Bayesian variable selection using cost-adjusted BIC, with application to cost-effective measurement of quality of health care

Fouskakis, D; Ntzoufras, I; Draper, D

dc.contributor.author	Fouskakis, D	en
dc.contributor.author	Ntzoufras, I	en
dc.contributor.author	Draper, D	en
dc.date.accessioned	2014-03-01T01:29:54Z
dc.date.available	2014-03-01T01:29:54Z
dc.date.issued	2009	en
dc.identifier.issn	1932-6157	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/19402
dc.subject	Bayesian information criterion (BIC)	en
dc.subject	Cost-adjusted BIC	en
dc.subject	Cost-benefit analysis	en
dc.subject	Input-output analysis	en
dc.subject	Laplace approximation	en
dc.subject	MCMC model composition (MC3)	en
dc.subject	Quality of health care	en
dc.subject	Reversible-jump Markov chain Monte Carlo (RJMCMC) methods	en
dc.subject	Sickness at hospital admission	en
dc.subject.other	PROSPECTIVE PAYMENT SYSTEM	en
dc.subject.other	GENERALIZED LINEAR-MODELS	en
dc.subject.other	STOCHASTIC OPTIMIZATION	en
dc.subject.other	PRIOR DISTRIBUTIONS	en
dc.subject.other	LINDLEY PARADOX	en
dc.subject.other	PERFORMANCE	en
dc.subject.other	PROVIDERS	en
dc.subject.other	INFERENCE	en
dc.subject.other	POLICY	en
dc.title	Bayesian variable selection using cost-adjusted BIC, with application to cost-effective measurement of quality of health care	en
heal.type	journalArticle	en
heal.identifier.primary	10.1214/08-AOAS207	en
heal.identifier.secondary	http://dx.doi.org/10.1214/08-AOAS207	en
heal.language	English	en
heal.publicationDate	2009	en
heal.abstract	In the field of quality of health care measurement, one approach to assessing patient sickness at admission involves a logistic regression of mortality within 30 days of admission on a fairly large number of sickness indicators (on the order of 100) to construct a sickness scale, employing classical variable selection methods to find an ""optimal"" subset of 10-20 indicators. Such ""benefit-only"" methods ignore the considerable differences among the sickness indicators in cost of data collection, an issue that is crucial when admission sickness is used to drive programs (now implemented or under consideration in several countries, including the U.S. and U.K.) that attempt to identify substandard hospitals by comparing observed and expected mortality rates (given admission sickness). When both data-collection cost and accuracy of prediction of 30-day mortality are considered, a large variable-selection problem arises in which costly variables that do not predict well enough should be omitted from the final scale. In this paper (a) we develop a method for solving this problem based on posterior model odds, arising from a prior distribution that (1) accounts for the cost of each variable and (2) results in a set of posterior model probabilities that corresponds to a generalized cost-adjusted version of the Bayesian information criterion (BIC), and (b) we compare this method with a decision-theoretic cost-benefit approach based on maximizing expected utility. We use reversible-jump Markov chain Monte Carlo (RJMCMC) methods to search the model space, and we check the stability of our findings with two variants of the MCMC model composition (MC3) algorithm. We find substantial agreement between the decision-theoretic and cost-adjusted-BIC methods; the latter provides a principled approach to performing a cost-benefit trade-off that avoids ambiguities in identification of an appropriate utility structure. Our cost-benefit approach results in a set of models with a noticeable reduction in cost and dimensionality, and only a minor decrease in predictive performance, when compared with models arising from benefit-only analyses. © Institute of Mathematical Statistics, 2009.	en
heal.publisher	INST MATHEMATICAL STATISTICS	en
heal.journalName	Annals of Applied Statistics	en
dc.identifier.doi	10.1214/08-AOAS207	en
dc.identifier.isi	ISI:000271979600008	en
dc.identifier.volume	3	en
dc.identifier.issue	2	en
dc.identifier.spage	663	en
dc.identifier.epage	690	en