The DOI matches its Crossref record; 306 of the 306 references it cites were found in a registry or an index.
Model Averaging and Its Use in Economics
Abstract
The method of model averaging has become an important tool to deal with model uncertainty, for example in situations where a large amount of different theories exist, as are common in economics. Model averaging is a natural and formal response to model uncertainty in a Bayesian framework, and most of the paper deals with Bayesian model averaging. The important role of the prior assumptions in these Bayesian procedures is highlighted. In addition, frequentist model averaging methods are also discussed. Numerical techniques to implement these methods are explained, and I point the reader to some freely available computational resources. The main focus is on uncertainty regarding the choice of covariates in normal linear regression models, but the paper also covers other, more challenging, settings, with particular emphasis on sampling models commonly used in economics. Applications of model averaging in economics are reviewed and discussed in a wide range of areas including growth economics, production modeling, finance and forecasting macroeconomic quantities. (JEL C11, C15, C20, C52, O47).
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Empirical work in these domain-specific areas is subject to significant uncertainty about model specification. This may be the consequence of the lack of a universally accepted theory that has been empirically verified as a (near) perfect explanation of reality (theory uncertainty), the multiple ways in which theories can be empirically tested (specification uncertainty), heterogeneity uncertainty”
From Modelling Motor Insurance Claim Frequency and Severity Using Gradient Boosting (2023) · cites this paper as Steel 2020
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing
Benjamini, Y., & Hochberg, Y. (1995) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1995.tb02031.x · Cited by 109,482 · cited 7×
“Comparisons of some methods (including the method by Benjamini and Hochberg (1995) aimed at controlling the false discovery rate) can be found in Deckers and Hanck (2014) in the context of cross-sectional growth regression.”
MethodInfluentialRegression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482 · cited 2×
“ed regression coefficients in the full model will be close to zero. A common classical method is penalized least squares, such as LASSO (least absolute shrinkage and selection operator), introduced by Tibshirani (1996), where the regression “fit” is maximized subject to a complexity penalty. Choosing a different penalty…”
MethodEstimating the Dimension of a Model
Schwarz, G. (1978) · The Annals of Statistics · doi:10.1214/aos/1176344136 · Cited by 47,033 · cited 2×
“The Bayesian information criterion (BIC) implies a stronger complexity penalty and was originally motivated through asymptotic equivalence with a Bayes factor (Schwarz, 1978).”
BackgroundMethodThe Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
The Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162
McCullagh, P., & Nelder, J. A. (1989) · doi:10.1007/978-1-4899-3242-6 · Cited by 16,836
Filders, R. (1992) · International Journal of Forecasting · doi:10.1016/0169-2070(92)90130-2 · Cited by 16,165
Kass, R. E., & Raftery, A. E. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476572 · Cited by 12,558
Economic Growth in a Cross Section of Countries
Barro, R. J. (1991) · The Quarterly Journal of Economics · doi:10.2307/2937943 · Cited by 9,263
Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
Fan, J., & Li, R. (2001) · Journal of the American Statistical Association · doi:10.1198/016214501753382273 · Cited by 8,900 · cited 3×
“Such approaches are e.g. the SCAD penalized regression of Fan and Li (2001) and adaptive LASSO methods as in Zou (2006).”
BackgroundMethodThe colonial origins of comparative development: An empirical investigation
Acemoglu, D., Johnson, S., & Robinson, J. A. (2001) · American Economic Review · doi:10.1257/aer.91.5.1369 · Cited by 8,517 · cited 4×
“w for a much more complete and nuanced inference from the data than the earlier studies, more adequately reflecting the uncertainty of any conclusions drawn. In addition, the instrument constructed by Acemoglu et al. (2001) has been criticised by Albouy (2012), due to the problems in obtaining reliable historical morta…”
BackgroundInfluentialThe adaptive lasso and its oracle properties
Zou, H. (2006) · Journal of the American Statistical Association · doi:10.1198/016214506000000735 · Cited by 7,470 · cited 2×
“Such approaches are e.g. the SCAD penalized regression of Fan and Li (2001) and adaptive LASSO methods as in Zou (2006).”
Method(2013) · American Economic Review · doi:10.1257/aer.103.6.i · Cited by 7,220
Bayesian model selection in social research
Raftery, A. E. (1995) · Sociological Methodology · doi:10.2307/271063 · Cited by 6,823 · cited 10×
“It has long been understood that the effect of the prior distribution on posterior model probabilities can be much more pronounced than its effect on posterior inference given a model (Kass and Raftery, 1995; Fernández et al., 2001a).”
BackgroundMethodResultInfluentialReversible jump Markov chain Monte Carlo computation and Bayesian model determination
GREEN, P. J. (1995) · Biometrika · doi:10.1093/biomet/82.4.711 · Cited by 5,930
Strictly Proper Scoring Rules, Prediction, and Estimation
Gneiting, T., & Raftery, A. E. (2007) · Journal of the American Statistical Association · doi:10.1198/016214506000001437 · Cited by 5,793 · cited 5×
“CRPS was found in Gneiting and Raftery (2007) to be less sensitive to outliers than LPS and was introduced in the context of growth regressions by Eicher et al. (2011).”
BackgroundInfluentialRodrik, D., Subramanian, A., & Trebbi, F. (2004) · Journal of Economic Growth · doi:10.1023/b:joeg.0000031425.72248.85 · Cited by 5,423
Frankel, J. A., & Romer, D. (1999) · American Economic Review · doi:10.1257/aer.89.3.379 · Cited by 5,384 · cited 3×
“ese extra variables are essentially added one by one, so that the number of different models actually presented is quite limited. Also, they do not consider any trade variables. In a similar fashion, Frankel and Romer (1999) focus on trade as a growth driver and present empirical evidence to support that theory, but w…”
BackgroundMethodInfluentialThe curse of natural resources
Sachs, J. D., & Warner, A. M. (2001) · European Economic Review · doi:10.1016/s0014-2921(01)00125-8 · Cited by 4,142 · cited 1×
“of cross-country growth to data generated as in Sala-i-Martin et al. (2004) from three different versions of the PWT, versions 6.”
MethodHoeting, J. A., Madigan, D., Raftery, A. E., & Volinsky, C. T. (1999) · Statistical Science · doi:10.1214/ss/1009212519 · Cited by 4,118 · cited 1×
“This review complements and extends other reviews and discussions; for example by Hoeting et al. (1999) on Bayesian model averaging, Clyde and George (2004) on model uncertainty, Moral-Benito (2015) on model averaging in economics and Wang et al. (2009) on frequentist model averaging.”
BackgroundJournal of Statistical Software
Leeuw, J. D. (2009) · WIREs Computational Statistics · doi:10.1002/wics.10 · Cited by 3,599
Bates, J. M., & Granger, C. W. J. (1969) · Journal of the Operational Research Society · doi:10.1057/jors.1969.103 · Cited by 3,201 · cited 5×
“Early examples of Frequentist Model Averaging (FMA) can be found in the forecasting literature, such as the forecast combinations of Bates and Granger (1969). This literature on forecast combinations has become quite voluminous, see e.g. Granger (1989) and Stock and Watson (2006) for reviews, while useful surveys of F…”
BackgroundInfluentialBayesian Analysis of Binary and Polychotomous Response Data
Albert, J. H., & Chib, S. (1993) · Journal of the American Statistical Association · doi:10.1080/01621459.1993.10476321 · Cited by 3,167 · cited 2×
“Typical priors have a product structure with a normal prior on βj (for example a g-prior) and an improper uniform on α. Generally, posterior inference for the probit model can be facilitated by using the data augmentation approach of Albert and Chib (1993).”
MethodSample Splitting and Threshold Estimation
Hansen, B. E. (2000) · Econometrica · doi:10.1111/1468-0262.00124 · Cited by 2,874 · cited 1×
“Piribauer (2016) estimates growth patterns in a spatial econometric framework, building on threshold estimation approaches (Hansen, 2000) to account for structural heterogeneity in the observations.”
BackgroundVariable Selection via Gibbs Sampling
George, E. I., & McCulloch, R. E. (1993) · Journal of the American Statistical Association · doi:10.1080/01621459.1993.10476353 · Cited by 2,828
Determinants of Long-Term Growth: A Bayesian Averaging of Classical Estimates (BACE) Approach
Sala-i-Martin, X., Doppelhofer, G., & Miller, R. I. (2004) · American Economic Review · doi:10.1257/0002828042002570 · Cited by 2,112 · cited 11×
“…also found in Ley and Steel (2012) where three datasets were analysed: two cross-country growth datasets as in Fernández et al. (2001b) (with n = 72 and k = 41) and Sala-i-Martin et al. (2004) (with n = 88 and k = 67) and the returns-to-schooling data of Tobias and Li (2004) (n = 1190 and k = 26).”
BackgroundMethodResultInfluential(2011) · Econometrica · doi:10.3982/ecta5771 · Cited by 2,096
Computing Bayes Factors by Combining Simulation and Asymptotic Approximations
Diciccio, T. J., Kass, R. E., Raftery, A., & Wasserman, L. (1997) · Journal of the American Statistical Association · doi:10.1080/01621459.1997.10474045 · Cited by 1,943 · cited 1×
“lo method is proportional to the reciprocal of the variance of the sample mean estimator normalized by the size of the generated sample. 38 in-depth discussion of all of these methods can be found in DiCiccio et al. (1997). 3.4Role of the prior It has long been understood that the effect of the prior distribution on p…”
MethodOn bias, inconsistency, and efficiency of various estimators in dynamic panel data models
Kiviet, J. F. (1995) · Journal of Econometrics · doi:10.1016/0304-4076(94)01643-e · Cited by 1,926 · cited 2×
“Daude et al. (2016) investigate the drivers of productive capabilities (which are important for growth) using BACE based on bias-corrected least squares dummy variable estimates (Kiviet, 1995) in a dynamic panel context with country-specific effects.”
MethodUsing Bayesian model averaging to calibrate forecast ensembles.
