POSTERIOR PREDICTIVE ASSESSMENT OF MODEL FITNESS VIA REALIZED DISCREPANCIES

By Andrew Gelman, Xiao-Li Meng, Hal S. Stern. 1996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Bayesian model for repeated measures zero-inflated count data with application to outpatient psychiatric service use (2010, methodology): “A second approach is to conduct posterior predictive checks, in which the observed data are compared to data replicated from the posterior predictive distribution (Gelman et al., 1996).”
The Problem of Infra-marginality in Outcome Tests for Discrimination (2016, background): “Such posterior predictive checks (Gelman et al., 2014, 1996) are a common approach for identifying and measuring systematic differences between a fitted Bayesian model and the data.”
Beyond subjective and objective in statistics (2015, methodology): “Hierarchical models and Bayesian inference are often used to manage the many levels of variation and uncertainty (see, for example, Sheiner (1984) and Gelman et al. (1996)).”
Scalable Recommendation with Hierarchical Poisson Factorization (2015, methodology): “We conﬁrmed this in Section 3 using a posterior predictive check [10].”
Toward Distribution Estimation under Local Differential Privacy with Small Samples (2018, methodology): “We may also be able to choose a better α by extending our method to the Bayesian framework in the same way as [19].”
Shape restricted regression with random Bernstein polynomials (2007, methodology): “[14] and Gelman [13]; in fact, we have implemented this assessment and found it quite satisfactory.”
Robust Demographic Inference from Genomic and SNP Data (2013, unknown): “One would ideally like to assess how well the model explains the data, which is usually done by some posterior predictive check in a Bayesian setting [77], or by getting the data p-value under a frequentist approach.”
Fast Threshold Tests for Detecting Discrimination (2017, background): “We further conﬁrm that these inferred parameters capture key features of the data by performing posterior predictive checks (Gelman et al., 1996).”
Bayesian Model Assessment Using Pivotal Quantities (2007, methodology): “Perhaps in response to this problem, Guttman (1967) and Rubin (1984) proposed model diagnostics based on posterior-predictive distributions, which were later extended to general discrepancy functions by Gelman, Meng, and Stern (1996) (see also Meng (1994) for accompanying theory).”
Using a Bayesian latent growth curve model to identify trajectories of positive affect and negative events following myocardial infarction. (2005, unknown): “Finally, to determine if the number of classes is too small, we use posterior predictive checks (Gelman et al., 1996): replicated data generated under the model is compared to the observed data for evidence of model failure.”