This paper develops two very simple tests for the null hypothesis of no cointegration in panel data. The tests are general enough to allow for heteroskedastic and serially correlated errors, unit specific time trends, cross-sectional dependence and an unknown structural break in both the intercept and slope of the cointegrated regression, which may be located at different dates for different un...

Testing whether two parameters have the same sign is a nonstandard problem due to the non-convex shape of the parameter subspace satisfying the composite null hypothesis, which is a nonlinear inequality constraint. We describe a simple example where the ordering of likelihood ratio (LR), Wald, and Bayesian sign equality tests reverses the “usual” ordering: the Wald rejection region is a subset ...

JEL Classification C12; C23; G21; G32. The only way to ensure a well-informed response to bank risks is by ensuring transparent disclosures that flourish with potential synergy. This study investigates the impact of bank disclosures on credit risk where panel data are used. PCSE and FGLS regression models are applied to a sample of 32 commercial banks in Bangladesh from 2010 to 2014. The result...

In this paper, we investigate the asymmetry in the tail dependence between US equity portfolios and the aggregate US market. Given the limited number of observations in the tails of a joint distribution, standard non-parametric measures of tail dependence often have poor finite-sample properties. We therefore develop a parametric model for measuring and testing asymmetry in tail dependence, usi...

In this paper, we propose new tests for threshold cointegration in the conditional autoregressive distributed lag (ADL) model. The indicators in the threshold model are based on either a nonstationary or stationary threshold variable. The proposed tests are appropriate when the conditioning variables are weakly exogenous. The cointegrating vector in this paper is not pre-specified. We adopt a s...

We propose a new robust hypothesis test for (possibly nonlinear) constraints on Mestimators with possibly non-differentiable estimating functions. The proposed test employs a random normalizing matrix computed from recursive M-estimators to eliminate the nuisance parameters arising from the asymptotic covariance matrix. It does not require consistent estimation of any nuisance parameters, in co...

Many questions in economics involve long-run or “trend” variation and covariation in time series. Yet, time series of typical lengths contain only limited information about this long-run variation. This paper suggests that long-run sample information can be isolated using a small number of low-frequency trigonometric weighted averages, which in turn can be used to conduct inference about long-r...

Tests of stationarity are routinely applied to highly autocorrelated time series. Following Kwiatkowski et al. (J. Econom. 54 (1992) 159), standard stationarity tests employ a rescaling by an estimator of the long-run variance of the (potentially) stationary series. This paper analytically investigates the size and power properties of such tests when the series are strongly autocorrelated in a ...

This paper considers nonstandard hypothesis testing problems that involve a nuisance parameter. We establish an upper bound on the weighted average power of all valid tests, and develop a numerical algorithm that determines a feasible test with power close to the bound. The approach is illustrated in six applications: inference about a linear regression coefficient when the sign of a control co...

Fisher’s pivot functions (PFs) continue to dominate statistical inference and bootstrap literature, despite Efron and Hinkley and Royall’s attempts to inject robustness. Vinod uses Godambe’s pivot functions (GPFs) based on Godambe—Durbin estimating functions (EFs) to develop numerically computed GPF roots. Such GPF roots can fill a long-standing need in the bootstrap literature for robust pivot...