Likelihood-free approximate Gibbs sampling
From MaRDI portal
Abstract: Likelihood-free methods such as approximate Bayesian computation (ABC) have extended the reach of statistical inference to problems with computationally intractable likelihoods. Such approaches perform well for small-to-moderate dimensional problems, but suffer a curse of dimensionality in the number of model parameters. We introduce a likelihood-free approximate Gibbs sampler that naturally circumvents the dimensionality issue by focusing on lower-dimensional conditional distributions. These distributions are estimated by flexible regression models either before the sampler is run, or adaptively during sampler implementation. As a result, and in comparison to Metropolis-Hastings based approaches, we are able to fit substantially more challenging statistical models than would otherwise be possible. We demonstrate the sampler's performance via two simulated examples, and a real analysis of Airbnb rental prices using a intractable high-dimensional multivariate non-linear state space model containing 13,140 parameters, which presents a real challenge to standard ABC techniques.
Recommendations
Cites work
- scientific article; zbMATH DE number 3297735 (Why is no real title available?)
- A comparative review of dimension reduction methods in approximate Bayesian computation
- A rare event approach to high-dimensional approximate Bayesian computation
- Approximate Bayesian Computation for Smoothing
- Approximate Bayesian computation: a nonparametric perspective
- Bayesian analysis of regression problems
- Bayesian dynamic Dirichlet models
- Bayesian forecasting and dynamic models.
- Bayesian indirect inference using a parametric auxiliary model
- Bayesian optimization for likelihood-free inference of simulator-based statistical models
- Behaviour of the Gibbs sampler when conditional distributions are potentially incompatible
- Conditional specification of statistical models.
- Constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation. With discussion and authors' reply
- Coupling stochastic EM and approximate Bayesian computation for parameter inference in state-space models
- Diagnostic tools for approximate Bayesian computation using the coverage property
- Dynamic Bayesian beta models
- Dynamic Generalized Linear Models and Bayesian Forecasting
- Dynamic Linear Models with R
- Expectation propagation for likelihood-free inference
- Extending approximate Bayesian computation methods to high dimensions via a Gaussian copula model
- Filtering via approximate Bayesian computation
- Fully conditional specification in multivariate imputation
- Functional regression approximate Bayesian computation for Gaussian process density estimation
- Likelihood-free Bayesian estimation of multivariate quantile distributions
- Noisy Monte Carlo: convergence of Markov chains with approximate transition kernels
- Numerical maximum likelihood estimation for the \(g\)-and-\(k\) and generalized \(g\)-and-\(h\) distributions
- Parameter estimation for hidden Markov models with intractable likelihoods
- Parameterization and Bayesian Modeling
- Piecewise approximate Bayesian computation: fast inference for discretely observed Markov models using a factorised posterior distribution
- Recalibration: a post-processing method for approximate Bayesian computation
- Sequential Monte Carlo without likelihoods
- The pseudo-marginal approach for efficient Monte Carlo computations
- Variational Bayes with synthetic likelihood
Cited in
(5)
This page was built for publication: Likelihood-free approximate Gibbs sampling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2195848)
