“反事实”思想在宏观政策效应评估中的应用
|
摘要
制定、实施政策是政府发挥职能的重要手段，当前中国经济正处于高速发展阶段，社会改革也在逐步深化，政策、规则的改变频频发生，为降低政策成本，促进政府决策的科学性，提高政府的宏观调控能力，亟需对政策实施的效果进行量化评估。通过构建“反事实”进行政策效应评估是当前政策评价研究中的热点，但这一思想在宏观经济领域并未取得太多进展，制约了宏观政策效应评估理论与实践的发展。
由于微观数据与宏观数据的数据特征不同，当前微观经济学中广泛使用的“反事实”构建方法，如双重差分方法（DID）、匹配方法（Matching）等都不能应用于宏观政策效应评估。而目前宏观政策效应评估中的主流方法，如向量自回归模型（VAR）、动态随机一般均衡模型（DSGE）等都需要设定多个结构模型，搜集大量的数据，运用复杂的求解技术求解，工作量巨大且在因果推断上也存在着不足。因此，在政策效应评估的实践中，亟需以“反事实”思想为指导，探索适用于宏观政策效应评估的新方法。在此背景下，本文引入Hsia（o2010）提出的利用面板数据截面之间的相关性构建“反事实”，进而进行政策效应评估的新方法，并围绕该方法进行一系列的理论和实证分析。
在介绍Hsiao方法的理论模型的基础上，本文就模型中的关键假设——条件独立假设进行重点分析，并使用蒙特卡罗模拟技术，就理论模型对关键假设的敏感性进行数值模拟。其次，设计两个案例分析，分别以西部大开发和中国应对金融危机的“四万亿”刺激计划为例，对这一方法的应用步骤和应注意的问题进行详尽的阐述。两个案例的侧重点有所不同，西部大开发案例满足该模型的关键假定，“四万亿”刺激计划或多或少会违背该假定，但可以通过各种技术选择合适的控制组。本文在前一案例中重点阐述了关键假设的检验，在后一案例中设计了对比模型，用实际数据分析关键假设的违背对政策效应测算的影响情况。经过理论分析和实证分析，本文得出如下结论：
理论分析的结果表明，Hsiao方法的结果对关键假设非常敏感，即使是关键假设的轻度违背，也会对模型结果产生显著影响。因此，判断案例是否适用该方法，是使用模型前必须要考虑的问题。同时，因为实际数据的产生机制未知，这一关键假设无法通过统计方法进行检验，只能经过充分翔实的论证进行判断。在实际中，若关键假设不能满足，则应采用DID等其他方法进行政策效应评估。与结构方程模型相比，该方法省去了具体的结构模型设立过程，能规避政策效应评估中难以解决的内生性问题，且能够反映外部冲击的影响，具有模型简捷、数据需求量小、运算简单等优势，对宏观政策效应评估的实践具有重要意义。
实证分析的结果表明，西部大开发对于缩小中东部与西部地区的相对差距至关重要，西部大开发的实施使得重庆人均GDP增长率增加了约2.24个百分点，各年的政策效应基本保持稳定，这一结果与刘生龙（2009）的研究结论近似，证明Hsiao方法具有较强的效力。但与其余学者的研究结论不同，本文对“四万亿”刺激计划的政策效应分析结果显示，2009年-2011年“四万亿”计划对各年经济增长的贡献分别为0.928、-0.575、0.021个百分点，整个研究区间内对GDP增长率的整体效应为0.138个百分点，几近于零。因此，“四万亿”刺激计划短期内效果显著，但对长期经济增长没有明显的促进作用。这表明，政府在实施大规模的扩张性财政政策时，应充分考虑政策的挤出效应，并关注由此引发的通胀等因素的副作用。
Formulating and implementing policies is an important means for governments to realizetheir function. Recently, Chinese economy is in a stage of rapid development, and social reform isgradually deepening, policies and rules change frequently. In order to reduce the cost of policy,promote the scientific nature of government decision-making, and enhance the government'sability of macroeconomic control, evaluation the effect of implemented policies is tremendouslyneeded. Evaluating policy effect through "counterfactual" constructing is a hot topic in the studyof policy evaluation, but this idea has not made much progress in macroeconomic field, whichrestricts the theory and practice development of macroeconomic policy evaluation.
As the characteristics of Micro and Macro data are different, the widely used methods for"counterfactual" construction in microeconomics, such as Difference-in-differences and matching,are not possible to be applied to macroeconomic policy evaluation. While the main methodrecently used in macroeconomic policy evaluation, such as vector autoregressive model, dynamicstochastic general equilibrium model also have some shortcomings. For example, they requires toset up several structure models, collecting large amounts of data, solved by solving complex, theworkload is huge and there exists difficulty in causal inference. Therefore, we need to take the"counterfactual" thought as the guide, and to explore new methods suitable for macroeconomicpolicy evaluation. Under this background, this paper introduced a new method proposed by Hsiao(2010), which used the correlation between cross-sections of panel dada to build "counterfactual"and estimated the policy effect, and conducted a series of theoretical and empirical analysis aroundthe method.
Based on the introduction of Hsiao’s theoretical model, this paper focused on the analysis ofthe key assumption in the model--conditional independence assumption, and used Monte Carlosimulation techniques to see how sensitive the empirical result was to the assumption. Secondly,this paper took Western Development Program and China's "Four Trillion" Stimulus Package asexamples, elaborated the application steps of this method and the problems that should be noticed.The case of Western Development Program met the key assumptions, while the latter violated thisassumption more or less, but we made it satisfy the critical assumption through a variety oftechniques. In the analysis of the former case, we focused on the inspection of key assumptions. As is regard to the latter case, we designed comparison model, and used the real data to figure outthe influence of the key assumption on policy effect calculation. Through the theoretical analysisand empirical analysis, the paper draws the following conclusion:
The theoretical analysis results show that, the result of the Hsiao’s method is very sensitive tothe critical assumptions, even if slight violation would have great impact on the empirical results.Therefore, we should consider the applicability of the method before using the model. At the sametime, because the actual data generation mechanism is unknown, the key hypothesis cannot betested by statistical methods, only be judged by fully detailed proof. In practice, if the keyassumption is not satisfied, one should adopt DID and other methods to evaluate the policy effect.Compared with the structural models, this method does not have to establish structure equations,and avoids solving the problem of endogeneity that’s common in the field of policy evaluation. Inaddition, it’s easy to reflect the impact of external shocks.After all, this model is simple, requiressmall amount of data, and easy to solve. As there are so many advantages, Hsiao’s method willhave important influence in the practice of macroeconomic policy evaluation.
The results of the empirical analysis show that, Western Development Program is essential innarrowing the gap between western regions and the other areas. Western Development Programhas raised the real GDP growth rate of Chongqing by2.24percentage during the year2000and2007, and this effect is steady around years. This result is similar to that of Liu Shenglong (2009),indicating that Hsiao’s method is effective. But contrary to the research conclusions of otherscholars, empirical analysis of the effect of China's "Four Trillion" Stimulus Package shows thatthe investment raised the real GDP growth rate by0.93percentage in2009,-0.575percentage in2010, and0.021percentage in2011. In the whole study interval, the overall effect is0.138percentage points, almost zero. The results indicate that for China, the Stimulus Package hasplayed a considerable role in stopping its recession in the global financial crisis, but it will notaffect the economy significantly in the long run. This Indicates that the government should takethe crowding-out effect into consideration, and focus on side effects of inflation and other factorscaused by this policy while implementing expansionary fiscal policies.