Raftery, A. E., Gneiting, T., Balabdaoui, F., & Polakowski, M. (2005) · Monthly Weather Review · doi:10.1175/mwr2906.1 · Cited by 1,915 · cited 1×
“- cients. Another increasingly important area of dynamic model averaging is the use of BMA methods for ensembles of deterministic models, which was introduced for probabilistic weather forecasting in Raftery et al. (2005). BMA is used to post-process the forecasts provided by ensembles65, where each forecast is associ…”
MethodMarginal Likelihood from the Gibbs Output
Chib, S. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476635 · Cited by 1,905 · cited 1×
“ted. This is not a straightforward calculation on the basis of MCMC output for each model, but there are a number of standard methods in the statistics literature. Chib (2011) discusses the method of Chib (1995) which is essentially based on Bayes’ formula evaluated at a particular value of the parameters. Another pop…”
MethodBayesian Model Averaging for Linear Regression Models
Raftery, A. E., Hoeting, J. A., & Madigan, D. (1997) · Cited by 1,746
Model Selection: An Integral Part of Inference
Buckland, S. T., Burnham, K. P., & Augustin, N. H. (1997) · Biometrics · doi:10.2307/2533961 · Cited by 1,717 · cited 1×
“Buckland et al. (1997) construct weights based on different information criteria.”
BackgroundAssessment and Propagation of Model Uncertainty
Draper, D. (1995) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1995.tb02015.x · Cited by 1,599 · cited 2×
“more precision to our inference than is warranted by the data, and this leads to overly confident decisions and predictions. In addition, our inference can be severely biased. See Chatfield (1995) and Draper (1995) for extensive discussions of model uncertainty. Over the last decade, there has been a rapidly growing awa…”
BackgroundBig Data: New Tricks for Econometrics
Varian, H. R. (2014) · Journal of Economic Perspectives · doi:10.1257/jep.28.2.3 · Cited by 1,557 · cited 2×
“Varian (2014) states that “An important insight from machine learning is that averaging over many small models tends to give better out-of-sample prediction than choosing a single model.”
BackgroundMethodInfluentialBayesian Model Averaging for Linear Regression Models
Raftery, A. E., Madigan, D., & Hoeting, J. A. (1997) · Journal of the American Statistical Association · doi:10.1080/01621459.1997.10473615 · Cited by 1,287 · cited 12×
“to the coefficients of the variables that are “inactive”34 in M j and a larger variance to the remaining coefficients. In addition, their overall prior is proper and does not assume a common intercept. Raftery et al. (1997) propose yet another approach and use a proper conjugate35 prior with a diagonal covariance struct…”
MethodInfluentialA Reference Bayesian Test for Nested Hypotheses and its Relationship to the Schwarz Criterion
Kass, R. E., & Wasserman, L. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476592 · Cited by 1,253 · cited 3×
“Koop and Korobilis (2012) apply DMA and DMS to inflation forecasting, and find that the best predictors change considerably over time and that DMA and DMS lead to improved forecasts with respect to the usual autoregressive and time-varying-parameter models.”
BackgroundMethodInfluentialModel Selection and Accounting for Model Uncertainty in Graphical Models Using Occam's Window
Madigan, D., & Raftery, A. E. (1994) · Journal of the American Statistical Association · doi:10.1080/01621459.1994.10476894 · Cited by 1,205 · cited 5×
“For example, Madigan and Raftery (1994) state that BMA predicts at least as well38 as any single model in terms of LPS and Min and Zellner (1993) show that expected squared error loss of point (predictive mean) forecasts is always minimized by BMA provided the model space includes the model that…”
BackgroundMethodInfluentialCombination forecasts of output growth in a seven‐country data set
Stock, J. H., & Watson, M. W. (2004) · Journal of Forecasting · doi:10.1002/for.928 · Cited by 1,137 · cited 2×
“Stock and Watson (2004) examine a number of weighting schemes in terms of the accuracy of point forecasts and find that forecast combinations can perform well in comparison with single models, but that the best weighting schemes are often the ones that incorporate little or no data adaptivity.”
BackgroundModel uncertainty, data mining and statistical inference
Chatfield, C. (1995) · Journal of the Royal Statistical Society. Series A (Statistics in Society) · doi:10.2307/2983440 · Cited by 1,103 · cited 1×
“See Chatfield (1995) and Draper (1995) for extensive discussions of model uncertainty.”
BackgroundBayesian Graphical Models for Discrete Data
Madigan, D., York, J., & Allard, D. (1995) · International Statistical Review / Revue Internationale de Statistique · doi:10.2307/1403615 · Cited by 1,090 · cited 2×
“…is to run an MCMC algorithm in model space, sampling the models that are most promising: the one that is most commonly used is a random-walk Metropolis sampler usually referred to as MC3, introduced in Madigan and York (1995) and used in e.g. Raftery et al. (1997a) and Fernández et al. (2001a).”
MethodMixtures of g Priors for Bayesian Variable Selection
Liang, F., Paulo, R., Molina, G., Clyde, M. A., & Berger, J. O. (2008) · Journal of the American Statistical Association · doi:10.1198/016214507000001337 · Cited by 1,089 · cited 13×
“This includes the priors proposed in Strawderman (1971) in the context of the normal means problem.”
BackgroundMethodInfluentialLeeper, E. M., Sims, C. A., Zha, T., Hall, R. E., & Bernanke, B. S. (1996) · Brookings Papers on Economic Activity · doi:10.2307/2534619 · Cited by 1,056 · cited 2×
“a benchmark? This is mentioned in Brock et al. (2003), who argue that priors “should be flexible enough to allow for their use across similar studies and thereby facilitate comparability of results.” Leeper et al. (1996) use the terminology “reference prior”29 as a prior which “only reflects a simple summary of beliefs…”
BackgroundMethodInfluentialBenchmark priors for Bayesian model averaging
Fernández, C., Ley, E., & Steel, M. F. J. (2001) · Journal of Econometrics · doi:10.1016/s0304-4076(00)00076-2 · Cited by 1,030
Self-citationThe Intrinsic Bayes Factor for Model Selection and Prediction
Berger, J. O., & Pericchi, L. R. (1996) · Journal of the American Statistical Association · doi:10.1080/01621459.1996.10476668 · Cited by 1,007 · cited 6×
“(2001a), Berger and Pericchi (2001) and Ley and Steel (2009b). One way of reducing the impact of such prior choices on the outcome is to use hyperpriors on w and g, which fits seamlessly with the Bayesian paradigm. Hierarchical priors on w are relatively easy to deal with and were already discussed in the previous sec…”
BackgroundMethodInfluentialGood, I. J. (1952) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1952.tb00104.x · Cited by 976 · cited 3×
“This was introduced in Good (1952) and used in the BMA context in Madigan et al. (1995), Fernández et al. (2001a,b) and Ley and Steel (2009b).”
Model uncertainty in cross‐country growth regressions
Fernández, C., Ley, E., & Steel, M. F. J. (2001) · Journal of Applied Econometrics · doi:10.1002/jae.623 · Cited by 891 · cited 51×
“While Fernández et al. (2001a) examined the effects of choosing fixed values for g, a more systematic investigation of the interplay between g and w was conducted in Ley and Steel (2009b) and Eicher et al. (2011).”
BackgroundMethodResultInfluentialSelf-citationHansen, B. E. (2007) · Econometrica · doi:10.1111/j.1468-0262.2007.00785.x · Cited by 837 · cited 6×
“Hansen (2007) shows that the weight vector chosen by MMA achieves optimality in the sense conveyed by Li (1987).”
BackgroundMethodInfluentialOptimal predictive model selection
Barbieri, M. M., & Berger, J. O. (2004) · The Annals of Statistics · doi:10.1214/009053604000000238 · Cited by 812 · cited 1×
“ly still underestimate uncertainty. Originating in machine learning, a number of algorithms aim to construct a prediction model 22Another possibly interesting model is the median probability model of Barbieri and Berger (2004), which is the model including those covariates which have marginal posterior inclusion proba…”
InfluentialModel Selection and the Principle of Minimum Description Length
Hansen, M. H., & Yu, B. (2001) · Journal of the American Statistical Association · doi:10.1198/016214501753168398 · Cited by 788 · cited 3×
“The free availability of software is generally very important for the adoption of methodology by applied users. There are a number of publicly available computational resources for conducting BMA. Early contributions are the code by Raftery et al. (1997a) (now published as an R package in Raftery et al.”
MethodInfluentialPower prior distributions for regression models
Chen, M.-H., & Ibrahim, J. G. (2000) · Statistical Science · doi:10.1214/ss/1009212673 · Cited by 732 · cited 2×
“This idea of imaginary data is also related to the power prior approach (Ibrahim and Chen (2000) initially developed on the basis of the availability of historical data (i.e. data arising from previous similar studies).”
MethodModel choice: a minimum posterior predictive loss approach
Gelfand, A. (1998) · Biometrika · doi:10.1093/biomet/85.1.1 · Cited by 724 · cited 3×
“George (1999a) comments that “It is tempting to criticize BMA because it does not offer better average predictive performance than a correctly specified single model.”
BackgroundMethodFrequentist Model Average Estimators
Hjort, N. L., & Claeskens, G. (2003) · Journal of the American Statistical Association · doi:10.1198/016214503000000828 · Cited by 688 · cited 4×
“In the context of normal linear regression, Hoeting et al. (1996) propose a Bayesian method for simultaneous variable selection and outlier identification, using variable inflation to model outliers.”
BackgroundMethodInfluentialThe Time Series and Cross-Section Asymptotics of Dynamic Panel Data Estimators
Alvarez, J., & Arellano, M. (2003) · Econometrica · doi:10.1111/1468-0262.00441 · Cited by 637 · cited 8×
“Moral-Benito (2012) considers such a dynamic panel model within the BMA approach by combining the likelihood function discussed in Alvarez and Arellano (2003) with the unit information g-prior.”
