In this paper, we make multi-step forecasts of the annual growth rates of the real GRP for each of the 31 Chinese provinces simultaneously. Beside the usual panel data models, we use panel models that explicitly account for spatial dependence between the GRP growth rates. In addition, the possibility of spatial effects being different for different groups of provinces (Interior and Coast) is allowed. We find that both pooling and accounting for spatial effects helps substantially improve the forecast performance compared to the benchmark models estimated for each of the provinces separately. It was also shown that effect of accounting for spatial dependence is even more pronounced at longer forecasting horizons (the forecast accuracy gain as measured by the root mean squared forecast error is about 8% at 1-year horizon and exceeds 25% at 13- and 14-year horizon).
Chinese provinces forecasting dynamic panel model spatial autocorrelation group-specific spatial dependence