由于微观数据与宏观数据的数据特征不同，当前微观经济学中广泛使用的“反事实”构建方法，如双重差分方法（DID）、匹配方法（Matching）等都不能应用于宏观政策效应评估。而目前宏观政策效应评估中的主流方法，如向量自回归模型（VAR）、动态随机一般均衡模型（DSGE）等都需要设定多个结构模型，搜集大量的数据，运用复杂的求解技术求解，工作量巨大且在因果推断上也存在着不足。因此，在政策效应评估的实践中，亟需以“反事实”思想为指导，探索适用于宏观政策效应评估的新方法。在此背景下，本文引入Hsia（o2010）提出的利用面板数据截面之间的相关性构建“反事实”，进而进行政策效应评估的新方法，并围绕该方法进行一系列的理论和实证分析。
在介绍Hsiao方法的理论模型的基础上，本文就模型中的关键假设——条件独立假设进行重点分析，并使用蒙特卡罗模拟技术，就理论模型对关键假设的敏感性进行数值模拟。其次，设计两个案例分析，分别以西部大开发和中国应对金融危机的“四万亿”刺激计划为例，对这一方法的应用步骤和应注意的问题进行详尽的阐述。两个案例的侧重点有所不同，西部大开发案例满足该模型的关键假定，“四万亿”刺激计划或多或少会违背该假定，但可以通过各种技术选择合适的控制组。本文在前一案例中重点阐述了关键假设的检验，在后一案例中设计了对比模型，用实际数据分析关键假设的违背对政策效应测算的影响情况。经过理论分析和实证分析，本文得出如下结论：
理论分析的结果表明，Hsiao方法的结果对关键假设非常敏感，即使是关键假设的轻度违背，也会对模型结果产生显著影响。因此，判断案例是否适用该方法，是使用模型前必须要考虑的问题。同时，因为实际数据的产生机制未知，这一关键假设无法通过统计方法进行检验，只能经过充分翔实的论证进行判断。在实际中，若关键假设不能满足，则应采用DID等其他方法进行政策效应评估。与结构方程模型相比，该方法省去了具体的结构模型设立过程，能规避政策效应评估中难以解决的内生性问题，且能够反映外部冲击的影响，具有模型简捷、数据需求量小、运算简单等优势，对宏观政策效应评估的实践具有重要意义。
实证分析的结果表明，西部大开发对于缩小中东部与西部地区的相对差距至关重要，西部大开发的实施使得重庆人均GDP增长率增加了约2.24个百分点，各年的政策效应基本保持稳定，这一结果与刘生龙（2009）的研究结论近似，证明Hsiao方法具有较强的效力。但与其余学者的研究结论不同，本文对“四万亿”刺激计划的政策效应分析结果显示，2009年-2011年“四万亿”计划对各年经济增长的贡献分别为0.928、-0.575、0.021个百分点，整个研究区间内对GDP增长率的整体效应为0.138个百分点，几近于零。因此，“四万亿”刺激计划短期内效果显著，但对长期经济增长没有明显的促进作用。这表明，政府在实施大规模的扩张性财政政策时，应充分考虑政策的挤出效应，并关注由此引发的通胀等因素的副作用。
Formulating and implementing policies is an important means for governments to realizetheir function. Recently, Chinese economy is in a stage of rapid development, and social reform isgradually deepening, policies and rules change frequently. In order to reduce the cost of policy,promote the scientific nature of government decision-making, and enhance the government'sability of macroeconomic control, evaluation the effect of implemented policies is tremendouslyneeded. Evaluating policy effect through "counterfactual" constructing is a hot topic in the studyof policy evaluation, but this idea has not made much progress in macroeconomic field, whichrestricts the theory and practice development of macroeconomic policy evaluation.
As the characteristics of Micro and Macro data are different, the widely used methods for"counterfactual" construction in microeconomics, such as Difference-in-differences and matching,are not possible to be applied to macroeconomic policy evaluation. While the main methodrecently used in macroeconomic policy evaluation, such as vector autoregressive model, dynamicstochastic general equilibrium model also have some shortcomings. For example, they requires toset up several structure models, collecting large amounts of data, solved by solving complex, theworkload is huge and there exists difficulty in causal inference. Therefore, we need to take the"counterfactual" thought as the guide, and to explore new methods suitable for macroeconomicpolicy evaluation. Under this background, this paper introduced a new method proposed by Hsiao(2010), which used the correlation between cross-sections of panel dada to build "counterfactual"and estimated the policy effect, and conducted a series of theoretical and empirical analysis aroundthe method.
Based on the introduction of Hsiao’s theoretical model, this paper focused on the analysis ofthe key assumption in the model--conditional independence assumption, and used Monte Carlosimulation techniques to see how sensitive the empirical result was to the assumption. Secondly,this paper took Western Development Program and China's "Four Trillion" Stimulus Package asexamples, elaborated the application steps of this method and the problems that should be noticed.The case of Western Development Program met the key assumptions, while the latter violated thisassumption more or less, but we made it satisfy the critical assumption through a variety oftechniques. In the analysis of the former case, we focused on the inspection of key assumptions. As is regard to the latter case, we designed comparison model, and used the real data to figure outthe influence of the key assumption on policy effect calculation. Through the theoretical analysisand empirical analysis, the paper draws the following conclusion:
The theoretical analysis results show that, the result of the Hsiao’s method is very sensitive tothe critical assumptions, even if slight violation would have great impact on the empirical results.Therefore, we should consider the applicability of the method before using the model. At the sametime, because the actual data generation mechanism is unknown, the key hypothesis cannot betested by statistical methods, only be judged by fully detailed proof. In practice, if the keyassumption is not satisfied, one should adopt DID and other methods to evaluate the policy effect.Compared with the structural models, this method does not have to establish structure equations,and avoids solving the problem of endogeneity that’s common in the field of policy evaluation. Inaddition, it’s easy to reflect the impact of external shocks.After all, this model is simple, requiressmall amount of data, and easy to solve. As there are so many advantages, Hsiao’s method willhave important influence in the practice of macroeconomic policy evaluation.
The results of the empirical analysis show that, Western Development Program is essential innarrowing the gap between western regions and the other areas. Western Development Programhas raised the real GDP growth rate of Chongqing by2.24percentage during the year2000and2007, and this effect is steady around years. This result is similar to that of Liu Shenglong (2009),indicating that Hsiao’s method is effective. But contrary to the research conclusions of otherscholars, empirical analysis of the effect of China's "Four Trillion" Stimulus Package shows thatthe investment raised the real GDP growth rate by0.93percentage in2009,-0.575percentage in2010, and0.021percentage in2011. In the whole study interval, the overall effect is0.138percentage points, almost zero. The results indicate that for China, the Stimulus Package hasplayed a considerable role in stopping its recession in the global financial crisis, but it will notaffect the economy significantly in the long run. This Indicates that the government should takethe crowding-out effect into consideration, and focus on side effects of inflation and other factorscaused by this policy while implementing expansionary fiscal policies.
引文
7国务院发展研究中心、世界自然基金会：《中国经济刺激计划对气候和能源的影响》，2011年2月。
8王秀萍.金砖四国也能够对金融危机措施及效果[J].企业家天地，2011（4）：9-10.
ABADIE A, J GARDEAZABAL. The Economic Costs of Conflict: A Case Study of the BasqueCountry [J]. American Economic Review,2003,93:113-132.
AND J HAINMUELLER.Synthetic Control Methods for Comparative CaseStudies: Estimating the Effect of California’s Tobacco Control Program [J].Journal of theAmerican Statistical Association,2010,105:493-505.