MethodInfluentialApproximate Bayes factors and accounting for model uncertainty in generalised linear models
Raftery, A. (1996) · Biometrika · doi:10.1093/biomet/83.2.251 · Cited by 633 · cited 1×
“e.g. logistic or logit regression models, probit models), Poisson, multinomial (e.g. ordered response models, proportional odds models) or gamma distributed. An early contribution to BMA with GLMs is Raftery (1996), who proposes to use approximations for the Bayes factors, based on the Laplace method for integrals. He…”
MethodRegressions by Leaps and Bounds
Furnival, G. M., & Wilson, R. W. (1974) · Technometrics · doi:10.1080/00401706.1974.10489231 · Cited by 625
Bayes and empirical-Bayes multiplicity adjustment in the variable-selection problem
Scott, J. G., & Berger, J. O. (2010) · The Annals of Statistics · doi:10.1214/10-aos792 · Cited by 573 · cited 5×
“…simple way to elicit w is through the prior mean model size, which is wk.25 As the choice of w can have a substantial effect on the results, various authors (Brown et al., 1998; Clyde and George, 2004; Ley and Steel, 2009b; Scott and Berger, 2010) have suggested to put a Beta(a, b) hyperprior on w.”
BackgroundInfluentialThe Risk Inflation Criterion for Multiple Regression
Foster, D. P., & George, E. I. (1994) · The Annals of Statistics · doi:10.1214/aos/1176325766 · Cited by 541 · cited 2×
“• The risk inflation criterion prior, proposed by Foster and George (1994), is based on the Risk inflation criterion (RIC) which leads to g = k(2) using a minimax perspective.”
MethodLong memory and persistence in aggregate output
Diebold, F. X., & Rudebusch, G. D. (1989) · Journal of Monetary Economics · doi:10.1016/0304-3932(89)90003-2 · Cited by 541 · cited 1×
“ed Hauser et al. (1999) (who use a frequentist model selection approach) to conclude that ARFIMA models are not appropriate for inference on persistence, in conflict with the earlier recommendation in Diebold and Rudebusch (1989). However, by using model averaging rather than model selection, we are not forced to 78The…”
MethodWhat have we learned from a decade of empirical research on growth? Growth Empirics and Reality
Brock, W. A. (2001) · The World Bank Economic Review · doi:10.1093/wber/15.2.229 · Cited by 529 · cited 9×
“These more or less intuitive but ad-hoc approaches were precursors to a more formal treatment through BMA discussed and implemented in Brock and Durlauf (2001) and Fernández et al. (2001b).”
BackgroundMethodInfluentialFrankel, J., & Saravelos, G. (2012) · Journal of International Economics · doi:10.1016/j.jinteco.2011.12.009 · Cited by 525 · cited 1×
“An algorithm for finding the best models is the so-called leaps and bounds method used by Raftery (1995) for BMA, based on the all-subsets regression algorithm of Furnival and Wilson (1974). The resulting set of best models can then still be reduced further through Occam’s window if required.”
MethodCalibration and empirical Bayes variable selection
George, E. (2000) · Biometrika · doi:10.1093/biomet/87.4.731 · Cited by 520 · cited 4×
“…the sup vector norm (weaker than the usual l2 norm) in situations where k grows with sample size and derive necessary and sufficient conditions for consistency under the standard g-prior, the Empirical Bayes specification of George and Foster (2000) and the hyper-g and Zellner-Siow mixture priors.”
BackgroundMethodInfluentialLi, K.-C. (1987) · The Annals of Statistics · doi:10.1214/aos/1176350486 · Cited by 514
Computing Bayes Factors Using a Generalization of the Savage-Dickey Density Ratio
Verdinelli, I., & Wasserman, L. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476554 · Cited by 506 · cited 1×
“For nested models, we can often compute Bayes factors through the Savage-Dickey density ratio (Verdinelli and Wasserman, 1995), which is typically both easy to calculate and accurate.”
MethodBates, J. M., & Granger, C. W. J. (1969) · OR · doi:10.2307/3008764 · Cited by 502
Hansen, B. E., & Racine, J. S. (2012) · Journal of Econometrics · doi:10.1016/j.jeconom.2011.06.019 · Cited by 496 · cited 2×
“Hansen and Racine (2012) introduced another estimator within the FMA framework called jackknife model averaging (JMA) that selects appropriate weights for averaging models by minimizing a cross-validation (leave-one-out) criterion.”
BackgroundMethodData mining reconsidered: encompassing and the general‐to‐specific approach to specification search
Hoover, K. D., & Perez, S. J. (1999) · The Econometrics Journal · doi:10.1111/1368-423x.00025 · Cited by 486 · cited 1×
“We refer the reader to Hoover and Perez (1999) and Hendry and Krolzig (2005) for background.”
Ley, E., & Steel, M. F. J. (2009) · Journal of Applied Econometrics · doi:10.1002/jae.1057 · Cited by 477
Self-citationPosterior odds ratios for selected regression hypotheses
Zellner, A., & Siow, A. (1980) · Trabajos de Estadistica Y de Investigacion Operativa · doi:10.1007/bf02888369 · Cited by 463 · cited 3×
“When we consider hierarchical priors on g, model selection consistency is achieved by the Zellner-Siow prior in Zellner and Siow (1980) but not by local and global EB priors nor by the hyper-g prior in Liang et al. (2008a), who therefore introduce a consistent modification, the hyper-g/n prior,…”
MethodInfluentialRaftery, A. E., Kárný, M., & Ettler, P. (2010) · Technometrics · doi:10.1198/tech.2009.08104 · Cited by 452 · cited 10×
“For dynamic models, an efficient implementation of the DMA methodology of Raftery et al. (2010) is provided in the R package eDMA (Catania and Nonejad, 2017b), as described in Catania and Nonejad (2017a).”
BackgroundMethodInfluentialTransparency, Reproducibility, and the Credibility of Economics Research
Christensen, G., & Miguel, E. (2018) · Journal of Economic Literature · doi:10.1257/jel.20171350 · Cited by 446 · cited 2×
“iscard estimates inconsistent with the competitionfragility hypothesis, one of the two main hypotheses in this area. For an in-depth discussion of publication bias and meta-analyses in economics, see Christensen and Miguel (2018). 71 nants of output changes after crises and conclude that for high-income countries the…”
BackgroundResultvan den Broeck, J., Koop, G., Osiewalski, J., & Steel, M. F. J. (1994) · Journal of Econometrics · doi:10.1016/0304-4076(94)90087-6 · Cited by 408 · cited 2×
“van der Maas (2014) proposes a dynamic BMA framework that allows for time variation in the set of variables that is included in the model, as well as structural breaks in the intercept and conditional variance.”
BackgroundMethodSelf-citationDormann, C. F., Calabrese, J. M., Guillera‐Arroita, G., Matechou, E., Bahn, V., Bartoń, K., Beale, C. M., Ciuti, S., Elith, J., Gerstner, K., et al. (2018) · Ecological Monographs · doi:10.1002/ecm.1309 · Cited by 400 · cited 2×
“reviews and discussions; for example by Hoeting et al. (1999) on BMA, Clyde and George (2004) on model uncertainty, Moral-Benito (2015) on model averaging in economics and Wang et al. (2009) on FMA. Dormann et al. (2018) present an elaborate survey of model averaging methods used in ecology. A recent book on model ave…”
BackgroundFORECASTING INFLATION USING DYNAMIC MODEL AVERAGING*
Koop, G., & Korobilis, D. (2012) · International Economic Review · doi:10.1111/j.1468-2354.2012.00704.x · Cited by 390 · cited 2×
“Koop and Korobilis (2012) apply DMA and DMS to inflation forecasting, and find that the best predictors change considerably over time and that DMA and DMS lead to improved forecasts with respect to the usual autoregressive and time-varying-parameter models.”
MethodInfluentialThe Focused Information Criterion
Claeskens, G., & Hjort, N. L. (2003) · Journal of the American Statistical Association · doi:10.1198/016214503000000819 · Cited by 380 · cited 6×
“AIC, the focused information criterion, FIC, of Claeskens and Hjort (2003) and empirical Bayes ideas), they provide a frequentist view of the performance of BMA schemes (in the sense of limiting distributions and large sample approximations to risks).”
MethodInfluentialGeweke, J., & Amisano, G. (2011) · Journal of Econometrics · doi:10.1016/j.jeconom.2011.02.017 · Cited by 366
Objective Bayesian Methods for Model Selection: Introduction and Comparison
Berger, J. O., & Pericchi, L. R. (2001) · Institute of Mathematical Statistics Lecture Notes - Monograph Series · doi:10.1214/lnms/1215540968 · Cited by 355 · cited 4×
“If the arbitrary constant relates to a parameter that is common to all models, it will simply cancel in the ratio (3), and for such parameters we can thus employ improper priors (Fernández et al., 2001a; Berger and Pericchi, 2001).”
BackgroundInfluentialA comparison of two model averaging techniques with an application to growth empirics
Magnus, J. R., Powell, O., & Prüfer, P. (2010) · Journal of Econometrics · doi:10.1016/j.jeconom.2009.07.004 · Cited by 355 · cited 6×
“do not. Thus, for example BACE (Bayesian averaging of classical estimates) of Sala-i-Martin et al. (2004) will be discussed in Section 3 (Subsection 3.7) and weighted average least squares (WALS) of Magnus et al. (2010) is explained in Section 4. As a consequence, all methods discussed in Section 3 can be used for mod…”
MethodInfluentialOn adaptive Markov chain Monte Carlo algorithms
Atchadé, Y. F., & Rosenthal, J. S. (2005) · Bernoulli · doi:10.3150/bj/1130077595 · Cited by 353 · cited 2×
“See Atchadé and Rosenthal (2005) for an introduction.”
BackgroundMethodA Simple Explanation of the Forecast Combination Puzzle*
Smith, J., & Wallis, K. F. (2009) · Oxford Bulletin of Economics and Statistics · doi:10.1111/j.1468-0084.2008.00541.x · Cited by 335 · cited 1×
“o data adaptivity. This empirical fact that “optimally” estimated weights often perform worse than equal weights in terms of mean squared forecast error is known as the “forecast combination puzzle”. Smith and Wallis (2009) provide an explanation for this phenomenon in terms of the additional uncertainty associated wi…”
BackgroundEicher, T. S., Papageorgiou, C., & Raftery, A. E. (2011) · Journal of Applied Econometrics · doi:10.1002/jae.1112 · Cited by 331 · cited 10×
“While Fernández et al. (2001a) examined the effects of choosing fixed values for g, a more systematic investigation of the interplay between g and w was conducted in Ley and Steel (2009b) and Eicher et al. (2011).”
