Bayesian model averaging: a systematic review and conceptual classification. (English) Zbl 07763573
Summary: Bayesian model averaging (BMA) provides a coherent and systematic mechanism for accounting for model uncertainty. It can be regarded as an direct application of Bayesian inference to the problem of model selection, combined estimation and prediction. BMA produces a straightforward model choice criterion and less risky predictions. However, the application of BMA is not always straightforward, leading to diverse assumptions and situational choices on its different aspects. Despite the widespread application of BMA in the literature, there were not many accounts of these differences and trends besides a few landmark revisions in the late 1990s and early 2000s, therefore not accounting for advancements made in the last decades. In this work, we present an account of these developments through a careful content analysis of 820 articles in BMA published between 1996 and 2016. We also develop a conceptual classification scheme to better describe this vast literature, understand its trends and future directions and provide guidance for the researcher interested in both the application and development of the methodology. The results of the classification scheme and content review are then used to discuss the present and future of the BMA literature.
{© 2017 The Authors. International Statistical Review © 2017 International Statistical Institute}
{© 2017 The Authors. International Statistical Review © 2017 International Statistical Institute}
MSC:
| 62-XX | Statistics |
Keywords:
Bayesian model averaging; systematic review; conceptual classification scheme; qualitative content analysisReferences:
| [1] | Annest, A., Bumgarner, R.E, Raftery, A.E & Yeung, K.Y. (2009). Iterative bayesian model averaging: a method for the application of survival analysis to high‐dimensional microarray data. BMC Bioinf., 10(1), 1-72. |
| [2] | Arnold, R., Hayakawa, Y. & Yip, P. (2010). Capture-recapture estimation using finite mixtures of arbitrary dimension. Biometrics, 66(2), 644-655. · Zbl 1192.62251 |
| [3] | Baragatti, M. (2011). Bayesian variable selection for probit mixed models applied to gene selection. Bayesian Anal., 6(2), 209-229. · Zbl 1330.62297 |
| [4] | Barber, J.J, Gelfand, A.E & Silander, J.A (2006). Modelling map positional error to infer true feature location. Can. J. Stat., 34(4), 659-676. · Zbl 1115.62103 |
| [5] | Blattenberger, G., Fowles, R., Loeb, P.D. & Clarke, W.A (2012). Understanding the cell phone effect on vehicle fatalities: a bayesian view. Appl. Econ., 44(14), 1823-1835. |
| [6] | Boddhireddy, P., Kelly, M., Northcutt, S., Prayaga, K., Rumph, J. & DeNise, S. (2014). Genomic predictions in angus cattle: comparisons of sample size, response variables, and clustering methods for cross‐validation. J. Anim. Sci., 92(2), 485-497. |
| [7] | Boone, E.L, Simmons, S.J, Bao, H. & Stapleton, A.E (2008). Bayesian hierarchical regression models for detecting qtls in plant experiments. J. Appl. Stat., 35(7), 799-808. · Zbl 1169.62312 |
| [8] | Boone, E.L, Ye, K. & Smith, E.P (2005). Assessment of two approximation methods for computing posterior model probabilities. Comput. Stat. Data Anal., 48(2), 221-234. · Zbl 1429.62092 |
| [9] | Brown, P.J., Vannucci, M. & Fearn, T. (2002). Bayes model averaging with selection of regressors. J. R. Stat. Soc. Ser.B (Statistical Methodology), 64(3), 519-536. · Zbl 1073.62004 |