ACEMOGLU, DARON, SIMON JOHNSON, et al. The Colonial Origins of ComparativeDevelopment: An Empirical Investigation [J]. American Economic Review,2001,91:1369-1401.
AMEMIYA, T. Advanced Econometrics [M].Cambridge: Harvard University Press,1985.
ANGRIST, JOSHUA D.Lifetime Earnings and the Vietnam Era Draft Lottery: Evidence fromSocial Security Administrative Records [J].American Economic Review,1990,80:313-336.
AND ALAN B KRUEGER. Does Compulsory School Attendance Affect
Schooling and Earnings [J].Quarterly Journal of Economics,1991,106:976–1014.
AND VICTOR LAVY. Using Maimonides’ Rule to Estimate the Effect of Class
Size on Scholastic Achievement [J]. Quarterly Journal of Economics,1999,114:533-575.
AND PISCHKE STEFFEN J. Mostly Harmless Econometrics: An Empiricist’s
Companion[M]. Princeton: Princeton University Press,2008.
AND PISCHKE STEFFEN J.The Credibility Revolution in Empirical Economics:How Better Research Design is Taking the Con out of Econometrics[R]. NBER Working Paper15794,2010.
ANDREA PUFAHL, C R. Evaluating the Effects of Farm Programs:Results from PropensityScore Matching [J]. Modelling of Agricultural and Rural Development Policies,2008,80:1-15.
BAI J, S NG. Determining the Number of Factors in Approximate Factor Models [J].Econometrica,2002,70:191-221.
Inferential Theory for Factor Models of Large Dimensions [J].Econometrica,2003,71:135-171.
AND S NG.Confidence Intervals for Diffusion Index Forecasts and Inference forFactor-augmented Regressions[J]. Manuscript, University of Michigan,2005.
AND S NG. Determining the Number of Primitive Shocks in Factor Models[J].Manuscript, University of Michigan,2005.
BARRO, ROBERT J, CHARLES J REDLICK. Macroeconomic Effects from GovernmentPurchases and Taxes[R]. NBER Working Paper15369,2009
BASSI L. The Effect of CETA on the Post-Program Earnings of Participants[J]. Journal of HumanResources,1983,18:539-556.
Estimating the Effects of Training Programs with Nonrandom Selection[J]. Reviewof Economics and Statistics,1984,66:36-43.
BELL B, BLUNDELL R, VAN REENEN J. Getting the Unemployed Back to Work: anEvaluation of the New Deal Proposals [J]. International Tax and Public Finance,1999,6:339–360.
BERNANKE B S, J BOIVIN. Monetary Policy in a Data-rich Environment [J]. Journal ofMonetary Economics,2003,50:525-546.
AND P ELIASZ. Measuring the Effects of Monetary Policy: a Factor-augmentedVector Autoregressive (FAVAR) Approach [J]. Quarterly Journal of Economics,2005,120:387-422.
BJORKLUND A, MOFFITT R. The Estimation of Wage Gains and Welfare Gains inSelf-Selection Models [J]. Reviews of Economics and Statistics,1987,69:42-49.
BLEAKLEY, HOYT. Disease and Development: Evidence from Hookworm Eradication in theAmerican South [J]. Quarterly Journal of Economics,2007,122:73-117.
BLUNDELL, R, COSTA DIAS, M. Evaluation Methods for Non-Experimental Data. FiscalStudies,2000,21:427-468.
BOUND JOHN, DAVID JAEGER, REGINA BAKER. Problems with Instrumental VariablesEstimation when the Correlation between the Instruments and the Endogenous ExplanatoryVariable is Weak [J].Journal of the American Statistical Association,1995,90:443-450.
CARD, DAVID, ALAN B KRUEGER. Does School Quality Matter? Returns to Education and theCharacteristics of Public Schools in the United States [J]. Journal of Political Economy,1992,100:1-40.
School Quality and Black–White Relative Earnings: A Direct Assessment [J].Quarterly Journal of Economics,1992,120:151-200.
Minimum Wages and Employment: A Case Study of the Fast-Food Industry in NewJersey and Pennsylvania [J].American Economic Review,1994,84:772-793.
CHARLES O JONES. An Introduction to the Study of Public Policy [M].3rd ed. Monetary,California: Brooks/Cole Publishing Company,1984.
COVA P, PISAN M, REBUCCI A. Macroeconomic Effects of China’s Fiscal Stimulus [R].Inter-American Development Bank: working paper, No IDB-WP-211,2010.
DANIEL LERNER, HAROLD D LASSWELL.Policy Sciences [M].Stanford University Press,1966.
DANIEL O GILLIGAN, JOHN HODDINOTT. The Impact of Ethiopia’s Productive Safety NetProgramme and its Linkages [R]. IFPRI Discussion Paper No.00839,2008.
DAVID NACHMIAS, CHAVA FRANKFORT NACHMIAS. Research Methods in the SocialSciences [M]. New York: St. Martin's Press,1976.
DIAO XINSHEN, Z YUMEI, Z C KEVIN. The Global Recession and China’s Stimulus Package:A General Equilibrium Assessment of Country Level Impacts [J]. China Economic Review,2012,23:1-17.
DONOHUE, JOHN J, JUSTIN WOLFERS. Uses and Abuses of Empirical Evidence in the DeathPenalty Debate [J]. Stanford Law Review,2005,58:791–845.
EHRLICH, ISAAC. The Deterrent Effect of Capital Punishment: A Question of Life and Death [J].American Economic Review,1975,65:397-417.
Capital Punishment and Deterrence: Some Further Thoughts and AdditionalEvidence [J]. Journal of Political Economy,1977,85:741-788.
On the Issue of Causality in the Economic Model of Crime and Law Enforcement:Some Theoretical Considerations and Experimental Evidence [J]. American Economic Review,1987,77:99-106.
Crime, Punishment, and the Market for Offenses [J]. Journal of EconomicPerspectives,1996,10:43-67.
FORNI, M, HALLIN, M, LIPPI, M, ET AL. The Generalized Dynamic Factor Model:Identifcation and Estimation [J]. Review of Economics and Statistics,Forthcoming,1999.
The Generalized Factor Model: Identification and Estimation [J]. The Review ofEconomics and Statistics,2000,82:540–554.
Dynamic Common Factors in Large Cross-sections [J]. Empirical Economics,2002,21:27–42.
GIANNONE, D, L REICHLIN, L SALA. Monetary Policy in Real Time[J].//Mark Gertler,Kenneth Rogoff.NBER Macroeconomics Annual2004[M]. MIT Press,2005:161-200.
GOLDBERGER, A. Best Linear Unbiased Prediction in the Generalized Linear Regression Model[J]. Journal of the American Statistical Association,1962,57:369-375.
GREGORY, A, A HEAD. Fluctuations in Productivity, Investment, and the Current Account [J].Journal of Monetary Economics,1999,44:423-452.
HAHN, TODD, VANDER KLAAUW.Identification and Estimation of Treatment Effects with aRegression Discontinuity Design [J]. Econometrica,2001,69:201-209.
HECKMAN, J J AND E J VYTLACIL. Local Instrumental Variables [M]//C Hsiao, K Morimuneand J L Powell. Nonlinear Statistical Modeling. Cambridge: Cambridge University Press,2001:1-46.
AND V J HOTZ. Choosing Among Alternative Nonexperimental Methods forEstimating the Impact of Social Programs: The Case of Manpower Training [J]. Journal of theAmerican Statistical Association,1989,84:862-874.
