Panel LM Unit‐root Tests with Level Shifts*

This paper proposes a new panel unit‐root test based on the Lagrangian multiplier (LM) principle. We show that the asymptotic distribution of the new panel LM test is not affected by the presence of structural shifts. This result holds under a mild condition that N/T→k, where k is any finite constant. Our simulation study shows that the panel LM unit‐root test is not only robust to the presence of structural shifts, but is more powerful than the popular Im, Pesaran and Shin (IPS) test. We apply our new test to the purchasing power parity (PPP) hypothesis and find strong evidence for PPP.     

Combination of Tests for Cointegration in Cross‐Correlated Panels

In this paper, Cheng and Sheng's (2017) combination of ‘combinations of P‐values’ (CCP) is extended to a combination of more than two tests and applied for cointegration testing in cross‐correlated panels. In a Monte Carlo experiment, power and size of the different combinations of combinations are investigated. If uncertainty about the panel configuration is taken into account, the results indicate that a multi‐test combination can minimize power losses. Furthermore, the usefulness of the combinations studied is illustrated by an application to international interest rate linkage. Cross‐sectional dependencies in both the simulation and the empirical studies are accounted for by using the block bootstrap.     

Diagnostic Tests of Cross‐section Independence for Limited Dependent Variable Panel Data Models*

This article considers the problem of testing for cross‐section independence in limited dependent variable panel data models. It derives a Lagrangian multiplier (LM) test and shows that in terms of generalized residuals of Gourieroux et al. (1987) it reduces to the LM test of Breusch and Pagan (1980) . Because of the tendency of the LM test to over‐reject in panels with large N (cross‐section dimension), we also consider the application of the cross‐section dependence test (CD) proposed by Pesaran (2004) . In Monte Carlo experiments it emerges that for most combinations of N and T the CD test is correctly sized, whereas the validity of the LM test requires T (time series dimension) to be quite large relative to N. We illustrate the cross‐sectional independence tests with an application to a probit panel data model of roll‐call votes in the US Congress and find that the votes display a significant degree of cross‐section dependence.     

The Yen Real Exchange Rate may be Stationary after all: Evidence from Non‐linear Unit‐root Tests*

The empirical literature that tests for purchasing power parity (PPP) by focusing on the stationarity of real exchange rates has so far provided, at best, mixed results. The behaviour of the yen real exchange rate has most stubbornly challenged the PPP hypothesis and deepened this puzzle. This paper contributes to this discussion by providing new evidence on the stationarity of bilateral yen real exchange rates. We employ a non‐linear version of the augmented Dickey–Fuller test, based on an exponentially smooth‐transition autoregressive model (ESTAR) that enhances the power of the tests against mean‐reverting non‐linear alternative hypotheses. Our results suggest that the bilateral yen real exchange rates against the other G7 and Asian currencies were mean reverting during the post‐Bretton Woods era. Thus, the real yen behaviour may not be so different after all but simply perceived to be so because of the use of a restrictive alternative hypothesis in previous tests.     

Finite Sample Correction Factors for Panel Cointegration Tests*

In this paper we present finite T mean and variance correction factors and corresponding response surface regressions for the panel cointegration tests presented in Pedroni (1999, 2004) , Westerlund (2005) , Larsson et al. (2001) and Breitung (2005) . For the single equation tests, we consider up to 12 regressors and for the system tests vector autoregression dimensions up to 12 variables. All commonly used specifications for the deterministic components are considered. The sample sizes considered are T ∈ {10,20,30,40,50,60,70,80,90,100,200,500}.     

Truncated Product Methods for Panel Unit Root Tests*

This paper proposes two new panel unit root tests based on Zaykin et al. (2002) ’s truncated product method. The first one assumes constant correlation between P‐values and the second one uses sieve bootstrap to allow for general forms of cross‐section dependence in the panel units. Monte Carlo simulation shows that both tests have reasonably good size and are powerful in cases of some very large P‐values. The proposed tests are applied to a panel of real GDP and inflation density forecasts, resulting in evidence that professional forecasters may not update their forecast precision in an optimal Bayesian way.     

Testing Exogeneity in the Bivariate Probit Model: A Monte Carlo Study*

We conduct an extensive Monte Carlo experiment to examine the finite sample properties of maximum‐likelihood‐based inference in the bivariate probit model with an endogenous dummy. We analyse the relative performance of alternative exogeneity tests, the impact of distributional misspecification and the role of exclusion restrictions to achieve parameter identification in practice. The results allow us to infer important guidelines for applied econometric practice.     

