Beefy Boxes and Bandwidth Generously Provided by pair Networks
laziness, impatience, and hubris
 
PerlMonks  

Re: Simulating uni-dimensional Hawkes processes

by frozenwithjoy (Curate)
on Feb 18, 2013 at 04:13 UTC ( #1019270=note: print w/ replies, xml ) Need Help??


in reply to Simulating uni-dimensional Hawkes processes

Can you give us both the expected and the actual outputs for a set of "random" numbers? Thanks.


Comment on Re: Simulating uni-dimensional Hawkes processes
Replies are listed 'Best First'.
Re^2: Simulating uni-dimensional Hawkes processes
by glrm_master (Initiate) on Feb 18, 2013 at 19:36 UTC

    Hi forzenwithjoy, and thanks for your time!

    I'm not sure I understand what you are asking me for. The code is supposed to generate a sequence of "arrival times" that are supposed to be produced by a self-exciting point process with lambda as its intensity function... in order to do so, i generate some arrival times and then perform an Acceptance/Rejection of sorts that will drop some of them (with a certain probability) and generate new ones... i usually let the loop run about 10,000 or 50,000 times and than feed the generated arrival times into MLE estimation to get "back" the values of my 3 parameters: alpha, beta and lambda0 (the base intensity)... for beta and alpha i get very cloes MLE estimates while the estimate for lambda0 is ALWAYS well off... this is my problem... what kind of outputs would you like me to show you??

    thanks a lot for your help! take care!

    kris

Log In?
Username:
Password:

What's my password?
Create A New User
Node Status?
node history
Node Type: note [id://1019270]
help
Chatterbox?
and the web crawler heard nothing...

How do I use this? | Other CB clients
Other Users?
Others meditating upon the Monastery: (5)
As of 2015-07-28 05:17 GMT
Sections?
Information?
Find Nodes?
Leftovers?
    Voting Booth?

    The top three priorities of my open tasks are (in descending order of likelihood to be worked on) ...









    Results (252 votes), past polls