BackgroundMethodInfluentialClyde, M., & George, E. I. (2004) · Statistical Science · doi:10.1214/088342304000000035 · Cited by 329
Invited review combining forecasts—twenty years later
Granger, C. W. J. (1989) · Journal of Forecasting · doi:10.1002/for.3980080303 · Cited by 322
The Properties of Automatic Gets Modelling
Hendry, D. F., & Krolzig, H. (2005) · The Economic Journal · doi:10.1111/j.0013-0133.2005.00979.x · Cited by 322 · cited 5×
“We refer the reader to Hoover and Perez (1999) and Hendry and Krolzig (2005) for background.”
BackgroundMethodInfluentialProper Bayes Minimax Estimators of the Multivariate Normal Mean
Strawderman, W. E. (1971) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177693528 · Cited by 317 · cited 2×
“e hyper-gpriors, which correspond to the following family of priors: p(g) = a 2 2 (1 + g) a=2 (13) where a>2 in order to have a proper distribution for g>0. This includes the priors proposed in Strawderman (1971) in the context of the normal means problem. A value of a = 4 was suggested by Cui and George (2008)…”
BackgroundAre Any Growth Theories Robust?
Durlauf, S. N., Kourtellos, A., & Tan, C. M. (2008) · The Economic Journal · doi:10.1111/j.1468-0297.2007.02123.x · Cited by 311 · cited 7×
“Masanjala and Papageorgiou (2008) and Eicher et al. (2011). However, this tricky issue of exploring very large model spaces is now mostly dealt with through so-called Markov chain Monte Carlo (MCMC) methods40. In particular, a popular strategy is to run an MCMC algorithm in model space, sampling the models that are mo…”
BackgroundMethodInfluentialHall, S. G., & Mitchell, J. (2007) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2006.08.001 · Cited by 307 · cited 2×
“Density forecasts combinations were discussed in Wallis (2005) and further developed by Hall and Mitchell (2007), where the combination weights are chosen to minimize the Kullback-Leibler “distance” between the predicted and true but unknown density.”
MethodMin, C.-K., & Zellner, A. (1993) · Journal of Econometrics · doi:10.1016/0304-4076(93)90102-b · Cited by 307
Comparison of Bayesian predictive methods for model selection
Piironen, J., & Vehtari, A. (2017) · Statistics and Computing · doi:10.1007/s11222-016-9649-y · Cited by 294 · cited 2×
“y better than single models (such as the model with highest posterior probability) in growth data. Ley and Steel (2009b) corroborate these findings, especially with a hyperprior on w, as used in (12). Piironen and Vehtari (2017) focus on model selection methods, but state that “From the predictive point of view, best r…”
BackgroundMethodCriteria for Bayesian model choice with application to variable selection
Bayarri, M. J., Berger, J. O., Forte, A., & García-Donato, G. (2012) · The Annals of Statistics · doi:10.1214/12-aos1013 · Cited by 293 · cited 14×
“For the regression coefficients βj , they propose a g-prior specification (Zellner, 18See Bayarri et al. (2012) for the precise definition of these criteria for “objective” model selection priors.”
BackgroundMethodInfluentialThe Colonial Origins of Comparative Development: An Empirical Investigation: Comment
Albouy, D. Y. (2012) · American Economic Review · doi:10.1257/aer.102.6.3059 · Cited by 291 · cited 1×
“ce from the data than the earlier studies, more adequately reflecting the uncertainty of any conclusions drawn. In addition, the instrument constructed by Acemoglu et al. (2001) has been criticised by Albouy (2012), due to the problems in obtaining reliable historical mortality data. However, a model averaging approach…”
MethodBayesian Model Averaging: A Systematic Review and Conceptual Classification
Fragoso, T. M., Bertoli, W., & Louzada, F. (2018) · International Statistical Review · doi:10.1111/insr.12243 · Cited by 284 · cited 1×
“Further, we can mention a review of weighted average least squares in Magnus and De Luca (2016) while Fragoso and Neto (2015) develop a conceptual classification scheme to better describe the literature in Bayesian model averaging.”
On the use of Non-Local Prior Densities in Bayesian Hypothesis Tests
Johnson, V. E., & Rossell, D. (2010) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2009.00730.x · Cited by 279 · cited 2×
“to fast shrinkage for spurious coefficients (and explore so-called nonlocal priors introduced by Johnson and Rossell (2010) that provide even faster shrinkage in the BMA context).”
BackgroundBayesian linear regression with sparse priors
Castillo, I., Schmidt-Hieber, J., & van der Vaart, A. (2015) · The Annals of Statistics · doi:10.1214/15-aos1334 · Cited by 277 · cited 3×
“In particular, Castillo et al. (2015) prove that BMA in linear regression leads to an optimal rate of contraction of the posterior on the regression coefficients to a sparse “true” data-generating model (a model where many of the coefficients are zero), provided the prior sufficiently penalizes…”
BackgroundInfluentialCross-country heterogeneity in intertemporal substitution
Havranek, T., Horvath, R., Irsova, Z., & Rusnak, M. (2015) · Journal of International Economics · doi:10.1016/j.jinteco.2015.01.012 · Cited by 273
Determinants of Economic Growth: A Bayesian Panel Data Approach
Moral-Benito, E. (2012) · Review of Economics and Statistics · doi:10.1162/rest_a_00154 · Cited by 270 · cited 5×
“Moral-Benito (2012) considers such a dynamic panel model within the BMA approach by combining the likelihood function discussed in Alvarez and Arellano (2003) with the unit information g-prior.”
BackgroundMethodInfluentialDeterminants of Economic Growth: Will Data Tell?Preprint
Jarociński, M., & Ciccone, A. (n.d.) · RePEc: Research Papers in Economics · Cited by 262
Bayesian stochastic search for VAR model restrictions
George, E. I., Sun, D., & Ni, S. (2008) · Journal of Econometrics · doi:10.1016/j.jeconom.2007.08.017 · Cited by 261 · cited 2×
“George et al. (2008) apply BMA ideas in VARs using SSVS methods with priors which do not induce exact zero restrictions on the coefficients, as in George and McCulloch (1993).”
MethodMasanjala, W. H., & Papageorgiou, C. (2008) · Journal of Applied Econometrics · doi:10.1002/jae.1020 · Cited by 254 · cited 7×
“if required. The Occam’s window and the leaps and bounds algorithms are among the methods implemented in the BMA R package of Raftery et al. (2010) and the leaps and bounds algorithm was used in e.g. Masanjala and Papageorgiou (2008) and Eicher et al. (2011). However, this tricky issue of exploring very large model sp…”
MethodInfluentialA Bayesian Variable-Selection Approach for Analyzing Designed Experiments With Complex Aliasing
Chipman, H., Hamada, M., & Wu, C. F. J. (1997) · Technometrics · doi:10.1080/00401706.1997.10485156 · Cited by 253 · cited 4×
“A form of dilution prior in the context of models with interactions of covariates is the heredity prior of Chipman et al. (1997) where interaction are only allowed to be included if both main effects are included (strong heredity) or at least one of the main effects (weak heredity). In the context of examining the sou…”
BackgroundMethodResultInfluentialDiscussion: Performance of Bayesian Model Averaging
Raftery, A. E., & Zheng, Y. (2003) · Journal of the American Statistical Association · doi:10.1198/016214503000000891 · Cited by 252 · cited 1×
“• BMA benefits from a number of appealing statistical properties, such as point estimators and predictors that minimize prior-weighted Mean Squared Error (MSE), and the calibration of the associated intervals (Raftery and Zheng, 2003).”
BackgroundMODEL AVERAGING IN ECONOMICS: AN OVERVIEW
Moral‐Benito, E. (2015) · Journal of Economic Surveys · doi:10.1111/joes.12044 · Cited by 249 · cited 2×
“out for an informed use of these methods. This review complements and extends other reviews and discussions; for example by Hoeting et al. (1999) on BMA, Clyde and George (2004) on model uncertainty, Moral-Benito (2015) on model averaging in economics and Wang et al. (2009) on FMA. Dormann et al. (2018) present an ela…”
BackgroundMethodBayesian Adaptive Sampling for Variable Selection and Model Averaging
Clyde, M. A., Ghosh, J., & Littman, M. L. (2011) · Journal of Computational and Graphical Statistics · doi:10.1198/jcgs.2010.09049 · Cited by 247 · cited 9×
“Clyde et al. (2011) remark that while the standard algorithms MC3 and SSVS are easy to implement, they may mix poorly when covariates are highly correlated.”
MethodInfluentialBayesian Model Averaging and exchange rate forecasts
Wright, J. H. (2008) · Journal of Econometrics · doi:10.1016/j.jeconom.2008.08.012 · Cited by 247 · cited 4×
“by many panel data applications: high model uncertainty, presence of slope heterogeneity, and potential divergence in short-run and long-run effects”. The use of BMA in forecasting exchange rates by Wright (2008) leads to the conclusion that BMA provides slightly better out-of-sample forecasts (measured by mean square…”
BackgroundMethodResultInfluentialThe forecast combination puzzle: A simple theoretical explanation
Claeskens, G., Magnus, J. R., Vasnev, A. L., & Wang, W. (2016) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2015.12.005 · Cited by 244 · cited 1×
“se to equal, then a simple average of competing forecasts (i.e. assuming the weights are equal) can dominate a forecast combination with weights that are estimated from the data. Along similar lines, Claeskens et al. (2015) also provide an explanation for the forecast combination puzzle, but they explicitly treat the…”
BackgroundThe conquest of US inflation: Learning and robustness to model uncertainty
Cogley, T., & Sargent, T. J. (2005) · Review of Economic Dynamics · doi:10.1016/j.red.2005.02.001 · Cited by 243 · cited 2×
“Cordero et al. (2016) use 60Here they follow the approach suggested by Amini and Parmeter (2012), who build on Magnus et al.”