HE DONG, ZHANG ZHIWEI, ZHANG WENLANG. How Large Will Be the Effect of China’sFiscal Stimulus Package on Output and Employment [J]. Pacific Economic Review,2009,14:730-744.
HOXBY, C M. The Effects of Class Size on Student Achievement:New Evidence fromPopulation Variation [J].Quarterly Journal of Economics,2000,115:1239-1285.
HSIAO, C. Autoregressive Modelling and Causal Ordering of Economic Variables[J]. Journal ofEconomic Dynamics and Control,1982,4:243-259.
Analysis of Panel Data [M].2nd ed. New York: Cambridge University Press,2003.
AND A K TAHMISCIOGLU. A Panel Analysis of Liquidity Constraints and FirmInvestment [J]. Journal of the American Statistical Association,1997,92:455-465.
H STEVE CHING AND SHUI KI WAN.A Panel Data Approach for ProgramEvaluation: Measuring the Benefts of Political and Economic Integration of Hong Kong withChina [J]. Journal of Applied Econometrics,2012,27:705-740.
AND S WAN. To Combine or not to Combine Forecasts. Mimeo,2009.
H STEVE CHING, HSIAO, C, S WAN, ET AL. Economic Benefits of Globalization: The Impactof Entry to the WTO on China’s Growth [J]. Pacific Economic Review,2011,16:285-301.
JAMES J HECKMAN. Effects of Child-Care Programs on Women's Work Effort [R/OL].National Bureau of Economic Research,1974:136-169. http://www.nber.org/chapters/c3687.
Sample Selection Bias as a Specification Error [J]. Econometrica,1979,65:153-179.
Econometric causality [J]. International Statistical Review,2008,52:1-27.
AND ROBB R. Alternative Methods for Evaluating the Impact of Interventions[M]//JAMES J HECKMAN, SINGER B. Longitudinal Analysis of Labor Market Data. NewYork: Cambridge University Press,1985:352.
AND ROBB R. Alternative Methods For Solving The Problem of Selection Bias inEvaluating The Impact of Treatments on Outcomes [M]//WAINER H. Drawing Inferences fromSelf-Selected Samples. Berlin: Springer-Verlag,1986.
Instrumental Variables: A Study of Implicit Behavioral Assumptions Used in MakingProgram Evaluations[J].The Journal of Human Resources,1997,32:441-462.
AND H I. Matching as an Econometric Evaluation Estimator: Evidence fromEvaluating a Job Training Programme [J]. The Review of Economic Studies,1997,77:605-654.
SMITH J AND CLEMENTS N. Making the Most Out of Program Evaluations andSocial Experiments: Accounting for Heterogeneity in Program Impacts[J].Review of EconomicStudies,1997,64:487-536.
KANNIKA D, CHENG HSIAO, XUEYAN ZHAO. Decriminalization and Marijuana SmokingPrevalence: Evidence From Australia [J].Journal of Bisiness and Econometrics,2010,38:344-356.
KAPETANIOS G, MUMTAZ H, STEVENS I, ET AL.Assessing the Economy Wide Effects ofQuantitative Easing [R]. Bank of England Working paper No.443,2012.
LALIVE, R. How do Extended Benefits Affect Unemployment Duration? A RegressionDiscontinuity Approach[J]. Journal of Econometrics,2008,142:785-806.
LALONDE, R. Evaluating the Econometric Evaluations of Training Programs with ExperimentalData [J]. American Economic Review,1986,76:604-620.
LEAMER, EDWARD. Let’s Take the Con Out of Econometrics[J]. American Economic Review,1978,73:31-43.
LEE D S. Randomized Experiments from Non-random Selection in US House elections[J].Journal of Econometrics,2008,144:675-697.
LUCAS, ROBERT E. What Economists Do. Unpublished,1988.
MCCRARY, JUSTIN. Manipulation of the Running Variable in the Regression DiscontinuityDesign: A Density Test [J]. Journal of Econometrics,2008,142:698-714.
MICHAEL HOWLETT, M RAMESH. Studying Public Policy: Policy Cycles and PolicySubsystems [M]. Oxford University Press,1995.
OKUI, R. The Optimal Choice of Moments in Dynamic Panel Data Models [J].Journal ofEconometrics,2009,151:1-161.
PERKINS S M, T W. For Objective Causal Inference: Design Trumps Analysis [J].The Annual ofApplied Atatistics,2000,48:93-101.
PERSSON TORSTEN, GUIDO TABELLINI. The Growth Effect of Democracy: Is itHeterogeneous and How Can it be Estimated [M]//E Helpman. Institutions and EconomicPerformance.Cambridge: Harvard University Press,2008.
PESARAN, M H, L V SMITH, R P SMITH. What if the UK or Sweden Had Joined the Euro in1999? An Empirical Evaluation Using a Global VAR[J]. International Journal of Finance andEconomics,2007,12:55-87.
AND SMITH R P. Counterfactual Analysis in Macro Econometrics: An EmpiricalInvestigation into the Effects of Quantitative Easing[R].IZA Discussion Paper No.6618,2012.
PUHANI P A.Poland on the Dole: The Effect of Reducing the Unemployment Benefit EntitlementPeriod[J]. Journal of Population Economics,2000,59:35-44.
RAMEY, VALERIE, AND MATTHEW D. SHAPIRO. Costly Capital Reallocation and the Effectsof Government Spending.” Carnegie-Rochester Conference Series on Public Policy,1998,48:145-194.
RAO, C R. Linear Statistical Inference and It’sApplications[M].2nd ed., New York:Wiley,1973.
RICHARDSON, GARY, AND WILLIAM TROOST. Monetary Intervention Mitigated BankingPanics during the Great Depression: Quasi-Experimental Evidence from a Federal ReserveDistrict Border,1929-1933[J].Journal of Political Economy,2009,117:1031-1073.
ROBERT W F. Railroads and American Economic Growth: Essays in Economic History [M].Baltimore: The Johns Hopkins University Press,1964.
ROMER, CHRISTINA D, DAVID H ROMER. Does Monetary Policy Matter? A New Test in theSpirit of Friedman and Schwartz [J].NBER Macroeconomics Annual,1989,4:121-70.
A New Measure of Monetary Shocks: Derivation and Implications [J]. AmericanEconomic Review,2004,4:1055-1084.
The Macroeconomic Effects of Tax Changes:Estimates Based on a New Measure ofFiscal Shocks[R]. NBER Working Paper No.13264,2007.
ROSENBAUM P, R D. The Central Role of the Propensity Score in Observational Studies forCausal Effects [J]. Biometrika,1983,84:41-55.
SANDRA CAVACO D F. Estimating the Effect of a Retraining Program on the Re-EmploymentRate of Displaced Workers [R].The Institute for the Study of Labor Working Paper,2009.
SARGENT, T J,C A SIMS. Business Cycle Modeling without Pretending to Have Too MuchA-Priori Economic Theory [M]//C SIMS, ET.AL. New Methods in Business Cycle Research.Minneapolis: Federal Reserve Bank of Minneapolis,1977.
SHAOHUA CHEN, R M. Are There Lasting Impacts of Aid to Poor Areas [R].World Bank PolicyResearch Working Paper4084,2008.
SIMS, CHRISTOPHER A. Macroeconomics and Reality [J].Econometrica,1980,48:1-48.
Uncertainty across Models [J]. American Economic Review,1988,78:163-167.
STEWART M B. The Employment Effects of the National Minimum Wage [J].The EconomicJournal,2004,63:110-116.
