Search results

This article investigates the robustness of impulse response estimators to near unit roots and near cointegration in vector autoregressive (VAR) models. We compare estimators based on VAR specifications determined by pretests for unit roots and cointegration as well as unrestricted VAR specifications in levels. Our main finding is that the impulse response estimators obtained from the levels specification tend to be most robust when the magnitude of the roots is not known. The pretest specification works well only when the restrictions imposed by the model are satisfied. Its performance deteriorates even for small deviations from the exact unit root for one or more model variables. We illustrate the practical relevance of our results through simulation examples and an empirical application.

Classical unit root tests are known to suffer from potentially crippling size distortions, and a range of procedures have been proposed to attenuate this problem, including the use of bootstrap procedures. It is also known that the estimating equation’s functional form can affect the outcome of the test, and various model selection procedures have been proposed to overcome this limitation. In this chapter, the authors adopt a model averaging procedure to deal with model uncertainty at the testing stage. In addition, the authors leverage an automatic model-free dependent bootstrap procedure where the null is imposed by simple differencing (the block length is automatically determined using recent developments for bootstrapping dependent processes). Monte Carlo simulations indicate that this approach exhibits the lowest size distortions among its peers in settings that confound existing approaches, while it has superior power relative to those peers whose size distortions do not preclude their general use. The proposed approach is fully automatic, and there are no nuisance parameters that have to be set by the user, which ought to appeal to practitioners.

This paper provides a selective survey of the panel macroeconometric techniques that focus on controlling the impact of “unobserved heterogeneity” across individuals and over time to obtain valid inference for “structures” that are common across individuals and over time. We consider issues of (i) estimating vector autoregressive models; (ii) testing of unit root or cointegration; (iii) statistical inference for dynamic simultaneous equations models; (iv) policy evaluation; and (v) aggregation and prediction.

This study aims to apply unit root test to investigate the behavior of Chinese firms toward their leverage policy. The study is based on two influential and competing theories of capital structure.

This study applies unit root test to investigate the behavior of Chinese firms toward their leverage policy. The study is based on two influential and competing theories of capital structure. Trade off theory advocates that firms have a target level of leverage ratio and that firms try to achieve that optimal leverage ratio, whereas pecking order theory argues that firms have no target level of leverage and that they follow a specific pattern of leverage. For this purpose, this study applies a Fisher type unit root test to 12,808 firm level observations. The data are unbalanced and cover a period from 1991 to 2014.

The results reveal the presence of a stationary behavior across short-term, long-term and total leverage policies. For short-term leverage policy, 21 per cent firms show stationary behavior, while for long-term, 20 per cent show a targeting behavior; for the total leverage policy 17 per cent of firms are found to follow a tradeoff model. To make the findings more interesting sample was further classified into profit and loss making firms. The study finds that loss making firms do not follow a target level of leverage in China. Furthermore, unit root is applied to all firms before and after crises-2008. It is revealed that stationary behavior is more prevalent before crises-2008.

This study is highly important from the point of view that it quantifies firms into distinct categories of following specific model of capital structure. To the best of the author’s knowledge, the findings of this study add to current research knowledge about Chinese firms with respect to adjustment behavior toward a target capital structure.

The purpose of this paper is to examine the time series properties of 26 macroeconomic variables in Papua New Guinea (PNG) over the period 1970‐2006.

Both unit root and stationarity tests without a structural break and the Lagrange Multiplier (LM) unit root test with one and two structural breaks developed by Lee and Strazicich are applied to each of the 26 macroeconomic variables in PNG. Compared to popular ADF‐type endogenous unit root tests such as those proposed by Zivot and Andrews and Lumsdaine and Papell, the LM unit root test with one and two structural breaks has the advantage that it is unaffected by breaks under the null.

The unit root and stationarity tests without structural breaks find at best mixed evidence of mean reversion and/or trend reversion for most variables. This result is likely to reflect the failure of these tests to allow for structural breaks, given the power to find stationarity declines if the data contain a structural break that is ignored. When the LM unit root test with one and two structural breaks is applied, it is found that at least 23 of the 26 macroeconomic variables are trend stationary.

