Likelihoodfree inference and approximate Bayesian computation for stochastic modelling
(2013) FMS820 20132Mathematical Statistics
 Abstract (Swedish)
 With increasing model complexity, sampling from the posterior distribution in a Bayesian context
becomes challenging. The reason might be that the likelihood function is analytically unavailable or
computationally costly to evaluate. In this thesis a fairly new scheme called approximate Bayesian
computation is studied which, through simulations from the likelihood function, approximately
simulates from the posterior. This is done mainly in a likelihoodfree Markov chain Monte Carlo
framework and several issues concerning the performance are addressed. Semiautomatic ABC,
producing nearsucient summary statistics, is applied to a hidden Markov model and the same
scheme is then used, together with a varying bandwidth, to make... (More)  With increasing model complexity, sampling from the posterior distribution in a Bayesian context
becomes challenging. The reason might be that the likelihood function is analytically unavailable or
computationally costly to evaluate. In this thesis a fairly new scheme called approximate Bayesian
computation is studied which, through simulations from the likelihood function, approximately
simulates from the posterior. This is done mainly in a likelihoodfree Markov chain Monte Carlo
framework and several issues concerning the performance are addressed. Semiautomatic ABC,
producing nearsucient summary statistics, is applied to a hidden Markov model and the same
scheme is then used, together with a varying bandwidth, to make inference on a real data study
under a stochastic LotkaVolterra model. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/studentpapers/record/4066642
 author
 Nilsson, Oskar
 supervisor

 Umberto Picchini ^{LU}
 organization
 course
 FMS820 20132
 year
 2013
 type
 H2  Master's Degree (Two Years)
 subject
 language
 English
 id
 4066642
 date added to LUP
 20130930 11:43:22
 date last changed
 20130930 11:43:22
@misc{4066642, abstract = {With increasing model complexity, sampling from the posterior distribution in a Bayesian context becomes challenging. The reason might be that the likelihood function is analytically unavailable or computationally costly to evaluate. In this thesis a fairly new scheme called approximate Bayesian computation is studied which, through simulations from the likelihood function, approximately simulates from the posterior. This is done mainly in a likelihoodfree Markov chain Monte Carlo framework and several issues concerning the performance are addressed. Semiautomatic ABC, producing nearsucient summary statistics, is applied to a hidden Markov model and the same scheme is then used, together with a varying bandwidth, to make inference on a real data study under a stochastic LotkaVolterra model.}, author = {Nilsson, Oskar}, language = {eng}, note = {Student Paper}, title = {Likelihoodfree inference and approximate Bayesian computation for stochastic modelling}, year = {2013}, }