| [10] | Bunnin, F.O., Guo, Y. & Ren, Y. (2002). Option pricing under model and parameter uncertainty using predictive densities. Stat. Comput., 12(1), 37-44. · Zbl 1247.91181 |
| [11] | Cerquides, J. & De Mántaras, R.L. (2005). Tan classifiers based on decomposable distributions. Mach. Learn., 59(3), 323-354. · Zbl 1105.68091 |
| [12] | Chen, C.W., Liu, F.C. & Gerlach, R. (2011). Bayesian subset selection for threshold autoregressive moving‐average models. Comput. Stat., 26(1), 1-30. · Zbl 1304.65023 |
| [13] | Chib, S. (1995). Marginal likelihood from the Gibbs output. J. Am. Stat. Assoc., 90(432), 1313-1321. · Zbl 0868.62027 |
| [14] | Clyde, M. & George, E.I (2004). Model uncertainty. Stat. Sci., 19, 81-94. · Zbl 1062.62044 |
| [15] | Conti, D.V., Cortessis, V., Molitor, J. & Thomas, D.C (2003). Bayesian modeling of complex metabolic pathways. Hum. Heredity, 56(1‐3), 83-93. |
| [16] | Dash, D. & Cooper, G.F (2004). Model averaging for prediction with discrete Bayesian networks. The J. Mach. Learn. Res., 5, 1177-1203. · Zbl 1222.68178 |
| [17] | Eicher, T.S, Papageorgiou, C. & Raftery, A.E (2011). Default priors and predictive performance in Bayesian model averaging, with application to growth determinants. J. Appl. Econometrics, 26(1), 30-55. |
| [18] | Fernandez, C., Ley, E. & Steel, M.F.J. (2001a). Benchmark priors for Bayesian model averaging. J. Econometrics, 100(2), 381-427. · Zbl 1091.62507 |
| [19] | Fernandez, C., Ley, E. & Steel, M.F. (2001b). Model uncertainty in cross‐country growth regressions. J. Appl. Econometrics, 16(5), 563-576. |
| [20] | Fridley, B.L (2009). Bayesian variable and model selection methods for genetic association studies. Genet. Epidemiol., 33(1), 27-37. |
| [21] | Friedman, N. & Koller, D. (2003). Being Bayesian about network structure. A Bayesian approach to structure discovery in Bayesian networks. Mach. Learn., 50(1‐2), 95-125. · Zbl 1033.68104 |
| [22] | Friel, N. & Wyse, J. (2012). Estimating the evidence-a review. Stat. Neerlandica, 66(3), 288-308. |
| [23] | Friston, K., Mattout, J., Trujillo‐Barreto, N., Ashburner, J. & Penny, W. (2007). Variational free energy and the laplace approximation. Neuroimage, 34(1), 220-234. |
| [24] | Furnival, G.M & Wilson, R.W (1974). Regressions by leaps and bounds. Technometrics, 16(4), 499-511. · Zbl 0294.62079 |
| [25] | Garthwaite, P.H. & Mubwandarikwa, E. (2010). Selection of weights for weighted model averaging. Aust. & N. Z. J. Stat., 52(4), 363-382. · Zbl 1373.62099 |
| [26] | Gelfand, A.E. & Dey, D.K. (1994). Bayesian model choice: asymptotics and exact calculations. J. R. Stat. Soc. Ser. B (Methodological), 501-514. · Zbl 0800.62170 |
| [27] | Gelman, A. & Meng, X. (1998). Simulating normalizing constants: from importance sampling to bridge sampling to path sampling. Stat. Sci., 13, 163-185. · Zbl 0966.65004 |
| [28] | Gelman, A., Meng, X. & Stern, H. (1996). Posterior predictive assessment of model fitness via realized discrepancies. Stat. Sin., 6(4), 733-760. · Zbl 0859.62028 |
| [29] | George, E.I. & McCulloch, R.E. (1993). Variable selection via Gibbs sampling. J. Am. Stat. Assoc., 88(423), 881-889. |
| [30] | George, E.I. & McCulloch, R.E (1997). Approaches for Bayesian variable selection. Stat. Sin., 7(2), 339-373. · Zbl 0884.62031 |
