I'm using Monte Carlo simulation and samples come from a Binomial distribution. Importance sampling looks to be necessary based on the required number of samples. The question is how to choose the best parameters for sampling from a Binomial distribution in order to use importance sampling.
Dear Edielson,
I do not know exactly your problem.
In general there are, at least, two main classes of approaches:
- or use adaptive importance sampling; see
M. Bugallo, L. Martino, J. Corander, "Adaptive Importance Sampling in Signal Processing", Digital Signal Processing, Volume 47, Pages: 36-49, 2015.
-or use a population of proposal pdfs (importance functions); see
V. Elvira, L. Martino, D. Luengo, M. F. Bugallo, "Generalized Multiple Importance Sampling", arXiv:1511.03095, 2015
Alternatively, you can use a "random walk importance sampling", see reference
L. Martino, V. Elvira, D. Luengo, J. Corander, "Layered Adaptive Importance Sampling", Statistics and Computing (accepted; in press), 2016. arXiv:1505.04732
For any question please do not hesitate in contacting me,
Best regards,
Luca Martino
Thank you Luca Martino, I will take a look in the material and contact you for any doubt.
Best regards,
Edielson
If you need I can pass you some Matlab code or maybe even adapt it in some way
BR,
Luca
- Badges
- Science topic
- Similar topics
- Correction