STOCK, J H, WATSON M W. New Indexes of Coincident and Leading Economic Indications[M]//O J BLANCHARD, S FISCHER. NBER Macroeconomics Annual. Cambridge MA: MITPress,1989.
Diffusion Indexes [R]. NBER Working Paper6702,1998.
Forecasting Infation[J]. Journal of Monetary Economics,1999,44:293–335.
Macroeconomic Forecasting Using Diffusion Indexes [J]. Journal of Business andEconomic Statistics,2002,20:147-162.
Implications of Dynamic Factor Models for VAR Analysis [M].Mimeo,2005.
STOCK, J, YOGO, M. Testing for Weak Instruments in Linear IV Regression [M]//ANDREWS,D, STOCK, J. Identification and Inference for Econometric Models: Essays in Honor ofThomas Rothenberg. Cambridge MA:Cambridge University Press,2005:80-108.
VELDE, FRANCOIS. Chronicles of a Deflation Unforetold [J]. Journal of Political Economy,2009,117:591–634.
WOOLDRIDGE, J M. Econometric Analysis of Cross Section and Panel Data. Cambridge, MA:MIT Press,2002.
毕滔，吴彦．西部大开发战略政策实施效果实证研究[J]．新疆财经学院学报，2007（4）：39-42．
陈萍．东北老工业基地振兴战略实施效果分析[J]．社会科学战线，2007（5）：56-60．
陈玉萍，吴海涛，陶大云，等．基于倾向得分匹配法分析农业技术采用对农户收入的影响——以滇西南农户改良陆稻技术采用为例[J]．中国农业科学，2010（5）：3667-3676．
陈振明．政策科学[M]．北京：中国人民大学出版社，2003．
淦未宇，徐细雄，易娟．我国西部大开发战略实施效果的阶段性评价与改进对策[J]．经济地理，2011（1）：40-45．
郭菊娥，郭广涛，孟磊，等．4万亿投资对中国经济的拉动效应测算分析[J]．管理评论，2009
（2）：98-104．
黄干，马成．“4万亿”的经济结构效应与财政投资结构优化——基于CGE建模的分析[J]．经济学家，2012（10）：71-80．
黄清．电力行业放松规制改革政策效果的实证研究——基于发电侧数据的双重差分模型检验[J]．山西财经大学学报，2009（1）：49-56．
靳春平，廖涛．西部大开发对地区经济发展的影响——以四川为例[J]．财经科学，2006（6）：103-110．
卡尔·帕顿，大卫·沙维奇．政策分析和规划的初步方法[M]．孙秀芝，胡启生等译，北京：华夏出版社，2001．
李国平，彭思奇，曾先峰，等．中国西部大开发战略经济效应评价——基于经济增长质量的视角[J]．当代经济科学，2011（7）：1-10．
李佳路．扶贫项目的减贫效果评估：对30个国家扶贫开发重点县调查[J]．改革，2010（8）：125-132．
李楠，乔榛．国有企业改制政策效果的实证分析——基于双重差分模型的估计[J]．数量经济技术经济研究，2010（2）：3-21．
李秀英．西部大开发战略下的东部经济发展[J]．经济研究参考，2004（92）：5-10．
刘斌，王春福．政策科学研究（第一卷）．北京：人民出版社，2000．
刘凤芹，马慧．倾向得分匹配方法的敏感性分析[J]．统计与信息论坛，2009（10）：7-13．
刘立峰．4万亿投资计划回顾与评价[J]．中国投资，2012（12）：35-38．
刘生龙，王亚华，胡鞍钢．西部大开发与区域经济收敛[J]．经济研究，2009（9）：94-105．
苗永旺，王亮亮．全球金融危机经济刺激方案的退出策略：历史经验与现实选择[J]．国际金融研究，2010（2）：48-53．
聂辉华，方明月，李涛．增值税转型对企业行为和绩效的影响[J]．管理世界，2009（5）：17-35．
沈利生．4万亿投资拉动经济增长的模拟分析[M]//张屹山．数量经济研究（第2卷），北京：科学出版社，2012．
王红茹．4万亿投资被赋予象征意义，预计可成就6万亿GDP[J]．中国经济周刊，2011（44）：1-2．
王露．8%保卫战：刺激政策或拉动GDP两个百分点[N]．21世纪经济报道，2008-11-11．
王美今，林建浩．计量经济学应用性研究的可信性革命[J]．经济研究，2012（2）：120-132．
王曦，陆荣．危机下四万亿投资计划的短期作用与长期影响[J]．中山大学学报（社会科学版），2009（4）：180-188．
王秀萍．金砖四国也能够对金融危机措施及效果[J]．企业家天地，2011（4）：9-10．
魏后凯，孙承平．我国西部大开发战略实施效果评价[J]．开发研究，2004（3）：21-25．
卫梦星．基于微观非实验数据的政策效应评估方法评价与比较[J]．西部论坛，2012（7）：42-49．
卫梦星．“四万亿”投资的增长效应分析——“反事实”方法的一个应用[J]．当代财经，2012
（11）：16-25．
吴燕玲．区域经济增长与国家发展战略——东北老工业基地振兴战略对黑龙江省经济发展的影响[J]．哈尔滨工业大学学报（社会科学版），2011（5）：41-46．
胥佚萱，林志伟．增值税转型改革与企业固定资产投资决策——基于中国上市公司数据的面板双重差分模型分析[J]．税务与经济，2011（1）：90-97．
杨飞虎．政府公共投资建设项目运行态势及政策建议——基于870份调查问卷的统计分析[J]．江西财经大学学报，2010（6）：14-19．
俞红海，徐龙炳．股权分置改革有效改善了公司绩效吗？——基于双重差分模型的估计[J]．浙江工商大学学报，2010（1）：56-62．
余静文，王春超．新“拟随机实验”方法的兴起——断点回归及其在经济学中的应用[J]．经济学动态，2011（2）：125-131．
余静文，王春超．转型时期中国城市圈的经济绩效[J]．当代经济科学，2010（5）：15-22．
余静文，赵大利．城市群落崛起、经济绩效与区域收入差距[J]．中南财经政法大学学报，2010（4）：30-38．
岳国强．4万亿新增投资的见效时间和拉动效应[J]．中国投资，2009（3）：29-32．
岳利萍，白永秀．从东西不同地区差距评价西部大开发战略实施绩效——基于主成份分析法的视角[J]．科研管理，2008（5）：84-91．
赵彤刚．4万亿投资将拉动明年GDP1．8个百分点[N]．中国证券报，2008-11-11．
“中国2007年投入产出表分析应用”课题组．基于2007年投入产出表的我国投资乘数测算和变动分析[J]．统计研究，2011（3）：3-7．
周黎安，陈烨．中国农村税费改革的政策效果:基于双重差分模型的估计[J]．经济研究，2005
（8）：44-53．
周荣祥．四万亿投资每年拉动GDP一个百分点[N]．证券时报，2008-11-28．
朱承亮，岳宏志，李婷．基于TFP视角的西部大开发战略实施绩效评价[J]．科学学研究，2009（11）：1662-1667．
祝接金，胡永平．政府支出、效率改进与经济增长——基于面板数据随机系数模型的实证研究[J]．当代财经，2005（2）：15-18．
朱宁宁，朱建军，刘思峰，等．我国政府建筑节能政策（措施）的实施效果评价[J]．中国管理科学，2008（10）：576-580．
8王秀萍.金砖四国也能够对金融危机措施及效果[J].企业家天地，2011（4）：9-10.
ABADIE A, J GARDEAZABAL. The Economic Costs of Conflict: A Case Study of the BasqueCountry [J]. American Economic Review,2003,93:113-132.