BackgroundMethodCross-country causes and consequences of the crisis: An update
Rose, A. K., & Spiegel, M. M. (2011) · European Economic Review · doi:10.1016/j.euroecorev.2010.12.006 · Cited by 243 · cited 3×
“Following the work of Rose and Spiegel (2011) and the earlier BMA approach of Giannone et al. (2011), Feldkircher (2014) uses BMA to identify the main macroeconomic and financial market conditions that help explain the real economic effects of the global financial crisis of 2008- 9.”
BackgroundMethodPolicy Evaluation in Uncertain Economic Environments
Brock, W. A., Durlauf, S. N., & West, K. D. (. D. (2003) · Brookings Papers on Economic Activity · doi:10.1353/eca.2003.0013 · Cited by 242
The Choice of Variables in Multiple Regression
Lindley, D. V. (1968) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1968.tb01505.x · Cited by 232 · cited 2×
“An early contribution is Lindley (1968), who proposes to include costs in the utility function for adding covariates, while Brown et al. (1999) extend this idea to multivariate regression.”
BackgroundBayesian Model Averaging in Proportional Hazard Models: Assessing the Risk of a Stroke
Volinsky, C. T., Madigan, D., Raftery, A. E., & Kronmal, R. A. (1997) · Journal of the Royal Statistical Society Series C: Applied Statistics · doi:10.1111/1467-9876.00082 · Cited by 226
Growth Regressions and What the Textbooks Don’t Tell You
Temple, J. (2000) · Bulletin of Economic Research · doi:10.1111/1467-8586.00103 · Cited by 216
Modelling UK inflation, 1875–1991
Hendry, D. F. (2001) · Journal of Applied Econometrics · doi:10.1002/jae.615 · Cited by 196 · cited 2×
“I refer the reader to Hoover and Perez (1999) and Hendry and Krolzig (2005) for background and details.”
BackgroundHabit formation in consumption: A meta-analysis
Havranek, T., Rusnak, M., & Sokolova, A. (2017) · European Economic Review · doi:10.1016/j.euroecorev.2017.03.009 · Cited by 190 · cited 3×
“Generally, the hierarchical prior on g implies that the marginal likelihood of a given model is not analytically known, but is the integral of (10) with respect to the prior of g. Liang et al. (2008a) propose the use of a Laplace approximation for this integral, while Ley and Steel (2012) use a Gibbs sampler approach…”
BackgroundMethodResultBayesian Model Averaging Employing Fixed and Flexible Priors: The BMS Package for R
Zeugner, S., & Feldkircher, M. (2015) · Journal of Statistical Software · doi:10.18637/jss.v068.i04 · Cited by 189 · cited 1×
“Details about BMS are given in Zeugner and Feldkircher (2015).”
BackgroundForecast Uncertainties in Macroeconomic Modeling: An Application to the U.K. Economy
Garratt, A., Lee, K. C., Pesaran, M. H., & Shin, Y. (2003) · Journal of the American Statistical Association · doi:10.1198/016214503000000765 · Cited by 183
Zhang, X., Yu, D., Zou, G., & Liang, H. (2016) · Journal of the American Statistical Association · doi:10.1080/01621459.2015.1115762 · Cited by 180 · cited 5×
“of the MSE. They compare their methods with those of Magnus et al. (2011), who also average feasible GLS estimators. Most asymptotically optimal FMA methods have been developed for linear models, but Zhang et al. (2016) specifically consider GLMs (see Section 3.9.1) and generalized linear mixedeffects models70 and prop…”
MethodInfluentialThe international transmission of US shocks—Evidence from Bayesian global vector autoregressions
Feldkircher, M., & Huber, F. (2016) · European Economic Review · doi:10.1016/j.euroecorev.2015.01.009 · Cited by 174 · cited 3×
“Indeed, Fernández et al. (2001a) suggest the use of the correlation between posterior model probabilities based on i) and ii) as an indicator of convergence of the chain.”
BackgroundMethodBayesian Model Averaging for Spatial Econometric Models
LeSage, J. P., & Parent, O. (2007) · Geographical Analysis · doi:10.1111/j.1538-4632.2007.00703.x · Cited by 173 · cited 5×
“vector filtering as in Crespo Cuaresma and Feldkircher (2013). Hortas-Rico and Rios (2016) investigate the drivers of urban income inequality using Spanish municipal data. They follow the framework of LeSage and Parent (2007) to incorporate spatial effects in the BMA analysis. Piribauer and Crespo Cuaresma (2016) compa…”
MethodInfluentialExpected-posterior prior distributions for model selection
Perez, J. M. (2002) · Biometrika · doi:10.1093/biomet/89.3.491 · Cited by 172 · cited 2×
“In addition, the mechanism of imaginary data forms the basis of the expected-posterior prior (Pérez and Berger, 2002).”
Spatial econometric panel data model specification: A Bayesian approach
LeSage, J. P. (2014) · Spatial Statistics · doi:10.1016/j.spasta.2014.02.002 · Cited by 172 · cited 2×
“BMA in this model was used in LeSage (2014), building on earlier work, such as LeSage and Parent (2007).”
BackgroundMethodCombining Density and Interval Forecasts: A Modest Proposal*
Wallis, K. F. (2005) · Oxford Bulletin of Economics and Statistics · doi:10.1111/j.1468-0084.2005.00148.x · Cited by 169 · cited 2×
“Density forecasts combinations were discussed in Wallis (2005) and further developed by Hall and Mitchell (2007), where the combination weights are chosen to minimize the Kullback-Leibler “distance” between the predicted and true but unknown density.”
BackgroundMethodInfluentialHendry, D. F., & Krolzig, H. (2004) · Oxford Bulletin of Economics and Statistics · doi:10.1111/j.1468-0084.2004.102_1.x · Cited by 168 · cited 3×
“They find many more occurrences of disjointness, where regressors are substitutes and really should not appear together. However, these latter regressors tend to be fairly unimportant drivers of growth. Man (2017) compares different jointness measures using data from a variety of disciplines and finds that results dif…”
BackgroundMethodResultInfluentialForecasting with Factor-Augmented Regression: A Frequentist Model Averaging Approach, Second Version
Cheng, X., & Hansen, B. E. (2013) · Journal of Econometrics · doi:10.1016/j.jeconom.2015.02.010 · Cited by 163
Is God in the details? A reexamination of the role of religion in economic growth
Durlauf, S. N., Kourtellos, A., & Tan, C. M. (2012) · Journal of Applied Econometrics · doi:10.1002/jae.1245 · Cited by 162
Feldkircher, M., Zeugner, S., MFeldkircher@imf.org, & SZeugner@imf.org (2009) · IMF Working Papers · doi:10.5089/9781451873498.001 · Cited by 162 · cited 3×
“(1997) and Fernández et al. (2001a). On the basis of the application in Masanjala and Papageorgiou (2008), Crespo Cuaresma (2011) finds that MC(3) leads to rather different results from the leaps and bounds method, which does not seem to explore the model space sufficiently well.”
BackgroundMethodLikelihood-Based Estimation of Dynamic Panels With Predetermined Regressors
Moral‐Benito, E. (2013) · Journal of Business and Economic Statistics · doi:10.1080/07350015.2013.818003 · Cited by 160 · cited 2×
“Thus, Moral-Benito (2016) proposes the use of a suitable likelihood function (derived in Moral-Benito (2013)) for dynamic panel data with fixed effects and weakly exogenous51 regressors, which is argued to be the most relevant form of endogeneity in the growth regression context.”
BackgroundMethodThe use of prior information in forecast combination
Diebold, F. X., & Pauly, P. (1990) · International Journal of Forecasting · doi:10.1016/0169-2070(90)90028-a · Cited by 159 · cited 1×
“iterature, in this paper gdenotes a variance factor rather than a precision factor as in Fern´andez et al. (2001a). Interestingly, the g-prior appears earlier in the context of combining forecasts by Diebold and Pauly (1990), who use a regression-based forecast combination framework as a means to introduce shrinkage i…”
MethodInfluentialMarinacci, M. (2015) · Journal of the European Economic Association · doi:10.1111/jeea.12164 · Cited by 158
Distribution theory of the least squares averaging estimator
Liu, C.-A. (2014) · Journal of Econometrics · doi:10.1016/j.jeconom.2014.07.002 · Cited by 155
Bayesian Measures of Model Complexity and Fit
Spiegelhalter, D. J., Best, N. G., Carlin, B. P., & Van Der Linde, A. (2002) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/1467-9868.00353 · Cited by 151 · cited 1×
“Spiegelhalter et al. (2002) propose the Deviance information criterion (DIC) which can be interpreted as a Bayesian generalization of AIC.11 4.”
BackgroundDilution priors: Compensating for model space redundancy
George, E. I. (2010) · Institute of Mathematical Statistics collections · doi:10.1214/10-imscoll611 · Cited by 150 · cited 2×
“for dilution by down-weighting prior probabilities on sets of similar 38They use a very tight prior indeed, which corresponds to a prior mean model size m= k=(k+1) which is less than one! 26 models. George (2010) suggests three distinct approaches for the construction of these so-called “dilution priors”, based on tes…”
BackgroundThe model confidence set package for R
Bernardi, M., & Catania, L. (2018) · International Journal of Computational Economics and Econometrics · doi:10.1504/ijcee.2018.091037 · Cited by 148
Luca, G. D., & Magnus, J. R. (2011) · The Stata Journal Promoting communications on statistics and Stata · doi:10.1177/1536867x1201100402 · Cited by 146
The resource curse revisited: A Bayesian model averaging approach
Arin, K. P., & Braunfels, E. (2018) · Energy Economics · doi:10.1016/j.eneco.2017.12.033 · Cited by 145 · cited 1×
“Arin and Braunfels (2017) examine the existence of the “natural resource curse” focusing on the empirical links between oil reserves and growth.”