Cross‐sectional Dependency and Size Distortion in a Small‐sample Homogeneous Panel Data Unit Root Test*

In this paper, we investigate the effects of cross‐sectional disturbance correlation in a homogeneous panel data unit root test. As reported by other authors, the unit root test has incorrect size in the presence of cross‐sectional correlation. We suggest that a previously known estimator can be used to reduce the size distortions. We supply response surface estimates for critical values and study the size characteristics of the proposed test. We find that the suggested estimator performs well in small‐sample homogeneous panel data unit root tests. The reduction in size distortion comes at a small cost of lower power against a stationary alternative.     

Regression‐based Tests for a Change in Persistence*

We show that the minimal forward (reverse) recursive unit tests of Banerjee, Lumsdaine and Stock [Journal of Business and Economics Statistics (1992) Vol. 10, pp. 271–288] are consistent against the alternative of a change in persistence from I(0) to I(1) [I(1) to I(0)]. However, these statistics are also shown to diverge for series which are I(0) throughout. Consequently, a rejection by these tests does not necessarily imply a change in persistence. We propose a further test, based on the ratio of these statistics, which is consistent against changes either from I(0) to I(1), or vice versa, yet does not over‐reject against constant I(0) series. Consistent breakpoint estimators are proposed.     

Truth and Robustness in Cross‐country Growth Regressions*

We re‐examine studies of cross‐country growth regressions by Levine and Renelt (American Economic Review, Vol. 82, 1992, pp. 942–963) and Sala‐i‐Martin (American Economic Review, Vol. 87, 1997a, pp. 178–183; Economics Department, Columbia, University, 1997b). In a realistic Monte Carlo experiment, their variants of Edward Leamer's extreme‐bounds analysis are compared with a cross‐sectional version of the general‐to‐specific search methodology associated with the LSE approach to econometrics. Levine and Renelt's method has low size and low power, while Sala‐i‐Martin's method has high size and high power. The general‐to‐specific methodology is shown to have a near nominal size and high power. Sala‐i‐Martin's method and the general‐to‐specific method are then applied to the actual data from Sala‐i‐Martin's original study.     

Testing Stationarity in Small‐ and Medium‐Sized Samples when Disturbances are Serially Correlated*

In this article, we study the size distortions of the KPSS test for stationarity when serial correlation is present and samples are small‐ and medium‐sized. It is argued that two distinct sources of the size distortions can be identified. The first source is the finite‐sample distribution of the long‐run variance estimator used in the KPSS test, while the second source of the size distortions is the serial correlation not captured by the long‐run variance estimator because of a too narrow choice of truncation lag parameter. When the relative importance of the two sources is studied, it is found that the size of the KPSS test can be reasonably well controlled if the finite‐sample distribution of the KPSS test statistic, conditional on the time‐series dimension and the truncation lag parameter, is used. Hence, finite‐sample critical values, which can be applied to reduce the size distortions of the KPSS test, are supplied. When the power of the test is studied, it is found that the price paid for the increased size control is a lower raw power against a non‐stationary alternative hypothesis.     

Exact Skewness–Kurtosis Tests for Multivariate Normality and Goodness‐of‐Fit in Multivariate Regressions with Application to Asset Pricing Models*

We study the problem of testing the error distribution in a multivariate linear regression (MLR) model. The tests are functions of appropriately standardized multivariate least squares residuals whose distribution is invariant to the unknown cross‐equation error covariance matrix. Empirical multivariate skewness and kurtosis criteria are then compared with a simulation‐based estimate of their expected value under the hypothesized distribution. Special cases considered include testing multivariate normal and stable error distributions. In the Gaussian case, finite‐sample versions of the standard multivariate skewness and kurtosis tests are derived. To do this, we exploit simple, double and multi‐stage Monte Carlo test methods. For non‐Gaussian distribution families involving nuisance parameters, confidence sets are derived for the nuisance parameters and the error distribution. The tests are applied to an asset pricing model with observable risk‐free rates, using monthly returns on New York Stock Exchange (NYSE) portfolios over 5‐year subperiods from 1926 to 1995.     

Monte Carlo tests with nuisance parameters: A general approach to finite-sample inference and nonstandard asymptotics

The technique of Monte Carlo (MC) tests [Dwass (1957, Annals of Mathematical Statistics 28, 181–187); Barnard (1963, Journal of the Royal Statistical Society, Series B 25, 294)] provides a simple method for building exact tests from statistics whose finite sample distribution is intractable but can be simulated (when no nuisance parameter is involved). We extend this method in two ways: first, by allowing for MC tests based on exchangeable possibly discrete test statistics; second, by generalizing it to statistics whose null distribution involves nuisance parameters [maximized MC (MMC) tests]. Simplified asymptotically justified versions of the MMC method are also proposed: these provide a simple way of improving standard asymptotics and dealing with nonstandard asymptotics.     

