手法を比較

	Model Confidence Set	Diebold-Mariano予測精度等価性検定	ステップワイズ回帰
分野	計量経済学	計量経済学	統計学
系統	Hypothesis test	Hypothesis test	Regression model
提唱年	2011	1995	1960
提唱者	Hansen, Lunde & Nason	Francis Diebold & Roberto Mariano	M. A. Efroymson
種類	Sequential hypothesis testing procedure for model comparison	Non-parametric forecast comparison test	Automated variable selection
原典	Hansen, P. R., Lunde, A., & Nason, J. M. (2011). The model confidence set. Econometrica, 79(2), 453–497.	Diebold, F. X., & Mariano, R. S. (1995). Comparing predictive accuracy. Journal of Business & Economic Statistics, 13(3), 253–263.	Efroymson, M. A. (1960). Multiple regression analysis. In A. Ralston & H. S. Wilf (Eds.), Mathematical Methods for Digital Computers (pp. 191–203). Wiley.
別名	MCS Procedure, Superior Set of Models, Model Selection Confidence Set, Model Güven Kümesi	DM Test, Test of Equal Forecast Accuracy, Diebold-Mariano Forecast Comparison Test, Tahmin Doğruluğu Eşitliği Testi	stepwise selection, forward stepwise regression, backward stepwise regression, forward-backward selection
関連	3	3	5
概要	The Model Confidence Set (MCS) is a sequential hypothesis-testing procedure introduced by Hansen, Lunde, and Nason (2011) that identifies the smallest collection of forecasting or predictive models statistically indistinguishable from the best-performing model at a given confidence level. Instead of selecting a single winner, MCS returns a set of superior models, making it especially valuable in econometric forecast comparisons where the true best model is unknown.	The Diebold-Mariano (DM) test, introduced by Diebold and Mariano in 1995, is a widely used non-parametric procedure for formally comparing the predictive accuracy of two competing forecasting models. It evaluates whether the difference in forecast errors between two models is statistically significant, without requiring nested models or specific distributional assumptions about the forecasts, making it broadly applicable across economics, finance, and time-series analysis.	Stepwise regression is an automated variable selection procedure for multiple linear regression that adds or removes predictor variables one at a time according to a statistical criterion, typically the F-statistic or a p-value threshold. The forward-selection algorithm was formally described by Efroymson (1960) and the bidirectional variant was popularised by Draper and Smith in their landmark 1966 text Applied Regression Analysis. Despite widespread historical use, the method is now widely critiqued, making its documentation essential in any canonical methods library.