BackgroundEmpirical Bayes vs. fully Bayes variable selection
Cui, W., & George, E. I. (2007) · Journal of Statistical Planning and Inference · doi:10.1016/j.jspi.2007.02.011 · Cited by 143 · cited 4×
“veraged over all models. Liang et al. (2008) propose specific ways of estimating gin this context. There is some evidence in the literature regarding comparisons between fully Bayes and EB procedures: Cui and George (2008) largely favour (global) EB in the context of known ˙and k = n, whereas Liang et al. (2008) find th…”
BackgroundInfluentialHavranek, T., & Sokolova, A. (2020) · Review of Economic Dynamics · doi:10.1016/j.red.2019.05.004 · Cited by 141
Fully Bayes factors with a generalized g-prior
Maruyama, Y., & George, E. I. (2011) · The Annals of Statistics · doi:10.1214/11-aos917 · Cited by 139 · cited 6×
“Generalized Linear Models (GLMs) describe a more general class of models (McCullagh and Nelder, 1989) that covers the normal linear regression model but also regression models where the response variable is non-normal, such as binomial (e.g. logistic or logit regression models, probit models), Poisson, multinomial (e.…”
BackgroundMethodInfluentialBANK COMPETITION AND FINANCIAL STABILITY: MUCH ADO ABOUT NOTHING?
Žigraiová, D., & Havránek, T. (2015) · Journal of Economic Surveys · doi:10.1111/joes.12131 · Cited by 139
Mixtures of g -priors for Bayesian model averaging with economic applications
Ley, E., & Steel, M. F. J. (2012) · Journal of Econometrics · doi:10.1016/j.jeconom.2012.06.009 · Cited by 139 · cited 1×
“egy is to run an MCMC algorithm in model space, sampling the models that are most promising: the one that is most commonly used is a random-walk Metropolis sampler usually referred to as MC, introduced in Madigan and York (1995) and used in e.”
Self-citationJointness of growth determinants
Doppelhofer, G., & Weeks, M. (2009) · Journal of Applied Econometrics · doi:10.1002/jae.1046 · Cited by 139 · cited 7×
“Man (2017) compares different jointness measures using data from a variety of disciplines and finds that results differ substantially between the measures of Doppelhofer and Weeks (2009) on the one hand and Ley and Steel (2007) on the other hand.”
InfluentialForecast Combination and Model Averaging Using Predictive Measures
Eklund, J., & Karlsson, S. (2007) · Econometric Reviews · doi:10.1080/07474930701220550 · Cited by 136 · cited 2×
“(2010)) and the Fortran code used by Fernández et al. (2001a). Recently, a number of R-packages have been created, in particular the frequently used BMS package (Feldkircher and Zeugner, 2014).”
MethodA method for simultaneous variable selection and outlier identification in linear regression
Hoeting, J. A., Raftery, A. E., & Madigan, D. (1996) · Computational Statistics & Data Analysis · doi:10.1016/0167-9473(95)00053-4 · Cited by 134 · cited 3×
“In the context of normal linear regression, Hoeting et al. (1996) propose a Bayesian method for simultaneous variable selection and outlier identification, using variable inflation to model outliers.”
BackgroundMethodResultInfluentialDrachal, K. (2016) · Energy Economics · doi:10.1016/j.eneco.2016.09.020 · Cited by 128 · cited 4×
“Drachal (2016) investigates the determinants of monthly spot oil prices between 1986 and 2015, using Dynamic Model Averaging (DMA) and Dynamic Model Selection (DMS). Although some interesting patterns over time were revealed, no significant evidence was found that DMA is superior in terms of forecast accuracy over, fo…”
MethodInfluentialEconomic Predictions with Big Data: The Illusion of SparsityPreprint
Giannone, D., Lenza, M., & Primiceri, G. E. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3166281 · Cited by 127 · cited 1×
“Giannone et al. (2018) investigate whether sparse modelling is a good approach to predictive problems in economics on the basis of a number of datasets from macro, micro and finance.”
BackgroundSorting through global corruption determinants: Institutions and education matter – Not culture
Jetter, M., & Parmeter, C. F. (2018) · World Development · doi:10.1016/j.worlddev.2018.05.013 · Cited by 126 · cited 1×
“were then used as dependent variables in a BMA analysis, to further explain the heterogeneity between the 27 countries covered in the survey. In order to identify the main determinants of corruption, Jetter and Parmeter (2018) apply IVBMA to corruption data with a large number of endogenous regressors, using lagged va…”
MethodMarket Freedom and the Global Recession
Giannone, D., Lenza, M., & Reichlin, L. (2010) · IMF Economic Review · doi:10.1057/imfer.2010.14 · Cited by 122 · cited 4×
“This was introduced in Good (1952) and used in the BMA context in Madigan et al.”
MethodInfluentialHyper-$g$ priors for generalized linear models
Bové, D. S., & Held, L. (2011) · Bayesian Analysis · doi:10.1214/11-ba615 · Cited by 121 · cited 10×
“They conduct inference using an algorithm which is quite similar to that in Sabanés Bové and Held (2011b).”
BackgroundMethodInfluentialJointness in Bayesian variable selection with applications to growth regression
Ley, E., & Steel, M. F. J. (2007) · Journal of Macroeconomics · doi:10.1016/j.jmacro.2006.12.002 · Cited by 119 · cited 6×
“Man (2017) compares different jointness measures using data from a variety of disciplines and finds that results differ substantially between the measures of Doppelhofer and Weeks (2009) on the one hand and Ley and Steel (2007) on the other hand.”
BackgroundMethodInfluentialSelf-citationFeldkircher, M. (2014) · Journal of International Money and Finance · doi:10.1016/j.jimonfin.2013.12.003 · Cited by 115 · cited 6×
“Using the formal BMA approach, Feldkircher and Zeugner (2012) examine more in detail what causes the lack of robustness found in Ciccone and Jarociński (2010). One first conclusion is that the changes are roughly halved if the analyses with the different PWT data use the same set of countries. They also stress that th…”
MethodInfluentialAdaptive sampling for Bayesian variable selection
Nott, D. J., & Kohn, R. (2005) · Biometrika · doi:10.1093/biomet/92.4.747 · Cited by 114 · cited 2×
“More advanced algorithms that utilize other proposals can then be considered, such as adaptive MCMC41 (Nott and Kohn, 2005) or evolutionary Monte Carlo (Liang and Wong, 2000).”
MethodInfluentialVariable Selection for Logistic Regression Using a Prediction‐Focused Information Criterion
Claeskens, G., Croux, C., & Kerckhoven, J. V. (2006) · Biometrics · doi:10.1111/j.1541-0420.2006.00567.x · Cited by 110 · cited 2×
“This was done in e,g, Claeskens et al. (2006) (for logistic models), Zhang et al.”
BackgroundMethodGeneralised density forecast combinations
Kapetanios, G., Mitchell, J., Price, S., & Fawcett, N. W. P. (2015) · Journal of Econometrics · doi:10.1016/j.jeconom.2015.02.047 · Cited by 104 · cited 2×
“30Textbook treatments of this approach can be found in Chapter 11 of Koop (2003) and Chapter 2 of Fletcher (2018).”
BackgroundMixtures of g -Priors in Generalized Linear Models
Li, Y., & Clyde, M. A. (2018) · Journal of the American Statistical Association · doi:10.1080/01621459.2018.1469992 · Cited by 101 · cited 3×
“The priors on the model parameters designed for GLMs in Li and Clyde (2017) employ a different type of “centering” (induced by the observed information matrix at the MLE of the coefficients), leading to a g-prior that displays local orthogonality properties at the MLE.”
BackgroundMethodInfluentialModel uncertainty in Panel Vector Autoregressive models
Koop, G. M., & Korobilis, D. (2015) · European Economic Review · doi:10.1016/j.euroecorev.2015.09.006 · Cited by 98 · cited 2×
“model of the UK economy. George et al. (2008) apply BMA ideas in VARs using SSVS methods with priors which do not induce exact zero restrictions on the coefficients, as in George and McCulloch (1993). Koop and Korobilis (2016) extend this to Panel VARs where the restrictions of interest involve interdependencies betwee…”
BackgroundMethodA Mallows-Type Model Averaging Estimator for the Varying-Coefficient Partially Linear Model
Zhu, R., Wan, A. T. K., Zhang, X., & Zou, G. (2018) · Journal of the American Statistical Association · doi:10.1080/01621459.2018.1456936 · Cited by 96
Sickles, R. C. (2004) · Journal of Econometrics · doi:10.1016/j.jeconom.2004.05.004 · Cited by 94
Seeing the forest through the trees: a meta-analysis of political budget cycles
Philips, A. (2016) · Public Choice · doi:10.1007/s11127-016-0364-1 · Cited by 93 · cited 2×
“Another example of the use of BMA in meta-analysis is Philips (2016) who investigates political budget cycles and finds support for some of the context-conditional theories in that literature.”
ResultFrequentist model averaging estimation: a review
Wang, H., Zhang, X., & Zou, G. (2009) · Journal of Systems Science and Complexity · doi:10.1007/s11424-009-9198-y · Cited by 92 · cited 3×
“Wang et al. (2009) claim that there are model selection methods that automatically incorporate model uncertainty by selecting variables and estimating parameters simultaneously.”
BackgroundMethodSPATIAL FILTERING, MODEL UNCERTAINTY AND THE SPEED OF INCOME CONVERGENCE IN EUROPE
Cuaresma, J. C., & Feldkircher, M. (2012) · Journal of Applied Econometrics · doi:10.1002/jae.2277 · Cited by 91 · cited 8×
“Crespo Cuaresma et al. (2017) use SAR models to jointly model income growth and human capital accumulation and mitigate the computational requirements by using an approximation based on spatial eigenvector filtering as in Crespo Cuaresma and Feldkircher (2013).”
MethodInfluentialOn Sampling Strategies in Bayesian Variable Selection Problems With Large Model Spaces
García‐Donato, G., & Martínez‐Beneito, M. A. (2012) · Journal of the American Statistical Association · doi:10.1080/01621459.2012.742443 · Cited by 88 · cited 1×
“Generic numerical methods were compared in Garcı́a-Donato and Martı́nez-Beneito (2013), who identify two different strategies:”
MethodCOMPARISON OF MODEL AVERAGING TECHNIQUES: ASSESSING GROWTH DETERMINANTS
Amini, S. M., & Parmeter, C. F. (2012) · Journal of Applied Econometrics · doi:10.1002/jae.2288 · Cited by 87 · cited 7×
“Cordero et al. (2016) use 60Here they follow the approach suggested by Amini and Parmeter (2012), who build on Magnus et al. (2010) and use orthogonalization of the covariate space, thus reducing the number of models that need to be estimated from 2k to k.”