AND J HAINMUELLER.Synthetic Control Methods for Comparative CaseStudies: Estimating the Effect of California’s Tobacco Control Program [J].Journal of theAmerican Statistical Association,2010,105:493-505.
ACEMOGLU, DARON, SIMON JOHNSON, et al. The Colonial Origins of ComparativeDevelopment: An Empirical Investigation [J]. American Economic Review,2001,91:1369-1401.
AMEMIYA, T. Advanced Econometrics [M].Cambridge: Harvard University Press,1985.
ANGRIST, JOSHUA D.Lifetime Earnings and the Vietnam Era Draft Lottery: Evidence fromSocial Security Administrative Records [J].American Economic Review,1990,80:313-336.
AND ALAN B KRUEGER. Does Compulsory School Attendance Affect
Schooling and Earnings [J].Quarterly Journal of Economics,1991,106:976–1014.
AND VICTOR LAVY. Using Maimonides’ Rule to Estimate the Effect of Class
Size on Scholastic Achievement [J]. Quarterly Journal of Economics,1999,114:533-575.
AND PISCHKE STEFFEN J. Mostly Harmless Econometrics: An Empiricist’s
Companion[M]. Princeton: Princeton University Press,2008.
AND PISCHKE STEFFEN J.The Credibility Revolution in Empirical Economics:How Better Research Design is Taking the Con out of Econometrics[R]. NBER Working Paper15794,2010.
ANDREA PUFAHL, C R. Evaluating the Effects of Farm Programs:Results from PropensityScore Matching [J]. Modelling of Agricultural and Rural Development Policies,2008,80:1-15.
BAI J, S NG. Determining the Number of Factors in Approximate Factor Models [J].Econometrica,2002,70:191-221.
Inferential Theory for Factor Models of Large Dimensions [J].Econometrica,2003,71:135-171.
AND S NG.Confidence Intervals for Diffusion Index Forecasts and Inference forFactor-augmented Regressions[J]. Manuscript, University of Michigan,2005.
AND S NG. Determining the Number of Primitive Shocks in Factor Models[J].Manuscript, University of Michigan,2005.
BARRO, ROBERT J, CHARLES J REDLICK. Macroeconomic Effects from GovernmentPurchases and Taxes[R]. NBER Working Paper15369,2009
BASSI L. The Effect of CETA on the Post-Program Earnings of Participants[J]. Journal of HumanResources,1983,18:539-556.
Estimating the Effects of Training Programs with Nonrandom Selection[J]. Reviewof Economics and Statistics,1984,66:36-43.
BELL B, BLUNDELL R, VAN REENEN J. Getting the Unemployed Back to Work: anEvaluation of the New Deal Proposals [J]. International Tax and Public Finance,1999,6:339–360.
BERNANKE B S, J BOIVIN. Monetary Policy in a Data-rich Environment [J]. Journal ofMonetary Economics,2003,50:525-546.
AND P ELIASZ. Measuring the Effects of Monetary Policy: a Factor-augmentedVector Autoregressive (FAVAR) Approach [J]. Quarterly Journal of Economics,2005,120:387-422.
BJORKLUND A, MOFFITT R. The Estimation of Wage Gains and Welfare Gains inSelf-Selection Models [J]. Reviews of Economics and Statistics,1987,69:42-49.
BLEAKLEY, HOYT. Disease and Development: Evidence from Hookworm Eradication in theAmerican South [J]. Quarterly Journal of Economics,2007,122:73-117.
BLUNDELL, R, COSTA DIAS, M. Evaluation Methods for Non-Experimental Data. FiscalStudies,2000,21:427-468.
BOUND JOHN, DAVID JAEGER, REGINA BAKER. Problems with Instrumental VariablesEstimation when the Correlation between the Instruments and the Endogenous ExplanatoryVariable is Weak [J].Journal of the American Statistical Association,1995,90:443-450.
CARD, DAVID, ALAN B KRUEGER. Does School Quality Matter? Returns to Education and theCharacteristics of Public Schools in the United States [J]. Journal of Political Economy,1992,100:1-40.
School Quality and Black–White Relative Earnings: A Direct Assessment [J].Quarterly Journal of Economics,1992,120:151-200.
Minimum Wages and Employment: A Case Study of the Fast-Food Industry in NewJersey and Pennsylvania [J].American Economic Review,1994,84:772-793.
CHARLES O JONES. An Introduction to the Study of Public Policy [M].3rd ed. Monetary,California: Brooks/Cole Publishing Company,1984.
COVA P, PISAN M, REBUCCI A. Macroeconomic Effects of China’s Fiscal Stimulus [R].Inter-American Development Bank: working paper, No IDB-WP-211,2010.
DANIEL LERNER, HAROLD D LASSWELL.Policy Sciences [M].Stanford University Press,1966.
DANIEL O GILLIGAN, JOHN HODDINOTT. The Impact of Ethiopia’s Productive Safety NetProgramme and its Linkages [R]. IFPRI Discussion Paper No.00839,2008.
DAVID NACHMIAS, CHAVA FRANKFORT NACHMIAS. Research Methods in the SocialSciences [M]. New York: St. Martin's Press,1976.
DIAO XINSHEN, Z YUMEI, Z C KEVIN. The Global Recession and China’s Stimulus Package:A General Equilibrium Assessment of Country Level Impacts [J]. China Economic Review,2012,23:1-17.
DONOHUE, JOHN J, JUSTIN WOLFERS. Uses and Abuses of Empirical Evidence in the DeathPenalty Debate [J]. Stanford Law Review,2005,58:791–845.
EHRLICH, ISAAC. The Deterrent Effect of Capital Punishment: A Question of Life and Death [J].American Economic Review,1975,65:397-417.
Capital Punishment and Deterrence: Some Further Thoughts and AdditionalEvidence [J]. Journal of Political Economy,1977,85:741-788.
On the Issue of Causality in the Economic Model of Crime and Law Enforcement:Some Theoretical Considerations and Experimental Evidence [J]. American Economic Review,1987,77:99-106.
Crime, Punishment, and the Market for Offenses [J]. Journal of EconomicPerspectives,1996,10:43-67.
FORNI, M, HALLIN, M, LIPPI, M, ET AL. The Generalized Dynamic Factor Model:Identifcation and Estimation [J]. Review of Economics and Statistics,Forthcoming,1999.
The Generalized Factor Model: Identification and Estimation [J]. The Review ofEconomics and Statistics,2000,82:540–554.
Dynamic Common Factors in Large Cross-sections [J]. Empirical Economics,2002,21:27–42.
GIANNONE, D, L REICHLIN, L SALA. Monetary Policy in Real Time[J].//Mark Gertler,Kenneth Rogoff.NBER Macroeconomics Annual2004[M]. MIT Press,2005:161-200.
GOLDBERGER, A. Best Linear Unbiased Prediction in the Generalized Linear Regression Model[J]. Journal of the American Statistical Association,1962,57:369-375.
GREGORY, A, A HEAD. Fluctuations in Productivity, Investment, and the Current Account [J].Journal of Monetary Economics,1999,44:423-452.
HAHN, TODD, VANDER KLAAUW.Identification and Estimation of Treatment Effects with aRegression Discontinuity Design [J]. Econometrica,2001,69:201-209.
HECKMAN, J J AND E J VYTLACIL. Local Instrumental Variables [M]//C Hsiao, K Morimuneand J L Powell. Nonlinear Statistical Modeling. Cambridge: Cambridge University Press,2001:1-46.