| [31] | Geweke, J. (1999). Using simulation methods for Bayesian econometric models: inference, development, and communication. Econometric Rev., 18(1), 1-73. · Zbl 0930.62105 |
| [32] | Goenner, C.F. (2004). Uncertainty of the liberal peace. J. Peace Res., 41(5), 589-605. |
| [33] | Goenner, C.F. (2010). Discrimination and mortgage lending in Boston: the effects of model uncertainty. The J. Real Estate Finance Econ., 40(3), 260-285. |
| [34] | Green, P.J. (1995). Reversible jump Markov chain Monte Carlo computation and Bayesian model determination. Biometrika, 82(4), 711-732. · Zbl 0861.62023 |
| [35] | Guan, Y. & Stephens, M. (2011). Bayesian variable selection regression for genome‐wide association studies and other large‐scale problems. The Ann. Appl. Stat., 5, 1780-1815. · Zbl 1229.62145 |
| [36] | Guarín, A., González, A., Skandalis, D. & Sánchez, D. (2014). An early warning model for predicting credit booms using macroeconomic aggregates. Ensayos Sobre Política Económica, 32(SPE73), 77-86. |
| [37] | Habier, D., Tetens, J., Seefried, F., Lichtner, P. & Thaller, G. (2010). The impact of genetic relationship information on genomic breeding values in german holstein cattle. Genet. Sel. Evol., 42(1), 1-5. |
| [38] | Hachicha, W. & Ghorbel, A. (2012). A survey of control‐chart pattern‐recognition literature (1991-2010) based on a new conceptual classification scheme. Comput. Ind. Eng., 63(1), 204-222. |
| [39] | Hoeting, J.A., Madigan, D., Raftery, A.E. & Volinsky, C.T. (1999). Bayesian model averaging: a tutorial. Stat. Sci., 14, 382-401. · Zbl 1059.62525 |
| [40] | Hoeting, J.A., Raftery, A.E. & Madigan, D. (2002). Bayesian variable and transformation selection in linear regression. J. Comput. Graphical Stat., 11(3), 485-507. |
| [41] | Hsieh, H.‐F. & Shannon, S.E. (2005). Three approaches to qualitative content analysis. Qual. Health Res., 15(9), 1277-1288. |
| [42] | Jacobson, T. & Karlsson, S. (2004). Finding good predictors for inflation: a Bayesian model averaging approach. J. Forecasting, 23(7), 479-496. |
| [43] | Kadane, J.B & Lazar, N.A (2004). Methods and criteria for model selection. J. Am. Stat. Assoc., 99(465), 279-290. · Zbl 1089.62501 |
| [44] | Kass, R.E. & Raftery, A.E. (1995). Bayes factors. J. Am. Stat. Assoc., 90(430), 773-795. · Zbl 0846.62028 |
| [45] | King, R. & Brooks, S. (2001). On the Bayesian analysis of population size. Biometrika, 88(2), 317-336. · Zbl 1011.62030 |
| [46] | Kizilkaya, K., Fernando, R. & Garrick, D. (2010). Genomic prediction of simulated multibreed and purebred performance using observed fifty thousand single nucleotide polymorphism genotypes. J. Animal Sci., 88(2), 544-551. |
| [47] | Koop, G. & Potter, S. (2004). Forecasting in dynamic factor models using Bayesian model averaging. The Econometrics J., 7(2), 550-565. · Zbl 1063.62032 |
| [48] | Lamon, E.C. & Clyde, M.A. (2000). Accounting for model uncertainty in prediction of chlorophyll a in lake okeechobee. J. Agric. Biol. Environ. Stat., 5, 297-322. |
| [49] | Leamer, E.E. (1978). Specification Searches. Wiley: New York. · Zbl 0384.62089 |
| [50] | Liddle, A.R., Mukherjee, P., Parkinson, D. & Wang, Y. (2006). Present and future evidence for evolving dark energy. Phys. Rev. D, 74(12), 123506. |
| [51] | Lunn, D.J (2008). Automated covariate selection and Bayesian model averaging in population pk/pd models. J. Pharmacokinet. Pharmacodyn., 35(1), 85-100. |