BackgroundMethodResultInfluentialMutual funds flows and the geography of contagion
Puy, D. (2015) · Journal of International Money and Finance · doi:10.1016/j.jimonfin.2015.06.014 · Cited by 84 · cited 3×
“An early contribution to BMA with GLMs is Raftery (1996), who proposes to use approximations for the Bayes factors, based on the Laplace method for integrals.”
BackgroundMethodInfluentialNonlocal Priors for High-Dimensional Estimation
Rossell, D., & Telesca, D. (2015) · Journal of the American Statistical Association · doi:10.1080/01621459.2015.1130634 · Cited by 83 · cited 1×
“Rossell and Telesca (2017) show that BMA leads to fast shrinkage for spurious coefficients (and explore so-called nonlocal priors that provide even faster shrinkage in the BMA context).”
BackgroundEconomic diversity, unemployment and the Great Recession
Watson, P. S., & Deller, S. C. (2017) · The Quarterly Review of Economics and Finance · doi:10.1016/j.qref.2016.12.003 · Cited by 83 · cited 2×
“the introduction of an unknown number of structural breaks and find strong support for models with such breaks, although they conclude that there is less evidence for structural break since the 1990s. Watson and Deller (2017) consider the relationship between economic diversity and unemployment in the light of the econ…”
BackgroundDynamics of global business cycle interdependence
Ductor, L., & Leiva‐León, D. (2016) · Journal of International Economics · doi:10.1016/j.jinteco.2016.07.003 · Cited by 83 · cited 2×
“Dilution priors were implemented in economics by Durlauf et al. (2008) to represent priors that are uniform on theories (i.”
BackgroundBayesian model averaging in the instrumental variable regression model
Koop, G. M., León‐González, R., & Strachan, R. W. (2012) · Journal of Econometrics · doi:10.1016/j.jeconom.2012.06.005 · Cited by 82 · cited 6×
“Koop et al. (2012) use their instrumental variables BMA method in this context.”
MethodInfluentialBayesian Additive Regression Trees using Bayesian model averaging
Hernández, B., Raftery, A. E., Pennington, S. R., & Parnell, A. C. (2017) · Statistics and Computing · doi:10.1007/s11222-017-9767-1 · Cited by 82 · cited 13×
“For example, Madigan and Raftery (1994) state that BMA predicts at least as well38 as any single model in terms of LPS and Min and Zellner (1993) show that expected squared error loss of point (predictive mean) forecasts is always minimized by BMA provided the model space includes the model that generated the data. Ra…”
BackgroundMethodInfluentialA three-step algorithm for CANDECOMP/PARAFAC analysis of large data sets with multicollinearity
Kiers, H. A. L. (1998) · Journal of Chemometrics · doi:10.1002/(sici)1099-128x(199805/06)12:3<173::aid-cem505>3.0.co;2-0 · Cited by 81 · cited 11×
“Brown et al. (1998) extend the MC(3) proposal by adding a “swap” move where one included and one excluded covariate are selected at random and the proposed model is the one where they are swapped. They suggest to generate a candidate model by either using the MC(3) move or the swap move. Lamnisos et al. (2009) extend…”
BackgroundInfluentialForecasting house prices using dynamic model averaging approach: Evidence from China
Wei, Y., & Cao, Y. (2016) · Economic Modelling · doi:10.1016/j.econmod.2016.12.002 · Cited by 81 · cited 3×
“Of course, as Wright (2008) states: “One does not have to be a subjectivist Bayesian to believe in the usefulness of BMA, or of Bayesian shrinkage techniques more generally.”
BackgroundMethodBayesian analysis of long memory and persistence using ARFIMA models
Koop, G. M., Ley, E., Osiewalski, J., & Steel, M. F. J. (1997) · Journal of Econometrics · doi:10.1016/0304-4076(95)01787-9 · Cited by 79 · cited 8×
“ng-age population. 5.2Inflation and Output Forecasting In the context of time series modelling with ARIMA and ARFIMA models, BMA was used for posterior inference on impulse responses78 for real GNP in Koop et al. (1997). This is an example where the behaviour of the quantity of interest (impulse response) is very diffe…”
BackgroundMethodInfluentialSelf-citationFirm Default Prediction: A Bayesian Model-Averaging Approach
Traczynski, J. (2017) · Journal of Financial and Quantitative Analysis · doi:10.1017/s002210901700031x · Cited by 78 · cited 2×
“Traczynski (2017) uses a Bayesian model-averaging approach for predicting firm bankruptcies and defaults at a 12-month horizon using hazard models.”
MethodAmini, S. M., & Parmeter, C. F. (2011) · Journal of Economic and Social Measurement · doi:10.3233/jem-2011-0350 · Cited by 77 · cited 7×
“In the context of growth applications with large model spaces, Amini and Parmeter (2012) introduce an operational version of MMA by using the same semiorthogonal 53These models are GLMs with so-called random effects, e.”
MethodInfluentialHauser, M. A., Pötscher, B. M., & Reschenhofer, E. (1999) · Empirical Economics · doi:10.1007/s001810050054 · Cited by 76
Brown, P. J. (1999) · Biometrika · doi:10.1093/biomet/86.3.635 · Cited by 75 · cited 2×
“An early contribution is Lindley (1968), who proposes to include costs in the utility function for adding covariates, while Brown et al. (1999) extend this idea to multivariate regression.”
BackgroundTuition Fees and University Enrolment: A Meta‐Regression Analysis
Havránek, T., Iršová, Z., & Zeynalova, O. (2018) · Oxford Bulletin of Economics and Statistics · doi:10.1111/obes.12240 · Cited by 73 · cited 1×
“(2016) use BMA methods to assess the determinants of cognitive and non-cognitive educational outcomes in Spain. The link between tuition fees and demand for higher education has been investigated in Havranek et al. (2018) in a meta-analysis framework. After accounting for publication bias, they conclude that the mean…”
MethodAn Empirical Analysis of Local Opposition to New Transmission Lines Across the EU-27
Cohen, J. J., Moeltner, K., Reichl, J., & Schmidthaler, M. (2016) · The Energy Journal · doi:10.5547/01956574.37.3.jcoh · Cited by 72 · cited 5×
“Cohen et al. (2016) investigate the social acceptance of power transmission lines using a survey that was conducted in the EU.”
MethodInfluentialBayesian Variable and Transformation Selection in Linear Regression
Hoeting, J. A., Raftery, A. E., & Madigan, D. (2002) · Journal of Computational and Graphical Statistics · doi:10.1198/106186002501 · Cited by 72
WEIGHTED‐AVERAGE LEAST SQUARES (WALS): A SURVEY
Magnus, J. R., & Luca, G. D. (2014) · Journal of Economic Surveys · doi:10.1111/joes.12094 · Cited by 70 · cited 1×
“(2004) use asymptotic reasoning in the specific setting of the linear model with a g-prior to avoid specifying a prior on the model parameters and arrive at a BIC approximation in this manner. They call the resulting procedure BACE (Bayesian averaging of classical estimates). This approach was generalized to panel dat…”
MethodMagnus, J. R., Wan, A. T. K., & Zhang, X. (2010) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2010.09.023 · Cited by 67 · cited 3×
“(2004) use asymptotic reasoning in the specific setting of the linear model with a g-prior to avoid specifying a prior on the model parameters and arrive at a BIC approximation in this manner. They call the resulting procedure BACE (Bayesian averaging of classical estimates). This approach was generalized to panel dat…”
MethodInfluentialExchange market pressures during the financial crisis: A Bayesian model averaging evidence
Feldkircher, M., Horváth, R., & Rusnák, M. (2013) · Journal of International Money and Finance · doi:10.1016/j.jimonfin.2013.08.021 · Cited by 67 · cited 1×
“Feldkircher et al. (2014) focus on finding leading indicators for exchange market pressures during the crisis and their BMA results indicate that inflation plays an important aggravating role, whereas international reserves act as a mitigating factor.”
BackgroundMethods and Tools for Bayesian Variable Selection and Model Averaging in Normal Linear Regression
Forte, A., García‐Donato, G., & Steel, M. F. J. (2018) · International Statistical Review · doi:10.1111/insr.12249 · Cited by 64
Self-citationVariable selection in qualitative models via an entropic explanatory power
Dupuis, J. A., & Robert, C. P. (2002) · Journal of Statistical Planning and Inference · doi:10.1016/s0378-3758(02)00286-0 · Cited by 63 · cited 2×
“variate regression. Other Bayesian model selection procedures that are based on optimising some loss or utility function can be found in e.g. Gelfand and Ghosh (1998), Draper and Fouskakis (2000) and Dupuis and Robert (2003). Note that decision-based approaches do need the specification of a utility function, which is…”
BackgroundDoes trust contribute to stock market development?
Ng, A., Ibrahim, M. H., & Mirakhor, A. (2014) · Economic Modelling · doi:10.1016/j.econmod.2014.10.056 · Cited by 62 · cited 2×
“d unemployment rates across all years of the sample (2007-2014). The economic diversity of neighbours is only strongly associated with reduced unemployment rates at the height of the Great Recession. Ng et al. (2016) investigate the relevance of social capital in stock market development using 72 BMA methods and concl…”
BackgroundThe impact of financial regulation on current account balances
Moral‐Benito, E., & Roehn, O. (2015) · European Economic Review · doi:10.1016/j.euroecorev.2015.07.005 · Cited by 62 · cited 1×
“Moral-Benito and Roehn (2016) explore the relationship between financial market regulation and current account balances.”
BackgroundFeldkircher, M., & Zeugner, S. (2012) · Journal of Applied Econometrics · doi:10.1002/jae.2265 · Cited by 61 · cited 2×
“Using the formal BMA approach, Feldkircher and Zeugner (2012) examine more in detail what causes the lack of robustness found in Ciccone and Jarociński (2010).”
