Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
1149527 | Journal of Statistical Planning and Inference | 2010 | 11 Pages |
Abstract
The paper considers local linear regression of a time series model with non-stationary regressors and errors. Asymptotic property of the local linear estimator is derived under a new dependence measure of non-stationary time series. We apply the local linear regression method to estimate the “time-varying” coefficients of an economic-causal model for the industrial sector of the U.S. economy. Nonparametric bootstrap test on the time-varying coefficients strongly suggests that the price/income elasticities of the U.S. durable goods demand are time-varying.
Related Topics
Physical Sciences and Engineering
Mathematics
Applied Mathematics
Authors
Kun Ho Kim, Zhou Zhou, Wei Biao Wu,