| [52] | Madigan, D. & Raftery, A.E. (1994). Model selection and accounting for model uncertainty in graphical models using Occam’s window. J. Am. Stat. Assoc., 89(428), 1535-1546. · Zbl 0814.62030 |
| [53] | Madigan, D., York, J. & Allard, D. (1995). Bayesian graphical models for discrete data. Int. Stat. Rev./Revue Int. de Stat., 63, 215-232. · Zbl 0834.62003 |
| [54] | Mäntyniemi, S., Haapasaari, P., Kuikka, S., Parmanne, R., Lehtiniemi, M., Kaitaranta, J. & Hilborn, R. (2013). Incorporating stakeholders’ knowledge to stock assessment: central baltic herring. Can. J. Fish. Aquat.Sci., 70(4), 591-599. |
| [55] | Medvedovic, M. & Sivaganesan, S. (2002). Bayesian infinite mixture model based clustering of gene expression profiles. Bioinformatics, 18(9), 1194-1206. |
| [56] | Meuwissen, T.E., Hayes, B.J. & Goddard, M.E. (2001). Prediction of total genetic value using genome‐wide dense marker maps. Genetics, 157(4), 1819-1829. |
| [57] | Moher, D., Liberati, A., Tetzlaff, J. & Altman, D.G. (2009). Preferred reporting items for systematic reviews and meta‐analyses: the prisma statement. Ann. Internal Med., 151(4), 264-269. |
| [58] | Morales, K.H., Ibrahim, J.G., Chen, C.‐J. & Ryan, L.M. (2006). Bayesian model averaging with applications to benchmark dose estimation for arsenic in drinking water. J. Am. Stat. Assoc., 101(473), 9-17. · Zbl 1118.62373 |
| [59] | Newton, M.A. & Raftery, A.E. (1994). Approximate Bayesian inference with the weighted likelihood bootstrap. J. R. Stat. Soc. Ser. B (Methodological), 56, 3-48. · Zbl 0788.62026 |
| [60] | Oehler, V.G, Yeung, K., Choi, Y.E, Bumgarner, R.E, Raftery, A.E & Radich, J.P (2009). The derivation of diagnostic markers of chronic myeloid leukemia progression from microarray data. Blood, 114(15), 3292-3298. |
| [61] | Parkinson, D. & Liddle, A.R (2013). Bayesian model averaging in astrophysics: a review. Stat. Anal. Data Mining: The ASA Data Sci. J., 6(1), 3-14. · Zbl 07260349 |
| [62] | Penny, W.D, Stephan, K.E, Daunizeau, J., Rosa, M.J, Friston, K.J, Schofield, T.M & Leff, A.P (2010). Comparing families of dynamic causal models. PLoS Comput. Biol., 6(3), e1000709-e1000709. |
| [63] | Phelan, S., Liu, T., Gorin, A., Lowe, M., Hogan, J., Fava, J. & Wing, R.R. (2009). What distinguishes weight‐loss maintainers from the treatment‐seeking obese? Analysis of environmental, behavioral, and psychosocial variables in diverse populations. Ann. Behav. Med., 38(2), 94-104. |
| [64] | Plummer, M. (2003). Jags: a program for analysis of Bayesian graphical models using gibbs sampling. In Proceedings of the 3rd International Workshop on Distributed Statistical Computing, Vol. 124, pp. 1-125. Technische Universit at Wien. |
| [65] | Raftery, A.E. (1996). Approximate Bayes factors and accounting for model uncertainty in generalised linear models. Biometrika, 83(2), 251-266. · Zbl 0864.62049 |
| [66] | Raftery, A.E, Gneiting, T., Balabdaoui, F. & Polakowski, M. (2005). Using Bayesian model averaging to calibrate forecast ensembles. Mon. Weather Rev., 133(5), 1155-1174. |
| [67] | Raftery, A.E, Kárnỳ, M. & Ettler, P. (2010). Online prediction under model uncertainty via dynamic model averaging: application to a cold rolling mill. Technometrics, 52(1), 52-66. |
| [68] | Raftery, A.E & Painter, I.S (2005). BMA: an R package for Bayesian model averaging. R News, 5(2), 2-8. |