BackgroundMethodForecast accuracy and economic gains from Bayesian model averaging using time‐varying weights
Hoogerheide, L. F., Kleijn, R., Ravazzolo, F., van Dijk, H. K., & Verbeek, M. (2009) · Journal of Forecasting · doi:10.1002/for.1145 · Cited by 61 · cited 1×
“Other time-varying Bayesian model weight schemes are considered in Hoogerheide et al. (2010), who find that they outperform other combination forecasting schemes in terms of predictive and economic gains.”
BackgroundEliciting prior information to enhance the predictive performance of bayesian graphical models
Madigan, D., Gavrin, J., & Raftery, A. E. (1995) · Communications in Statistics - Theory and Methods · doi:10.1080/03610929508831616 · Cited by 60 · cited 1×
“This was introduced in Good (1952) and used in the BMA context in Madigan et al. (1995), Fernández et al. (2001a,b) and Ley and Steel (2009b).”
MethodBayesian Variable Selection Under Collinearity
Ghosh, J., & Ghattas, A. E. (2015) · The American Statistician · doi:10.1080/00031305.2015.1031827 · Cited by 60 · cited 8×
“Reported mean excess sensitivity seems materially affected by demographic variables, publication bias and liquidity constraints and they conclude that the permanent income hypothesis seems a pretty good approximation of the actual behavior of the average consumer. Havranek et al. (2017) consider estimates of habit for…”
BackgroundResultInfluentialSoftware for Bayesian cross section and panel spatial model comparison
LeSage, J. P. (2015) · Journal of Geographical Systems · doi:10.1007/s10109-015-0217-3 · Cited by 60 · cited 2×
“This software uses parallel computing if shared memory multiple processors hardware is available, In addition, code exists in other computing environments; for example LeSage (2015) describes Matlab code for BMA with spatial models.”
BackgroundMethodGeneralized Least Squares Model Averaging
Liu, Q., Okui, R., & Yoshimura, A. (2015) · Econometric Reviews · doi:10.1080/07474938.2015.1092817 · Cited by 59 · cited 4×
“One way to do this is the Occam’s window algorithm, which was proposed by Madigan and Raftery (1994) for graphical models and extended to linear regression in Raftery et al.”
MethodInfluentialDeterminants of Economic Growth: Will Data Tell?
Ciccone, A., & Jarociński, M. (2008) · American Economic Journal Macroeconomics · doi:10.1257/mac.2.4.222 · Cited by 58 · cited 6×
“Two other well-known R-packages are BAS (Clyde, 2017), explained in Clyde et al. (2011), and BayesVarSel (Garcı́a-Donato and Forte, 2015), described in Garcı́a-Donato and Forte (2016). When endogenous regressors are suspected, the R-package ivbma (Lenkoski et al., 2014) implements the method of Karl and Lenkoski (2012…”
MethodInfluentialBrock, W. A., & Durlauf, S. N. (2001) · World Bank, Washington, DC eBooks · doi:10.1596/17447 · Cited by 57
Two-Stage Bayesian Model Averaging in Endogenous Variable Models
Lenkoski, A., Eicher, T. S., & Raftery, A. E. (2013) · Econometric Reviews · doi:10.1080/07474938.2013.807150 · Cited by 56 · cited 3×
“When endogenous regressors are suspected, the R-package ivbma (Lenkoski et al., 2014) implements the method of Karl and Lenkoski (2012).”
BackgroundMethodThe elusive effects of trade on growth: Export diversity and economic take‐off
Eicher, T. S., & Kuenzel, D. J. (2016) · Canadian Journal of Economics/Revue canadienne d économique · doi:10.1111/caje.12197 · Cited by 55 · cited 6×
“The influence of trade on growth is analysed in Eicher and Kuenzel (2016), who use BMA methods while taking into account the endogeneity of trade variables, through the two-stage BMA approach of Lenkoski et al. (2014).”
BackgroundMethodInfluentialLamnisos, D., Griffin, J. E., & Steel, M. F. J. (2009) · Journal of Computational and Graphical Statistics · doi:10.1198/jcgs.2009.08027 · Cited by 54 · cited 2×
“Details and comparison of popular algorithms can be found in Lamnisos et al. (2009).”
BackgroundSelf-citationLeading indicators of financial stress: New evidence
Vašíček, B., Žigraiová, D., Hoeberichts, M. M., Vermeulen, R., Šmídková, K., & de Haan, J. (2016) · Journal of Financial Stability · doi:10.1016/j.jfs.2016.05.005 · Cited by 54 · cited 2×
“BMA was used to identify the leading indicators of financial stress in 25 OECD countries by Vašı́ček et al. (2017). They find that financial stress is difficult to predict out of sample, either modelling all countries at the same time (as a panel) or individually.”
MethodRevisiting the link between growth and federalism: A Bayesian model averaging approach
Asatryan, Z., & Feld, L. P. (2014) · Journal of Comparative Economics · doi:10.1016/j.jce.2014.04.005 · Cited by 54 · cited 5×
“A specific focus on the effect of measures of fiscal federalism on growth was adopted in Asatryan and Feld (2015).”
BackgroundResultInfluentialDynamic model averaging in large model spaces using dynamic Occam׳s window
Onorante, L., & Raftery, A. E. (2015) · European Economic Review · doi:10.1016/j.euroecorev.2015.07.013 · Cited by 51 · cited 2×
“Finally, Onorante and Raftery (2016) introduce a dynamic Occam’s window to deal with larger model spaces. van der Maas (2014) proposes a dynamic BMA framework that allows for time variation in the set of variables that is included in the model, as well as structural breaks in the intercept and…”
BackgroundWANT EXPORT DIVERSIFICATION? EDUCATE THE KIDS FIRST
Jetter, M., & Hassan, A. R. (2015) · Economic Inquiry · doi:10.1111/ecin.12213 · Cited by 49
Endogeneity and panel data in growth regressions: A Bayesian model averaging approach
León‐González, R., & Montolio, D. (2015) · Journal of Macroeconomics · doi:10.1016/j.jmacro.2015.07.003 · Cited by 48 · cited 2×
“The methodology of León-González and Montolio (2015) is used to deal with endogenous regressors as well as country-specific fixed effects.”
Method
Research works printed but not linked: 22
- Blażejowski Marcin, 2020, Journal of Applied Econometrics. Published ahead of print
- Catania Leopoldo, 2017, Version, 0, 3
- Chen Ming-Hui, 2003, Statistica Sinica, 13, 461
- George E., 1999, Statistical Science, 14, 409
- George Edward I, 1997, Statistica Sinica, 7, 339
- Hanck Christoph, 2016, Economics Bulletin, 36, 2037
- Kapetanios George, 2018, Economic Statistics Centre of Excellence Discussion Paper, 2018
- Kourtellos Andros, 2015, Rimini Centre for Economic Analysis Working Paper, 15
- Leamer Edward E, 1983, American Economic Review, 73, 31
- Leamer Edward E, 1985, American Economic Review, 75, 308
- Lenkoski A., A., 2014, Version, 1, 05
- Li Cong, 2018, Statistica Sinica, 28, 2795
- Liang Faming, 2000, Statistica Sinica, 10, 317
- Mazerolle Marc J, 2017, Version, 2, 3
- Meng Xiao-Li, 1996, Statistica Sinica, 6, 831
- Osiewalski Jacek, 1993, Cuadernos Económicos, 55, 327
- Sabanés Bové Daniel, 2011, Bayesian Analysis, 6, 387, 10.1214/ba/1339616469 · doi:10.1214/ba/1339616469
- Martin Xavier, 1997, American Economic Review, 87, 178
- Shao Jun, 1997, Statistica Sinica, 7, 221
- Volinsky Chris T, 1997, Applied Statistics, 46, 443
- Zeugner Stefan, 2014, Bayesian Model Averaging in R. Version, 0, 3
- Zhang Xinyu, 2019, Statistica Sinica, 29, 693
Cited by
Model averaging prediction by K-fold cross-validation
Zhang, X., & Liu, C.-A. (2023) · Journal of Econometrics · doi:10.1016/j.jeconom.2022.04.007 · Cited by 310
Forecast combinations: An over 50-year review
Wang, X., Hyndman, R. J., Li, F., & Kang, Y. (2023) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2022.11.005 · Cited by 280
“Two main strands can be identified: frequentist approaches (e.g., Fletcher, 2018) and Bayesian approaches (e.g. Steel, 2020).”
BackgroundRemittances and economic growth: A meta-analysis
Cazachevici, A., Havranek, T., & Horvath, R. (2020) · World Development · doi:10.1016/j.worlddev.2020.105021 · Cited by 262
Disease Detection in Apple Leaves Using Deep Convolutional Neural Network
Bansal, P., Kumar, R., & Kumar, S. (2021) · Agriculture · doi:10.3390/agriculture11070617 · Cited by 249
“To predict class probability, the result is computed by calculating the argmax of the summed probabilities for each class. predict class probability, the result is computed by calculating the argmax summed probabilities for 15 of 23 In this approach, every classifier’s contribution remains equal to…”
BackgroundMethodOption Return Predictability with Machine Learning and Big Data
Bali, T. G., Beckmeyer, H., Mörke, M., & Weigert, F. (2023) · The Review of Financial Studies · doi:10.1093/rfs/hhad017 · Cited by 205
Metadata
- Authors
- Steel, M. F. J.
- Affiliations
- University of Warwick (GB)
- Corresponding author
- Steel, Mark F. J.
- ORCID
- Steel, Mark F. J.
- Venue
- Journal of Economic Literature
- Publisher
- American Economic Association
- Published
- 2020-09-01
- Volume
- 58
- Issue
- 3
- Pages
- 644-719
- ISSN
- 0022-0515 (ISSN-L)
- OpenAlex
- W2759653811
- Cited by
- 321
- References
- 278
- Citations by year
- 2026: 33 · 2025: 52 · 2024: 45 · 2023: 52 · 2022: 47 · 2021: 60 · 2020: 20
- FWCI
- 31.67
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Economic Literature (publishedVersion)
- Warwick Research Archive Portal (University of Warwick) (acceptedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Inference
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Applications
- Keywords
- model averaging, model uncertainty, Bayesian model averaging, frequentist model averaging, prior assumptions, covariate selection, normal linear regression, sampling model, growth theory, production modeling, macroeconomic forecasting, econometric model selection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.