tag:crantastic.org,2005:/packages/BSLLatest activity for BSL2019-07-10T07:40:32Zcrantastic.orgtag:crantastic.org,2005:TimelineEvent/904942019-07-10T07:40:32Z2019-07-10T07:40:32ZBSL was upgraded to version 3.0.0<a href="/packages/BSL">BSL</a> was <span class="action">upgraded</span> to version <a href="/packages/BSL/versions/86028">3.0.0</a><br /><h3>Package description:</h3><p>Bayesian synthetic likelihood (BSL, Price et al. (2018) <doi:10.1080/10618600.2017.1302882>) is an alternative to standard, non-parametric approximate Bayesian computation (ABC). BSL assumes a multivariate normal distribution for the summary statistic likelihood and it is suitable when the distribution of the model summary statistics is sufficiently regular. This package provides a Metropolis Hastings Markov chain Monte Carlo implementation of three methods (BSL, uBSL and semiBSL) and two shrinkage estimations (graphical lasso and Warton's estimation). uBSL (Price et al. (2018) <doi:10.1080/10618600.2017.1302882>) uses an unbiased estimator to the normal density. A semi-parametric version of BSL (semiBSL, An et al. (2018) <arXiv:1809.05800>) is more robust to non-normal summary statistics. Shrinkage estimations can help to bring down the number of simulations when the dimension of the summary statistic is high (e.g., BSLasso, An et al. (2019) <doi:10.1080/10618600.2018.1537928>). Extensions to this package are planned.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/836982019-01-16T09:00:36Z2019-01-16T09:00:36ZBSL was upgraded to version 2.0.0<a href="/packages/BSL">BSL</a> was <span class="action">upgraded</span> to version <a href="/packages/BSL/versions/79572">2.0.0</a><br /><h3>Package description:</h3><p>Bayesian synthetic likelihood (BSL, Price et al. (2018) <doi:10.1080/10618600.2017.1302882>) is an alternative to standard, non-parametric approximate Bayesian computation (ABC). BSL assumes a multivariate normal distribution for the summary statistic likelihood and it is suitable when the distribution of the model summary statistics is sufficiently regular. This package provides a Metropolis Hastings Markov chain Monte Carlo implementation of BSL, BSLasso and semiBSL. BSL with graphical lasso (BSLasso, An et al. (2018) <https://eprints.qut.edu.au/102263/>) is computationally more efficient when the dimension of the summary statistic is high. A semi-parametric version of BSL (semiBSL, An et al. (2018) <arXiv:1809.05800>) is more robust to non-normal summary statistics. Extensions to this package are planned.</p>crantastic.orgtag:crantastic.org,2005:TimelineEvent/729442018-03-23T14:20:28Z2018-03-23T14:20:28ZBSL was released<a href="/packages/BSL">BSL</a> was <span class="action">released</span><br /><h3>Package description:</h3><p>Bayesian synthetic likelihood (BSL, Price et al. (2018) <doi:10.1080/10618600.2017.1302882>) is an alternative to standard, non-parametric approximate Bayesian computation (ABC). BSL assumes a multivariate normal distribution for the summary statistic likelihood and it is suitable when the distribution of the model summary statistics is sufficiently regular. This package provides a Metropolis Hastings Markov chain Monte Carlo implementation of three methods (BSL, uBSL and semiBSL) and two shrinkage estimations (graphical lasso and Warton's estimation). uBSL (Price et al. (2018) <doi:10.1080/10618600.2017.1302882>) uses an unbiased estimator to the normal density. A semi-parametric version of BSL (semiBSL, An et al. (2018) <arXiv:1809.05800>) is more robust to non-normal summary statistics. Shrinkage estimations can help to bring down the number of simulations when the dimension of the summary statistic is high (e.g., BSLasso, An et al. (2019) <doi:10.1080/10618600.2018.1537928>). Extensions to this package are planned.</p>crantastic.org