Monte Carlo tests of autocorrelation

Barnard's Monte Carlo test procedure can be used to eliminate the problem of the inconclusive region of the Durbin-Watson statistic in an elegant way. In contrast to conventional tests, this procedure can be extended straightforwardly to systems of equations, which is illustrated here for a translog system. An extension to bootstraps, which avoids the normality assumption, is also discussed.     

Monte Carlo studies on the effectiveness of the bootstrap bias reduction method on 2SLS estimates

If first moments exist, two stage least squares estimators are consistent although biased. In this paper several bias correction methods are compared including bootstrap two stage least squares, Nagar's k-class and jackknife estimators for both parametric and non-parametric cases. Monte Carlo experiments on several models investigate the non-large sample properties of these estimators. The results strongly favor the bootstrap procedure judged by the amount of bias reduction and comparative variances.     

Forecasting the German population with Monte Carlo methods

This paper presents an approach of constructing confidence intervals by means of Monte Carlo simulation. This technique attempts to incorporate the uncertainty involved in projecting the German population by letting the fertility, mortality and net immigration rates vary as a random variable with a specific distribution. Since fertility and migration are by far the most volatile, and therefore, the most critical components to population forecasting, this technique has the potential of accounting for this uncertainty, if the subjective distributions are specified with enough care.     

Multiple minima and the Cochrane-Orcutt technique: Some initial Monte Carlo results

The paper reports the initial results of a Monte Carlo study into the occurrence of multiple minima (sum of squared residuals) in regression models. Likely reasons for such occurrences are discussed including ‘symmetry’ and the effects of sample size.     

Testing the stationarity of economic time series: further Monte Carlo evidence

Testing the stationarity of economic time series has become a central issue in empirical economics. This paper evaluates, via Monte Carlo simulation, the empirical power and size of the augmented Dickey-Fuller test for a unit root (ADF test), the most widely used in empirical works, and of the test recently proposed by Kwiatkowski et al. (1992; KPSS test), where the null hypothesis is one of stationarity. The evidence confirms that both procedures suffer from very low power and, more so in the case of the KPSS test, large size distortions, especially in samples of the sizes usually available in practical applications. Moreover, their performance is highly sensitive to the true generating process, as well as to the way one parameterizes each test. It is shown, however, that a combined ADF-KPSS procedure would significantly reduce the number of erroneous conclusions, although at the cost of producing a fairly large number of inconclusive answers.     

Long-run purchasing power parity revisited: a Monte Carlo simulation

The existence of long-run purchasing power parity (PPP) implies that a cointegration vector of nominal exchange rate, domestic price, and foreign price is expected regardless of using the Engle-Granger two-step method or Johansen maximum likelihood approach. However, this paper has found conflicting results: the Engle-Granger technique tends to reject the long-run PPP hypothesis whereas the Johansen method is generally supportive of long-run PPP. Via Monte Carlo simulations, the present paper finds that the Johansen approach has a bias toward supporting long-run PPP especially under the circumstances in which the assumption of normally or/and independently and identically distributed disturbance terms is violated.     

A Monte Carlo test of preference independence

Theil (1987) recently developed distribution-free Monte Carlo testing procedures for demand homogeneity and Slutsky symmetry which do not use asymptotic theory. In this paper we introduce a similar procedure to test preference independence. The application of this procedure is illustrated with Dutch data.     

A Monte Carlo study of growth regressions

Using Monte Carlo simulations, this paper evaluates the bias properties of estimators commonly used to estimate growth regressions derived from the Solow model. We explicitly allow for measurement error, country-specific fixed effects and regressor endogeneity. An OLS estimator applied to a single cross-section of variables averaged over time (the between estimator) performs best in terms of the extent of bias on each of the estimated coefficients. Fixed-effects and the Arellano–Bond GMM estimator overstate the speed of convergence under a wide variety of assumptions, while the between estimator understates it. Finally, fixed effects and Arellano–Bond bias towards zero the slope estimates on the human and physical capital accumulation variables, while the between estimator and the Blundell–Bond system GMM estimator bias these coefficients upwards.      

