This paper presents a new ordinary least squares model averaging method which is proposed to be a preferable alternative to Mallows Model Averaging(MMA), Bayesian Model Averaging (BMA) and naïve simple forecast average. The method is developed to deal with possibly non-nested models and selects forecast weights by minimizing the unbiased estimator of mean-squared forecast error (MSFE). Proposed method also yields forecast confidence intervals with given significance level what is not possible when applying other model averaging methods. In addition out-of-sample simulation and empirical testing proves the supremacy of MSFE model averaging over existing combination approaches.
AkaikeH., Information theory and an extension of the maximum likelihood principle, in: Second International Symposium on Information Theory, PetrocB. and CsakeF., eds, 1973.
2.
AkaikeH., A bayesian extension of the minimum AIC procedure of autoregressive model fitting, Biometrika66 (1979), 237-242.
3.
BatesJ.M. and GrangerC.W.J., The combination of forecasts, Operations Research Quarterly20 (1969), 451-468.
4.
BrockW. and DurlaufS., Growth empirics and reality, World Bank Economic Review15 (2001), 229-272.
5.
BrockW., DurlaufS. and WestK.D., Policy analysis in ucertain economic environments, Brookings Papers on Economic Activity1 (2003), 235-322.
6.
BucklandS.T., BurnhamK.P. and AugustinN.H., Model selection: An integral part of inference, Biometrics53 (1997), 603-618.
7.
BurnhamK.P. and AndersonD.R., Model selection and multimodel inference: A practical information-theoretic approach, Second ed., Springer, New York, 2002.
8.
ClemenR.T., Combining forecasts: A review and annotated bibliography, International Journal of Forecasting5 (1989), 559-581.
9.
FernandezC., LeyE. and SteelM.F.J., Benchmark priors for bayesian model averaging, Journal of Econometrics100 (2001), 381-427.
10.
GarrattA., LeeK., PesaranM.H. and ShinY., Forecasting uncertainties in in macroeconomic modelling: An application to the UK economy, Journal of the American Statistical Association98 (2003), 823-838.
11.
GrangerC.W.J., Combining forecasts - twenty years later, Journal of Forecasting8 (1989), 167-173.
12.
GrangerC.W.J. and RamanathanR., Improved methods of combining forecast accuracy, Journal of Forecasting19 (1984), 197-204.
13.
HansenB.E., Least squares model averaging, Econometrica75 (2007), 1175-1189.
14.
HansenB.E., Least-squares forecast averaging, Journal of Econometrics146 (2008), 342-350.
15.
HansenB.E., Model averaging, asymptotic risk and regressor groups, Quantitative Economics5 (2014), 495-530.
16.
HansenB.E. and RacineJ.S., Jackknife model averaging, Journal of Econometrics167 (2012), 38-46.
17.
HendryD.F. and ClementsM.P., Pooling of forecasts, Econometrics Journal5 (2002), 1-26.
18.
HoetingJ.A., MadiganD., RafteryA.E. and VolinskyC.T., Bayesian model averaging: A tutorial, Statistical Science14(4) (1999), 382-417.
19.
IngC.-K., Multistep prediction in autoregressive processes, Econometric Theory19 (2003), 254-279.
20.
IngC.-K., Selecting optimal multistep predictors for autoregressive processes of unknown order, Annals of Statistics32 (2004), 693-722.
21.
IngC.-K., Accumulated prediction errors, information criteria and optimal forecasting for autoregressive time series, Annals of Statistics35 (2007), 1238-1277.
22.
IngC.-K. and WeiC.-Z., On same-realization prediction in an infinite-order autoregressive process, Journal of Multivariate Analysis85 (2003), 130-155.
23.
IngC.-K. and WeiC.-Z., Order selection for same-realization predictions in autoregressive processes, Annals of Statistics33 (2005), 2423-2474.
24.
LeeS. and KaragrigoriouA., An asymptotically optimal selection of the order of a linear process, Sankhya Series A63 (2001), 93-106.
25.
MallowsC.L., Some comments on Cp, Technometrics15 (1973), 661-675.
26.
MinC.-K. and ZellnerA., Bayesian and non-bayesian methods for combining models and forecasts with applications to forecasting international growth rates, Journal of Econometrics56 (1993), 89-118.
27.
MoodA., GraybillF. and BoesD., Introduction to the Theory of Statistics, 3rd ed., McGraw-Hill, 1974, pp. 229.
28.
NydickS.W., The Wishart and Inverse Wishart Distributions, 2012. [Online]. Available: http://wwwtc.umn.edu/nydic001/docs/unpubs/ Wishart_Distribution.pdf.
29.
RafteryA.E., MadiganD.H. and JenniferA.H., Bayesian model averaging for linear regression models, Journal of the American Statistical Association92(437) (1997), 179-191.
30.
RissanenJ., Order estimation by accumulated prediction errors, Journal of Applied Probability23A (1986), 55-61.
31.
Sala-i-MartinX., DoppelhoferG.M. and RonaldI., Determinants of long-term growth: A bayesian averaging of classical estimates (BACE) approach, American Economic Review94 (2004), 813-835.
32.
SchwartzG., Estimating the dimension of a model, Annals of Statistics6 (1978), 461-464.
33.
ShibataR., Asymptotically efficient selection of the order of the model for estimating parameters of a linear process, Annals of Statistics8 (1980), 147-164.
34.
ShibataR., An optimal selection of regression variables, Biometrika68 (1981), 45-54.
35.
ShibataR., Asymptotic mean efficiency of a selection of regression variables, Annals of the Institute of Statistical Mathematics35 (1983), 415-423.
36.
StockJ.H. and WatsonM.W., A comparison of linear and nonlinear univariate models for forecasting macroeconomic time series, in: Cointegration, Causality and Forecasting: A Festschrift for Clive WJ Granger, EngleR. and WhiteH., eds, Oxford University Press, 1999.
37.
StockJ.H. and WatsonM.W., Combination forecasts of output growth in a seven-country data set, Journal of Forecasting23 (2004), 405-430.
38.
StockJ.H. and WatsonM.W., An empirical comparison of methods for forecasting using many predictors, Working Paper, NBER, 2005.
39.
StockJ.H. and WatsonM.W., Forecasting with many predictors, in: Handbook of Economic Forecasting, ElliottG., GrangerC.W.J. and TimmermannA., eds, Elsevier, Amsterdam1 2006, pp. 515-554.
40.
TimmermannA., Forecast combinations, in: Handbook of Economic Forecasting, ElliottG., GrangerC.W.J. and TimmermannA., eds, Elsevier, Amsterdam12006, pp. 135-196..
41.
WishartJ., The generalized product moment distribution in samples from a normal multivariate population, Biometrica20A (1928), 32-52.
42.
WrightJ.H., Bayesian model averaging and exchange rate forecasting, Federal Reserve Board International Finance Discussion Papers (2003), 779.
43.
WrightJ.H., Forecasting US inflation by bayesian model averaging, Federal Reserve Board International Finance Discussion Papers (2003), 780.
44.
ZubakinV.A., KosorukovO.A. and MoiseevN.A., Improvement of regression forecasting models, Modern Applied Science9(6) (2015), 344-353.
