Estimation and Explanation of Time-Varying Weights in Chinese CPI

The time-varying weights in the Chinese consumer price index (CPI) are estimated using a time-varying coefficient model, which is shown to be useful for testing the CPI’s “weighting biases” and adjustment problem. The empirical results show that China’s CPI has “weighting biases,” in which the time-varying intercept reveals negative adjustment of the CPI. This means that people pay less for food and more for medical care, education, and housing. By comparing the weights between urban CPI and rural CPI, the extended examination suggests a widening income gap between urban and rural households.