A Monte Carlo test of Slutsky symmetry

This paper demonstrates how Barnard's (1963) Monte Carlo test procedure can be applied to Slutsky symmetry in demand systems.     

On the power of bootstrap tests for stationarity: a Monte Carlo comparison

This paper studies the behavior of recently proposed bootstrap tests for the null hypothesis of stationarity when the data are generated under the alternative hypothesis of a unit root. Using Monte Carlo experiments and empirical examples, it is shown that the power of these tests critically depends on the type of bootstrap employed. Specifically, while tests based on the stationary bootstrap have power functions that are increasing with respect to sample size, those based on the sieve bootstrap have non-monotonic power functions. We argue that this difference arises from the fact that the latter procedure does not impose the null hypothesis when generating the bootstrap samples while the former ensures that the bootstrap samples are stationary, conditional on the original data. Our results therefore suggest that while both forms of bootstrap are effective at providing improved distributional approximations under the null hypothesis, it is important to pay careful attention to the particular type of bootstrap being employed when attempting to distinguish between the unit root and stationarity hypotheses as the choice of bootstrap can have crucial implications for the power of the resulting tests.     

Testing misspecified non-nested factor demand systems: Some Monte Carlo results

Empirical factor demand analysis is a topic in which a choice must be made among several competing non-nested functional forms. Each of the commonly used factor demand systems, such as Translog, Generalized Leontief, Quadratic, and Generalized McFadden, exhibits statistical inadequacy when tested for the absence of residual autocorrelation, homoskedasticity and normality. This does not necessarily imply that the whole system is invalid, especially if misspecification affects only a subset of the equations forming the entire system. Since there is no theoretical guidance on how to select the model which is most able to capture the relevant features of the data, formal testing procedures can be useful. In the literature, paired and joint univariate non-nested tests (e.g. Davidson-MacKinnon's J and P tests, Bera-McAleer test and Barten-McAleer test) have been discussed at length, whereas virtually no attention has been paid to multivariate non-nested tests. In this paper we show how multivariate non-nested tests can be derived from their univariate counterparts, and we apply these tests to compare alternative factor demand systems. Since the outcome of a non-nested test is likely to be influenced by the type of misspecification affecting the competing models, we investigate the empirical performance of a multivariate non-nested test using new Monte Carlo experiments. The competing models are compared indirectly via a statistically adequate model which is considered as if it were the DGP. Under such circumstances, the distribution of the non-nested test of an incorrect null, when it is evaluated at the DGP, tends to be closer to the distribution of the test under the correct null, at least in small samples. A non-nested test is expected to select the model which is closest to the DGP. Moreover, we investigate the empirical behaviour of a non-nested test when the DGP has, in turn, autoregressive, heteroskedastic and non-normal errors. Finally, we provide some suggestions for the applied researcher. First version received: November 1999/Final version received: May 2001     

Rational expectations estimation of macroeconomic models: some Monte Carlo results

This paper analyzes the relative performance of alternative estimation methods for rational expectations macroeconomic models using a Monte Carlo approach. The methods studied include a single equation instrumental variable method most often attributed to McCallum, a full information substitution method proposed by Taylor and an efficient full information technique developed by Wickens. In general, the results of our Monte Carlo experiments indicate that although the full information methods tend to perform bettern than the single equation techniques, the gains of efficiency are relatively modest. However, in some experiments involving misspecification errors, the single equation method outperforms the full information estimators.     

Monte Carlo and bootstrap testing of demand homogeneity

To test for homogeneity of demand, a Monte Carlo test is formulated and it is extended to a bootstrap version.     

