Skip to main content

Research

Response surface models for the Leybourne unit root tests and lag order dependence (with Jesus Otero).

The paper calculates response surface models for a large range of quantiles of the Leybourne (1995) test for the null hypothesis of a unit root against the alternative of (trend) stationarity. The simulated critical values along with the corresponding p-values can be otained from the excel file:Simulated critical values and p-values for Leybourne Test (xlsx file).


Response surface estimates of the cross-sectionally augmented IPS tests for panel unit roots (with Jesus Otero).

The paper calculates response surface models for a large range of quantiles of the Pesaran (2007) (CIPS) test for the null hypothesis of a unit root against the alternative of (trend) stationarity. The simulated critical values along with the corresponding p-values can be otained from the excel file:Simulated critical values and p-values for CIPS Test (xlsx file).

Response surface models for OLS and GLS detrending-based unit root tests in nonlinear ESTAR models (with Jesus Otero).

This paper calculates response surface models for a large range of quantiles of the Kapetanios, Shin and Snell (2003) and Kapetanios and Shin (2008) tests for the null hypothesis of a unit root, against the alternative that the series of interest follows a globally stationary exponential smooth transition autoregressive process. The response surface models allow the estimation of finite sample critical values and approximate p-values for di.erent combinations of number of observations,
T, and lag order in the test regression, p, where the latter can be either specified by the user or optimally selected using a datadependent procedure. The new Stata commands kssur and ksur are presented, and their use illustrated with an empirical example (coffee prices).