Testing for Hysteresis in Unemployment in OECD Countries: New Evidence using Stationarity Panel Tests with Breaks*

This paper tests hysteresis effects in unemployment using panel data for 19 Organization for Economic Co‐operation and Development (OECD) countries covering the period 1956–2001. The tests exploit the cross‐sectional variations of the series, and additionally, allow for a different number of endogenous breakpoints in the unemployment series. The critical values are simulated based on our specific panel sizes and time periods. The findings stress the importance of accounting for exogenous shocks in the series and support the natural‐rate hypothesis of unemployment for the majority of the countries analysed.     

Explaining US–UK Interest Rate Differentials: A Reassessment of the Uncovered Interest Rate Parity in a Bayesian Framework*

In this paper, we test the uncovered interest rate parity (UIRP), allowing for transitory deviations from it. These deviations may arise from variations in risk premia, errors in expectations and linearization errors, and are modelled as a zero‐mean noise around the restrictions implied by the UIRP on a vector autoregression (VAR) in the interest rate differential and the spot exchange rate. Importantly, this approach includes the traditional one as a special case, which is derived by simply setting the noise to zero. When the noise is set to zero the UIRP is rejected, but if we allow for some degree of noise the UIRP is strongly supported by the data. Thus the UIRP relation does not hold exactly, but on average, with a stationary risk premium as opposed to a constant one. This result implies that analysing the effects of policy experiments under the null of the UIRP may be both safe and useful.     

Revisiting Error‐Autocorrelation Correction: Common Factor Restrictions and Granger Non‐Causality*

The paper questions the appropriateness of the practice known as ‘error‐autocorrelation correcting’ in linear regression, by showing that adopting an AR(1) error formulation is equivalent to assuming that the regressand does not Granger cause any of the regressors. This result is used to construct a new test for the common factor restrictions, as well as investigate – using Monte Carlo simulations – other potential sources of unreliability of inference resulting from this practice. The main conclusion is that when the Granger cause restriction is false, the ordinary least square and generalized least square estimators are biased and inconsistent, and using autocorrelation‐consistent standard errors does not improve the reliability of inference.     

A Non‐parametric Examination of Capital–Skill Complementarity*

This paper uses non‐parametric kernel methods to construct observation‐specific elasticities of substitution for a balanced panel of 73 developed and developing countries to examine the capital–skill complementarity hypothesis. The exercise shows some support for capital–skill complementarity, but the strength of the evidence depends upon the definition of skilled labour and the elasticity of substitution measure being used. The added flexibility of the non‐parametric procedure is also capable of uncover ing that the elasticities of substitution vary across countries, groups of countries and time periods.     

A Simple Test for Cointegration in Dependent Panels with Structural Breaks*

This paper develops a very simple test for the null hypothesis of no cointegration in panel data. The test is general enough to allow for heteroskedastic and serially correlated errors, unit‐specific time trends, cross‐sectional dependence and unknown structural breaks in both the intercept and slope of the cointegrated regression, which may be located at different dates for different units. The limiting distribution of the test is derived, and is found to be normal and free of nuisance parameters under the null. A small simulation study is also conducted to investigate the small‐sample properties of the test. In our empirical application, we provide new evidence concerning the purchasing power parity hypothesis.     

Exchange Rates and Fundamentals: Evidence from Long‐Horizon Regression Tests*

This article considers the long‐run relationship between nominal exchange rates and fundamentals from a different perspective. We apply a long‐horizon regression approach proposed by Fisher and Seater (1993) and find evidence supporting the explanatory power of exchange rate models. In particular, the Taylor‐rule model outperforms other conventional models. We then use the inverse power function (IPF) proposed by Andrews (1989) to investigate the power of the Fisher–Seater test. The IPF analysis provides additional evidence supporting exchange rate models.     

Time and causality: A Monte Carlo assessment of the timing-of-events approach

We present new Monte Carlo evidence regarding the feasibility of separating causality from selection within non-experimental duration data, by means of the non-parametric maximum likelihood estimator (NPMLE). Key findings are: (i) the NPMLE is extremely reliable, and it accurately separates the causal effects of treatment and duration dependence from sorting effects, almost regardless of the true unobserved heterogeneity distribution; (ii) the NPMLE is normally distributed, and standard errors can be computed directly from the optimally selected model; and (iii) unjustified restrictions on the heterogeneity distribution, e.g., in terms of a pre-specified number of support points, may cause substantial bias.