Deniz Dilan Karaman Örsal

Comparison of Panel Cointegration Tests

The main aim of this paper is to compare the size and size-adjusted power properties of four residual-based and one maximum-likelihood-based panel cointegration tests with the help of Monte Carlo simulations. In this study the panel-rho, the group-rho, the parametric panel-t, the parametric group-t statistics of Pedroni(1999} and the standardized LR-bar statistic of Larsson et al.(2001} are considered. The simulation results indicate that the panel-t and the standardized LR-bar statistic have the best size and power properties among the five panel cointegration test statistics evaluated.

Likelihood-based panel cointegration test in the presence of a linear time trend and cross-sectional dependence

ABSTRACT This article proposes a new likelihood-based panel cointegration rank test which extends the test of Örsal and Droge (2014) (henceforth panel SL test) to dependent panels. The dependence is modelled by unobserved common factors which affect the variables in each cross-section through heterogeneous loadings. The data are defactored following the panel analysis of nonstationarity in idiosyncratic and common components (PANIC) approach of Bai and Ng (2004) and the cointegrating rank of the defactored data is then tested by the panel SL test. A Monte Carlo study demonstrates that the proposed testing procedure has reasonable size and power properties in finite samples.

Panel cointegration testing in the presence of a time trend

A new likelihood-based panel cointegration test which allows a linear time trend in the data generating process is proposed. The test is an extension of the likelihood ratio type test with trend adjustment prior to testing to the panel data framework. Under the null hypothesis, the standardized statistic has a limiting normal distribution as the number of time periods and the number of cross-sections tend to infinity sequentially. Additionally, an approximation involving the moments based on a vector autoregressive process of order one is introduced. A Monte Carlo study demonstrates that the test has reasonable size and high power in finite samples.

The Changing Relationship Between Unemployment and Total Fertility

The aim of this paper is to investigate whether there has been a fundamental change in the relationship between economic conditions and fertility. We use panel data methods to study the short-term changes in total fertility and the unemployment rate in a range of Organisation for Economic Co-operation and Development (OECD) countries from 1957 to 2014. We find that although fertility was counter-cyclical before 1970, with good economic times being associated with lower fertility, since then it has become pro-cyclical, with good economic times being associated with higher fertility.

On the Existence of the Moments of the Asymptotic Trace Statistic

In this note we establish the existence of the first two moments of the asymptotic trace statistic, which appears as weak limit of the likelihood ratio statistic for testing the cointe- gration rank in a vector autoregressive model and whose moments may be used to develop panel cointegration tests. Moreover, we justify the common practice to approximate these moments by simulating a certain statistic, which converges weakly to the asymptotic trace statistic. To accomplish this we show that the moments of the mentioned statistic converge to those of the asymptotic trace statistic as the time dimension tends to infinity.

Analysing money demand relation for OECD countries using common factors

ABSTRACT This article investigates the existence of a long-run money demand relation for a panel data consisting of 13 OECD countries. The analysis is based on the most recent data. The existence of a long-run money demand relation is tested with two new meta-analytic panel cointegrating rank tests which are robust to cross-sectional dependence. Cross-sectional dependency in the data generating process is modelled by unobserved common factors. The observed data are decomposed into idiosyncratic and common components, and these two components are analysed separately to find out the driving forces of the long-run stationary relationship. The evidence shows that the long-run money demand relation is driven by the cross-unit cointegration. Finally, the long-run relation is estimated by taking the common factors into account.This article investigates the existence of a long-run money demand relation for a panel data consisting of 13 OECD countries. The analysis is based on the most recent data. The existence of a long-run money demand relation is tested with two new meta-analytic panel cointegrating rank tests which are robust to cross-sectional dependence. Cross-sectional dependency in the data generating process is modelled by unobserved common factors. The observed data are decomposed into idiosyncratic and common components, and these two components are analysed separately to find out the driving forces of the long-run stationary relationship. The evidence shows that the long-run money demand relation is driven by the cross-unit cointegration. Finally, the long-run relation is estimated by taking the common factors into account.

Essays on panel cointegration testing

This thesis is composed of four essays which contribute to the literature in panel cointegration methodology. The first essay compares the finite sample properties of the four residual-based panel cointegration tests of Pedroni (1995, 1999) and the likelihood-based panel cointegration test of Larsson et al. (2001). The simulation results indicate that the panel-t test statistic of Pedroni (1995, 1999) has the best finite sample properties among the five panel cointegration test statistics evaluated. The second essay presents a corrected version of the proof of Larsson et al. (2001) related to the finiteness of the moments of the asymptotic trace statistic. The proof is corrected for the case, in which the difference between the number of variables and the number of existing cointegrating relations is one. The third essay proposes a new likelihood-based panel cointegration test in the presence of a linear time trend in the data generating process. This new test is an extension of the likelihood ratio test of Saikkonen and Lütkepohl (2000a) for trend-adjusted data to the panel data framework, and is called the panel SL test. The idea is first to take the average of the individual LR (trace) statistics over the cross-sections and then to standardize the test statistic with the appropriate asymptotic moments. Under the null hypothesis, the panel SL test statistic is standard normally distributed as the number of time periods (T ) and the number of cross-sections (N) tend to infinity sequentially. By means of a Monte Carlo study the finite sample properties of the test are investigated. The new test presents reasonable size with the increase in T and N , and has high power in small samples. The last essay of the thesis analyzes the long-run money demand relation among OECD countries by panel unit root and cointegration testing techniques. The panel SL cointegration test and the tests of Pedroni (1999) are used to detect the existence of a stationary long-run money demand relation. Moreover, the money demand function is estimated with the panel dynamic ordinary least squares method of Mark and Sul (2003).