The time series properties of macroeconomic variables have important implications for several macroeconomic theories. There are, however, few studies of the time series properties of macroeconomic variables in developing countries and no comprehensive studies for any of the Pacific Island countries. This paper begins to fill this gap as the first to provide a systematic examination of the time series properties of macroeconomic variables in Paua New Guinea.

This study aims to examine the hysteresis hypothesis in unemployment using monthly data from 13 countries in transition.

Stationarity in the unemployment rate of selected transition economies was analyzed using four different group unit root tests, namely, linear, structural breaks, non-linear and structural breaks and non-linear.

The empirical results show that the unemployment hysteresis hypothesis is valid for the majority of transition economies, including Bulgaria, Croatia, the Czech Republic, Estonia, Hungary, the Kyrgyz Republic, Latvia, Lithuania, Poland, Romania and Slovenia. However, the results strongly reject the null hypothesis of unemployment hysteresis for the Kazakhstan and the Slovak Republics.

This study revealed that, for countries in transition, advanced unit root tests exhibit greater validity when compared to standard tests

This paper investigates forecasting US Treasury bond and Dollar Eurocurrency rates using the stochastic unit root (STUR) model of Leybourne et al. (1996), and the stochastic cointegration (SC) model of Harris et al. (2002, 2006). Both models have time-varying parameter representations and are conceptually attractive for modelling interest rates as both allow for conditional heteroscedasticity. I find that for many of the series considered STUR and SC models generate statistically significant gains in out-of-sample forecasting accuracy relative to simple orthodox models. The results obtained highlight the usefulness of these extensions and raise some issues for future research.

The purpose of this paper is to evaluate threshold effects in the persistence of South African aggregate inflation data.

The conventional approach for assessing the degree of persistence within an inflation process is via its integration properties. This study makes use of univariate threshold autoregressive (TAR) models and associated unit root testing procedures to investigate the integration properties of the inflation data. Out‐of‐sample forecasts are further performed for the TAR models and their linear counterparts.

The empirical results confirm threshold effects in the persistence of all employed aggregated measures of inflation, whereas such asymmetric effects are ambiguous for disaggregated inflation measures. None of the observed series is found to be stationary in their levels. The out‐of‐sample forecasts for all TAR models outperform their linear counterparts.

Given the scope of the study, the empirical analysis provides insight with concern to the performance of inflation subsequent to the adoption of the inflation target regime in South Africa. Of particular interest are the low persistence levels observed at inflation rates of below 4.7 and 4.4 percent for core and CPI inflation, respectively, as both these aggregated measures of inflation play an essential role in guiding monetary policy conduct within the economy. The overall findings imply that on an aggregate level, the South African Reserve Bank's (SARB's) current inflation target of 3‐6 percent encompasses a non‐stationary inflation range and thus proves to be restrictive on monetary policy conduct.

The paper fills in an important gap in the academic literature by evaluating asymmetric effects in the integration properties of inflation, at both aggregated and disaggregated levels, for the exclusive case of South Africa.

This chapter examines the limit properties of information criteria (such as AIC, BIC, and HQIC) for distinguishing between the unit-root (UR) model and the various kinds of explosive models. The explosive models include the local-to-unit-root model from the explosive side the mildly explosive (ME) model, and the regular explosive model. Initial conditions with different orders of magnitude are considered. Both the OLS estimator and the indirect inference estimator are studied. It is found that BIC and HQIC, but not AIC, consistently select the UR model when data come from the UR model. When data come from the local-to-unit-root model from the explosive side, both BIC and HQIC select the wrong model with probability approaching 1 while AIC has a positive probability of selecting the right model in the limit. When data come from the regular explosive model or from the ME model in the form of 1 + n^α/n with α ∈ (0, 1), all three information criteria consistently select the true model. Indirect inference estimation can increase or decrease the probability for information criteria to select the right model asymptotically relative to OLS, depending on the information criteria and the true model. Simulation results confirm our asymptotic results in finite sample.