AND V J HOTZ. Choosing Among Alternative Nonexperimental Methods forEstimating the Impact of Social Programs: The Case of Manpower Training [J]. Journal of theAmerican Statistical Association,1989,84:862-874.
HE DONG, ZHANG ZHIWEI, ZHANG WENLANG. How Large Will Be the Effect of China’sFiscal Stimulus Package on Output and Employment [J]. Pacific Economic Review,2009,14:730-744.
HOXBY, C M. The Effects of Class Size on Student Achievement:New Evidence fromPopulation Variation [J].Quarterly Journal of Economics,2000,115:1239-1285.
HSIAO, C. Autoregressive Modelling and Causal Ordering of Economic Variables[J]. Journal ofEconomic Dynamics and Control,1982,4:243-259.
Analysis of Panel Data [M].2nd ed. New York: Cambridge University Press,2003.
AND A K TAHMISCIOGLU. A Panel Analysis of Liquidity Constraints and FirmInvestment [J]. Journal of the American Statistical Association,1997,92:455-465.
H STEVE CHING AND SHUI KI WAN.A Panel Data Approach for ProgramEvaluation: Measuring the Benefts of Political and Economic Integration of Hong Kong withChina [J]. Journal of Applied Econometrics,2012,27:705-740.
AND S WAN. To Combine or not to Combine Forecasts. Mimeo,2009.
H STEVE CHING, HSIAO, C, S WAN, ET AL. Economic Benefits of Globalization: The Impactof Entry to the WTO on China’s Growth [J]. Pacific Economic Review,2011,16:285-301.
JAMES J HECKMAN. Effects of Child-Care Programs on Women's Work Effort [R/OL].National Bureau of Economic Research,1974:136-169. http://www.nber.org/chapters/c3687.
Sample Selection Bias as a Specification Error [J]. Econometrica,1979,65:153-179.
Econometric causality [J]. International Statistical Review,2008,52:1-27.
AND ROBB R. Alternative Methods for Evaluating the Impact of Interventions[M]//JAMES J HECKMAN, SINGER B. Longitudinal Analysis of Labor Market Data. NewYork: Cambridge University Press,1985:352.
AND ROBB R. Alternative Methods For Solving The Problem of Selection Bias inEvaluating The Impact of Treatments on Outcomes [M]//WAINER H. Drawing Inferences fromSelf-Selected Samples. Berlin: Springer-Verlag,1986.
Instrumental Variables: A Study of Implicit Behavioral Assumptions Used in MakingProgram Evaluations[J].The Journal of Human Resources,1997,32:441-462.
AND H I. Matching as an Econometric Evaluation Estimator: Evidence fromEvaluating a Job Training Programme [J]. The Review of Economic Studies,1997,77:605-654.
SMITH J AND CLEMENTS N. Making the Most Out of Program Evaluations andSocial Experiments: Accounting for Heterogeneity in Program Impacts[J].Review of EconomicStudies,1997,64:487-536.
KANNIKA D, CHENG HSIAO, XUEYAN ZHAO. Decriminalization and Marijuana SmokingPrevalence: Evidence From Australia [J].Journal of Bisiness and Econometrics,2010,38:344-356.
KAPETANIOS G, MUMTAZ H, STEVENS I, ET AL.Assessing the Economy Wide Effects ofQuantitative Easing [R]. Bank of England Working paper No.443,2012.
LALIVE, R. How do Extended Benefits Affect Unemployment Duration? A RegressionDiscontinuity Approach[J]. Journal of Econometrics,2008,142:785-806.
LALONDE, R. Evaluating the Econometric Evaluations of Training Programs with ExperimentalData [J]. American Economic Review,1986,76:604-620.
LEAMER, EDWARD. Let’s Take the Con Out of Econometrics[J]. American Economic Review,1978,73:31-43.
LEE D S. Randomized Experiments from Non-random Selection in US House elections[J].Journal of Econometrics,2008,144:675-697.
LUCAS, ROBERT E. What Economists Do. Unpublished,1988.
MCCRARY, JUSTIN. Manipulation of the Running Variable in the Regression DiscontinuityDesign: A Density Test [J]. Journal of Econometrics,2008,142:698-714.
MICHAEL HOWLETT, M RAMESH. Studying Public Policy: Policy Cycles and PolicySubsystems [M]. Oxford University Press,1995.
OKUI, R. The Optimal Choice of Moments in Dynamic Panel Data Models [J].Journal ofEconometrics,2009,151:1-161.
PERKINS S M, T W. For Objective Causal Inference: Design Trumps Analysis [J].The Annual ofApplied Atatistics,2000,48:93-101.
PERSSON TORSTEN, GUIDO TABELLINI. The Growth Effect of Democracy: Is itHeterogeneous and How Can it be Estimated [M]//E Helpman. Institutions and EconomicPerformance.Cambridge: Harvard University Press,2008.
PESARAN, M H, L V SMITH, R P SMITH. What if the UK or Sweden Had Joined the Euro in1999? An Empirical Evaluation Using a Global VAR[J]. International Journal of Finance andEconomics,2007,12:55-87.
AND SMITH R P. Counterfactual Analysis in Macro Econometrics: An EmpiricalInvestigation into the Effects of Quantitative Easing[R].IZA Discussion Paper No.6618,2012.
PUHANI P A.Poland on the Dole: The Effect of Reducing the Unemployment Benefit EntitlementPeriod[J]. Journal of Population Economics,2000,59:35-44.
RAMEY, VALERIE, AND MATTHEW D. SHAPIRO. Costly Capital Reallocation and the Effectsof Government Spending.” Carnegie-Rochester Conference Series on Public Policy,1998,48:145-194.
RAO, C R. Linear Statistical Inference and It’sApplications[M].2nd ed., New York:Wiley,1973.
RICHARDSON, GARY, AND WILLIAM TROOST. Monetary Intervention Mitigated BankingPanics during the Great Depression: Quasi-Experimental Evidence from a Federal ReserveDistrict Border,1929-1933[J].Journal of Political Economy,2009,117:1031-1073.
ROBERT W F. Railroads and American Economic Growth: Essays in Economic History [M].Baltimore: The Johns Hopkins University Press,1964.
ROMER, CHRISTINA D, DAVID H ROMER. Does Monetary Policy Matter? A New Test in theSpirit of Friedman and Schwartz [J].NBER Macroeconomics Annual,1989,4:121-70.
A New Measure of Monetary Shocks: Derivation and Implications [J]. AmericanEconomic Review,2004,4:1055-1084.
The Macroeconomic Effects of Tax Changes:Estimates Based on a New Measure ofFiscal Shocks[R]. NBER Working Paper No.13264,2007.
ROSENBAUM P, R D. The Central Role of the Propensity Score in Observational Studies forCausal Effects [J]. Biometrika,1983,84:41-55.
SANDRA CAVACO D F. Estimating the Effect of a Retraining Program on the Re-EmploymentRate of Displaced Workers [R].The Institute for the Study of Labor Working Paper,2009.
SARGENT, T J,C A SIMS. Business Cycle Modeling without Pretending to Have Too MuchA-Priori Economic Theory [M]//C SIMS, ET.AL. New Methods in Business Cycle Research.Minneapolis: Federal Reserve Bank of Minneapolis,1977.
SHAOHUA CHEN, R M. Are There Lasting Impacts of Aid to Poor Areas [R].World Bank PolicyResearch Working Paper4084,2008.
SIMS, CHRISTOPHER A. Macroeconomics and Reality [J].Econometrica,1980,48:1-48.
