I consider the asymptotic properties of a commonly advocated covariance matrix estimator for panel data. Under asymptotics where the cross-section dimension, n, grows large with the time dimension, T, fixed, the estimator is consistent while allowing essentially arbitrary correlation within each individual. However, many panel data sets have a non-negligible time dimension. I extend the usual a...

Using a panel data set of bilateral export flows from 12 EU countries to 20 OECD trading partners over the period 1992-2003, a panel cointegration approach to estimating the gravity model is adopted to test for the significance of European regional integration. A comparison of the results indicates that a positive and significant coefficient estimate of the EU dummy variable is found for both t...

We develop a set of nonparametric rank tests for non-stationary panels based on multivariate variance ratios which use untruncated kernels. As such, the tests do not require the choice of tuning parameters associated with bandwidth or lag length and also do not require choices with respect to numbers of common factors. The tests allow for unrestricted cross-sectional dependence and dynamic hete...

A semiparametric regression estimator that exploits categorical (i.e. discretesupport) kernel functions is developed for a broad class of hierarchical models including the pooled regression estimator, the fixed-effects estimator familiar from panel data, and the varying coefficient estimator, among others. Separate shrinking is allowed for each coefficient. Regressors may be continuous or discr...

We consider a common-components model for multivariate fractional cointegration, in which the s ≥ 1 components have different memory parameters. The cointegrating rank may exceed 1. We decompose the true cointegrating vectors into orthogonal fractional cointegrating subspaces such that vectors from distinct subspaces yield cointegrating errors with distinct memory parameters. We estimate each c...

In this paper we propose to overcome the problem of spurious regression between fractionally differenced processes by applying the discrete wavelet transform (DWT) to both processes and then estimating the regression in the wavelet domain. The DWT is known to approximately decorrelate heavily autocorrelated processes and, unlike applying a first difference filter, involves a recursive two-step ...

We propose a semiparametric first-difference estimator for panel censored-selection models where the selection equation is of tobit type. The estimator allows the unit-specific term to be arbitrarily related to regressors. The estimator minimizes a convex function and does not require any smoothing. A simulation study is provided comparing our proposal with the estimators of Wooldridge (Journal...