7 February 2026 in Journal of Econometrics
6 September 2026 in Journal of Econometrics
12 July 2022 in SSRN Electronic Journal
Time-varying coefficient models have been widely used to model changing relationships of economic and financial variables. The existing literature usually specifies the time-varying coefficient vector as a stochastic stationary process, a deterministic function of time, or a unit root process. In this paper, we propose two tests to distinguish these three specifications. Both test statistics follow asymptotic normal distributions under the respective null hypotheses and diverge to infinity in probability under the corresponding alternatives. To improve the finite sample performance of the tests, we propose a dependent wild bootstrap (DWB) to obtain the bootstrapped critical value or p-value and establish its asymptotic validity. Simulations show that our bootstrap-based tests perform reasonably well in finite samples. We apply the proposed tests to the time-varying specifications of the equity return's predictive model, Taylor rule, and inflation persistence. The results suggest that a unit root process is favored for the first application, while a deterministic function of time should be adopted for the last two applications.
21 September 2026 in SSRN Electronic Journal
Economic relationships estimated in one population are often used for inference or prediction in another, making transferability an important empirical question. We test whether a population conditional-mean relation learned in a source environment remains valid for the target population. The formulation is directional and requires only source coverage of target-relevant covariates. We construct the test from target outcomes and reweighted source moments, without estimating the target regression. A source residual makes the resulting score Neyman orthogonal, so that estimation of the source regression and the reweighting term affects the population moment only through the product of the two estimation errors. Gaussian integration yields a closed-form omnibus statistic. We establish consistency and nontrivial power against root-n-local alternatives under unequal sample sizes, serial dependence, and common shocks, and obtain critical values from a design-specific dependent wild bootstrap. Simulations examine finite-sample behavior under covariate shift and dependence, and an experiment with a smaller target sample studies the implications of avoiding target-regression estimation. Applications study statistical Engel curves and the transferability of employment relations summarized by source-trained model scores.
24 March 2020 in SSRN Electronic Journal
We estimate and test for multiple structural breaks in distribution with unknown break dates via a characteristic function approach. By minimizing the sum of squared generalized residuals, we can consistently estimate the break fractions. We propose a sup-F type test for structural breaks in distribution and suggest an information criterion and a sequential testing procedure to determine the number of breaks. We further construct a class of derivative tests to gauge the possible source of structural breaks, which is asymptotically more powerful than the nonparametric-based tests for structural breaks. Simulation studies show that our method performs well in determining the appropriate number of breaks and estimating the unknown breaks. Furthermore, the proposed tests have reasonable size and excellent power. In an application to exchange rate returns, our tests are able to detect structural breaks in distribution and locate the break dates. Our derivate tests indicate that the documented breaks appear to occur in variance and higher order moments, but not so often in mean.
24 March 2020 in SSRN Electronic Journal
We propose a new test for structural changes in large dimensional factor models via a discrete Fourier transform (DFT) approach. If structural changes occur, the conventional principal component analysis fails to estimate common factors and factor loadings consistently. The estimated residuals will contain information about structural changes. Therefore, we can compare the DFT of the estimated residuals with the null (zero) spectrum implied by no structural change. The proposed test is powerful against both smooth structural changes and abrupt structural breaks with a possibly unknown number of breaks and unknown break dates in factor loadings. It can detect a class of local alternatives at the parametric rate. As a result, the test is asymptotically more efficient than the existing tests in the factor model literature. And our test is also robust to serial and cross-sectional dependence of unknown form without having to estimate any long-run variance-covariance matrix. Moreover, it is easy to implement and tuning parameter-free. Monte Carlo studies demonstrate its reasonable size and excellent power in detecting various forms of structural changes in factor loadings. In an application to the U.S. macroeconomic data, we find significant and robust evidence of time-varying factor loadings.