Uncertainty across Models [J]. American Economic Review,1988,78:163-167.
STEWART M B. The Employment Effects of the National Minimum Wage [J].The EconomicJournal,2004,63:110-116.
STOCK, J H, WATSON M W. New Indexes of Coincident and Leading Economic Indications[M]//O J BLANCHARD, S FISCHER. NBER Macroeconomics Annual. Cambridge MA: MITPress,1989.
Diffusion Indexes [R]. NBER Working Paper6702,1998.
Forecasting Infation[J]. Journal of Monetary Economics,1999,44:293–335.
Macroeconomic Forecasting Using Diffusion Indexes [J]. Journal of Business andEconomic Statistics,2002,20:147-162.
Implications of Dynamic Factor Models for VAR Analysis [M].Mimeo,2005.
STOCK, J, YOGO, M. Testing for Weak Instruments in Linear IV Regression [M]//ANDREWS,D, STOCK, J. Identification and Inference for Econometric Models: Essays in Honor ofThomas Rothenberg. Cambridge MA:Cambridge University Press,2005:80-108.
VELDE, FRANCOIS. Chronicles of a Deflation Unforetold [J]. Journal of Political Economy,2009,117:591–634.
WOOLDRIDGE, J M. Econometric Analysis of Cross Section and Panel Data. Cambridge, MA:MIT Press,2002.
毕滔，吴彦．西部大开发战略政策实施效果实证研究[J]．新疆财经学院学报，2007（4）：39-42．
陈萍．东北老工业基地振兴战略实施效果分析[J]．社会科学战线，2007（5）：56-60．
陈玉萍，吴海涛，陶大云，等．基于倾向得分匹配法分析农业技术采用对农户收入的影响——以滇西南农户改良陆稻技术采用为例[J]．中国农业科学，2010（5）：3667-3676．
陈振明．政策科学[M]．北京：中国人民大学出版社，2003．
淦未宇，徐细雄，易娟．我国西部大开发战略实施效果的阶段性评价与改进对策[J]．经济地理，2011（1）：40-45．
郭菊娥，郭广涛，孟磊，等．4万亿投资对中国经济的拉动效应测算分析[J]．管理评论，2009
（2）：98-104．
黄干，马成．“4万亿”的经济结构效应与财政投资结构优化——基于CGE建模的分析[J]．经济学家，2012（10）：71-80．
黄清．电力行业放松规制改革政策效果的实证研究——基于发电侧数据的双重差分模型检验[J]．山西财经大学学报，2009（1）：49-56．
靳春平，廖涛．西部大开发对地区经济发展的影响——以四川为例[J]．财经科学，2006（6）：103-110．
卡尔·帕顿，大卫·沙维奇．政策分析和规划的初步方法[M]．孙秀芝，胡启生等译，北京：华夏出版社，2001．
李国平，彭思奇，曾先峰，等．中国西部大开发战略经济效应评价——基于经济增长质量的视角[J]．当代经济科学，2011（7）：1-10．
李佳路．扶贫项目的减贫效果评估：对30个国家扶贫开发重点县调查[J]．改革，2010（8）：125-132．
李楠，乔榛．国有企业改制政策效果的实证分析——基于双重差分模型的估计[J]．数量经济技术经济研究，2010（2）：3-21．
李秀英．西部大开发战略下的东部经济发展[J]．经济研究参考，2004（92）：5-10．
刘斌，王春福．政策科学研究（第一卷）．北京：人民出版社，2000．
刘凤芹，马慧．倾向得分匹配方法的敏感性分析[J]．统计与信息论坛，2009（10）：7-13．
刘立峰．4万亿投资计划回顾与评价[J]．中国投资，2012（12）：35-38．
刘生龙，王亚华，胡鞍钢．西部大开发与区域经济收敛[J]．经济研究，2009（9）：94-105．
苗永旺，王亮亮．全球金融危机经济刺激方案的退出策略：历史经验与现实选择[J]．国际金融研究，2010（2）：48-53．
聂辉华，方明月，李涛．增值税转型对企业行为和绩效的影响[J]．管理世界，2009（5）：17-35．
沈利生．4万亿投资拉动经济增长的模拟分析[M]//张屹山．数量经济研究（第2卷），北京：科学出版社，2012．
王红茹．4万亿投资被赋予象征意义，预计可成就6万亿GDP[J]．中国经济周刊，2011（44）：1-2．
王露．8%保卫战：刺激政策或拉动GDP两个百分点[N]．21世纪经济报道，2008-11-11．
王美今，林建浩．计量经济学应用性研究的可信性革命[J]．经济研究，2012（2）：120-132．
王曦，陆荣．危机下四万亿投资计划的短期作用与长期影响[J]．中山大学学报（社会科学版），2009（4）：180-188．
王秀萍．金砖四国也能够对金融危机措施及效果[J]．企业家天地，2011（4）：9-10．
魏后凯，孙承平．我国西部大开发战略实施效果评价[J]．开发研究，2004（3）：21-25．
卫梦星．基于微观非实验数据的政策效应评估方法评价与比较[J]．西部论坛，2012（7）：42-49．
卫梦星．“四万亿”投资的增长效应分析——“反事实”方法的一个应用[J]．当代财经，2012
（11）：16-25．
吴燕玲．区域经济增长与国家发展战略——东北老工业基地振兴战略对黑龙江省经济发展的影响[J]．哈尔滨工业大学学报（社会科学版），2011（5）：41-46．
胥佚萱，林志伟．增值税转型改革与企业固定资产投资决策——基于中国上市公司数据的面板双重差分模型分析[J]．税务与经济，2011（1）：90-97．
杨飞虎．政府公共投资建设项目运行态势及政策建议——基于870份调查问卷的统计分析[J]．江西财经大学学报，2010（6）：14-19．
俞红海，徐龙炳．股权分置改革有效改善了公司绩效吗？——基于双重差分模型的估计[J]．浙江工商大学学报，2010（1）：56-62．
余静文，王春超．新“拟随机实验”方法的兴起——断点回归及其在经济学中的应用[J]．经济学动态，2011（2）：125-131．
余静文，王春超．转型时期中国城市圈的经济绩效[J]．当代经济科学，2010（5）：15-22．
余静文，赵大利．城市群落崛起、经济绩效与区域收入差距[J]．中南财经政法大学学报，2010（4）：30-38．
岳国强．4万亿新增投资的见效时间和拉动效应[J]．中国投资，2009（3）：29-32．
岳利萍，白永秀．从东西不同地区差距评价西部大开发战略实施绩效——基于主成份分析法的视角[J]．科研管理，2008（5）：84-91．
赵彤刚．4万亿投资将拉动明年GDP1．8个百分点[N]．中国证券报，2008-11-11．
“中国2007年投入产出表分析应用”课题组．基于2007年投入产出表的我国投资乘数测算和变动分析[J]．统计研究，2011（3）：3-7．
周黎安，陈烨．中国农村税费改革的政策效果:基于双重差分模型的估计[J]．经济研究，2005
（8）：44-53．
周荣祥．四万亿投资每年拉动GDP一个百分点[N]．证券时报，2008-11-28．
朱承亮，岳宏志，李婷．基于TFP视角的西部大开发战略实施绩效评价[J]．科学学研究，2009（11）：1662-1667．
祝接金，胡永平．政府支出、效率改进与经济增长——基于面板数据随机系数模型的实证研究[J]．当代财经，2005（2）：15-18．
朱宁宁，朱建军，刘思峰，等．我国政府建筑节能政策（措施）的实施效果评价[J]．中国管理科学，2008（10）：576-580．