A Monte Carlo evaluation of labor supply models

In the area of labor supply and taxes advanced microeconometric methods have been developed in order to measure wage and income elasticities. Large variations in estimated elasticities have previously been reported in the literature. The purpose of the present study is to assess the sources for these discrepancies, and propose a robust estimator. According to our findings the commonly used maximum-likelihood estimator is sensitive to measurement errors in those variables that are needed in order to construct the individuals' budget sets. An iterative least squares estimator is preferred in small samples under several forms of specification and measurement errors.     

Semiparametric and nonparametric testing for long memory: A Monte Carlo study

The finite sample properties of three semiparametric estimators, several versions of the modified rescaled range, MRR, and three versions of the GHURST estimator are investigated. Their power and size for testing for long memory under short-run effects, joint short and long-run effects, heteroscedasticity andt-distributions are given using Monte Carlo methods. The MRR with the Bartlett window is generally robust with the disadvantage of a relatively small power. The trimmed Whittle likelihood has high power in general and is robust except for large short-run effects. The tests are applied to changes in exchange rate series (daily data) of 6 major countries. The hypothesis of no fractional integration is rejected for none of the series.     

Raising the bar of professionalism in futures studies

This article gives a behind-the-scenes look at how Joe Coates has been fulfilling an agent provocateur role for futures studies in the continuing high quality of his work and his watchdog-like role over the output of the field as a whole.     

A Monte Carlo comparison of estimating the number of dynamic factors

Based on a Monte Carlo simulation, this study compares the finite sample performance of five of the most widely used methods for estimating the number of dynamic factors. The simulation results show that although the performance is affected by the data generating process, the methods proposed by Hallin and Li?ka (J Am Stat Assoc 102(478):603–617, 2007) and Bai and Ng (Bus Econ Stat 25(1):52–60, 2007) generally outperform the others. Specifically, Amengual and Watson’s (J Bus Econ Stat 25(1):91–96, 2007) method is sensitive to cross-sectional correlation, and Breitung and Pigorsch’s (Oxf Bull Econ Stat 75(1):23–36, 2013) estimator is sensitive to the overestimation of the number of static factors. The results of this study are further supported by an empirical application to a Chinese macroeconomic dataset.     

信息通信技术（ICT）创新扩散及影响因素空间计量分析

本文运用2001—2018年全国288个地级以上城市统计数据,对信息通信技术(ICT)创新扩散及影响因素进行研究。首先采取改进的Bass模型来测算ICT创新扩散速度,然后构建ICT创新扩散及其影响因素的面板数据固定效应动态SAR模型,并采用拟极大似然估计法对动态SAR模型进行参数估计。研究表明:ICT创新扩散的时空效应显著,创新扩散不仅受本地影响还受邻近城市的影响;人口密度、人口流量、户均ICT消费支出及ICT供给能力等因素对其创新扩散有显著影响,且这些因素短期空间溢出效应和长期回流反馈效应显著。     

Monte Carlo simulation of macroeconomic risk with a continuum of agents: the symmetric case

Summary. Suppose a large economy with individual risk is modeled by a continuum of pairwise exchangeable random variables (i.i.d., in particular). Then the relevant stochastic process is jointly measurable only in degenerate cases. Yet in Monte Carlo simulation, the average of a large finite draw of the random variables converges almost surely. Several necessary and sufficient conditions for such “Monte Carlo convergence” are given. Also, conditioned on the associated Monte Carlo -algebra, which represents macroeconomic risk, individual agents' random shocks are independent. Furthermore, a converse to one version of the classical law of large numbers is proved. Received: October 29, 2001; revised version: April 24, 2002 RID="*" ID="*" Part of this work was done when Yeneng Sun was visiting SITE at Stanford University in July 2001. An early version of some results was included in a presentation to Tom Sargent's macro workshop at Stanford. We are grateful to him and Felix Kübler in particular for their comments. And also to Marcos Lisboa for several discussions with Peter Hammond, during which the basic idea of the paper began to take shape. Correspondence to: P.J. Hammond