am very sorry to disturb you but I still can't seem to understand
> this code fully, I will try to be more specific this time about what
> I don't understand:
> We create a a vector of Poisson distribution by using the command:
> t = poissrnd(lambda,[1,2*n/lambda]);
> This I understand, but then we use the command:
> t = 1+cumsum(t);
> I looked at the help and I understand what it does, and I
> guess and please correct me if I am wrong, that the purpose of this
> command is simply to organize the numbers by using the fact that any
> sum of Poisson distributed numbers are also Poisson distributed?
> &#61656; Although I didn't understand what you meant when you said: "
> So interarrival times of [1 2 3 4] actually arrive at actual times of
> [1 3 6 10]."
> What does it mean "actually arrive"???
> I just don't understand why do we accumulate arrivals?
> you very much and sorry for the trouble

I still think you are really looking for a poisson process. That is,
a vector which has events distributed according to the poisson
distribution. NOT events with poisson interarrival times, which is
what you asked for and what John gave you. It would be an odd
application to that truly called for poisson interarrivals, rather
than exponential interarrivals and poisson events.

The cumsum above is what turns interarrival times into actual arrival
times. Each entry the input vector is the time from one event to the
next. Say [1 2 3 4]. So the time from the first to the second is 1.
The time from the second to the third is 2. That makes the actual
arrival time of the third event = 3. (1+2) This is what is necessary
if you describe the statistics of the interarrival times of the events.



--
Peter Boettcher <boettcher@xxxxxxxxxx>
MIT Lincoln Laboratory
MATLAB FAQ: http://www.mit.edu/~pwb/cssm/
.



Relevant Pages

  • Re: poisson distribution
    ... >> average 10 cells and I want it to be poisson distributed, ... I tried looking at the poisson distribution onmatlab but ... The interarrival times of these events are exponentially distributed. ...
    (comp.soft-sys.matlab)
  • Re: Distribution of a vowel on the page
    ... times a vowel occurs on a line follows Poisson distribution or not. ... vowels and consonants in words violate that assumption. ... It occurs to me that if there is a positive correlation of having ...
    (sci.stat.math)
  • Re: Distribution of a vowel on the page
    ... times a vowel occurs on a line follows Poisson distribution or not. ... There are two reasons that the number of vowels on a line ... It occurs to me that if there is a positive correlation of having ...
    (sci.stat.math)
  • Re: Moving the Islands within Sequence Space
    ... Poisson distribution. ... I'm using a Poisson distribution." ... how RM/NS is capable of doing the job. ... And it is not an assumption that the pattern of sequence ...
    (talk.origins)
  • Re: Moving the Islands within Sequence Space
    ... Poisson distribution. ... Mr. Stockwell did not tell you that a Poisson ... I'm using a Poisson distribution." ... Why, again, can't 3 different sequences of 333 ...
    (talk.origins)