| [69] | Ranyimbo, A. & Held, L. (2006). Estimation of the false negative fraction of a diagnostic kit through Bayesian regression model averaging. Stat. Med., 25(4), 653-667. |
| [70] | Richardson, S. & Green, P.J. (1997). On Bayesian analysis of mixtures with an unknown number of components. J. R. Stat. Soc. Ser. B (Methodological), 59, 731-792. · Zbl 0891.62020 |
| [71] | Robert, C. & Casella, G. (2013). Monte Carlo Statistical Methods.Springer Science & Business Media: New York. |
| [72] | Roberts, H.V. (1965). Probabilistic prediction. J. Am. Stat. Assoc., 60(309), 50-62. · Zbl 0134.35802 |
| [73] | Sidman, A.H., Mak, M. & Lebo, M.J. (2008). Forecasting non‐incumbent presidential elections: lessons learned from the 2000 election. Int. J. Forecasting, 24(2), 237-258. |
| [74] | Silvestro, D., Zizka, G. & Schulte, K. (2014). Disentangling the effects of key innovations on the diversification of Bromelioideae (Bromeliaceae). Evolution, 68(1), 163-175. |
| [75] | Spiegelhalter, D.J, Thomas, A., Best, N.G & Gilks, W.R (1995). Bugs: Bayesian inference using Gibbs sampling, version 0.50. MRC Biostatistics Unit, Cambridge. |
| [76] | Swartz, M.D, Peterson, C.B, Lupo, P.J, Wu, X., Forman, M.R, Spitz, M.R, Hernandez, L.M, Vannucci, M. & Shete, S. (2013). Investigating multiple candidate genes and nutrients in the folate metabolism pathway to detect genetic and nutritional risk factors for lung cancer. Plos One, 8(1), 1-9. |
| [77] | Thomson, J.R, Mac Nally, R., Fleishman, E. & Horrocks, G. (2007). Predicting bird species distributions in reconstructed landscapes. Conserv. Biol., 21(3), 752-766. |
| [78] | Visweswaran, S., Angus, D.C, Hsieh, M., Weissfeld, L., Yealy, D. & Cooper, G.F (2010). Learning patient‐specific predictive models from clinical data. J. Biomed. Inf., 43(5), 669-685. |
| [79] | Volinsky, C.T., Madigan, D., Raftery, A.E. & Kronmal, R.A. (1997). Bayesian model averaging in proportional hazard models: assessing the risk of a stroke. J. R. Stat. Soc. Ser. C (Applied Statistics), 46(4), 433-448. · Zbl 0903.62093 |
| [80] | Vrontos, S.D., Vrontos, I.D. & Giamouridis, D. (2008). Hedge fund pricing and model uncertainty. J. Banking & Finance, 32(5), 741-753. |
| [81] | Wasserman, L. (2000). Bayesian model selection and model averaging. J. Math. Psychology, 44(1), 92-107. · Zbl 0946.62032 |
| [82] | Wintle, B.A, McCarthy, M.A, Volinsky, C.T & Kavanagh, R.P (2003). The use of Bayesian model averaging to better represent uncertainty in ecological models. Conserv. Biol., 17(6), 1579-1590. |
| [83] | Wu, C.‐H. & Drummond, A.J. (2011). Joint inference of microsatellite mutation models, population history and genealogies using transdimensional Markov chain Monte Carlo. Genetics, 188(1), 151-164. |
| [84] | Yeung, K.Y, Bumgarner, R.E. & Raftery, A.E (2005). Bayesian model averaging: development of an improved multi‐class, gene selection and classification tool for microarray data. Bioinformatics, 21(10), 2394-2402. |
| [85] | Yin, G. & Yuan, Y. (2009). Bayesian model averaging continual reassessment method in phase I clinical trials. J. Am. Stat. Assoc., 104(487), 954-968. · Zbl 1388.62008 |
| [86] | Zellner, A. (1986). On assessing prior distributions and bayesian regression analysis with g‐prior distributions. In Bayesian Inference and Decision Techniques: Essays in Honor of Bruno de Finetti, Ed. Zellner, A. (ed.), Amsterdam: North‐Holland. · Zbl 0655.62071 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
