In this paper we develop a semi-parametric approach to model nonlinear relationships in serially correlated data. To illustrate the usefulness of this approach, we apply it to a set of hourly electricity load data. This approach takes into consideration the effect of temperature combined with those of time-of-day and type-of-day via nonparametric estimation. In addition, an ARIMA model is used to model the serial correlation in the data. An iterative backfitting algorithm is used to estimate the model. Post-sample forecasting performance is evaluated and comparative results are presented.  Copyright © 2006 John Wiley & Sons, Ltd.

In this paper a class of nonparametric transfer function models is proposed to model nonlinear relationships between 'input' and 'output' time series. In this approach, the functional form of the transfer function is assumed to be unknown but smooth, and the noise is assumed to be stationary with a parametric autoregressive-moving average (ARMA) form. A new method is developed to jointly estimate the transfer function nonparametrically and the ARMA parameters parametrically. By modeling the transfer function nonparametrically, the model is flexible and can be used to model nonlinear relationship of unknown functional forms; by modeling the noise explicitly as a parsimonious ARMA model, the correlation in the data is removed so the transfer function can be estimated more efficiently. Additionally, the estimated ARMA parameters can be used to improve the forecasting performance. Estimation procedures are introduced and the asymptotic properties of the estimators are investigated. The finite-sample properties of the estimators are studied through simulations and one real example.JEL Classification: C14, C22

The logistics and manufacturing industries’ co-agglomeration (LMCA) and deep integration, as well as the industries’ digital transformation and intelligent upgrading, are of great significance to enhance regional economic resilience (EcoResi). This paper establishes a theoretical framework for LMCA and EcoResi based on the economic development theory and the new economic geography theory, explores the spatial spillover effect of LMCA on EcoResi, and measures the levels of LMCA and EcoResi. The data set is consisted of the indicators of LMCA and GDP growth rate of 30 provinces, centrally administered municipalities, and autonomous regions in China from 2006 to 2020. Spatial econometric models were used to empirically analyze the impact of LMCA on EcoResi based on provincial panel data. The results show that the improvement in LMCA not only improves the resilience of local economy, but it also has a significant spatial spillover effect. Further regional analyses show that LMCA has significant stimulating effects and spatial spillover effects on EcoResi in the central and western regions of China. However, the same effects are not significant in the eastern region of China. This research enriches the literature by suggesting effective ways to enhance EcoResi through LMCA.

SummaryIn this paper a semi‐parametric approach is developed to model non‐linear relationships in time series data using polynomial splines. Polynomial splines require very little assumption about the functional form of the underlying relationship, so they are very flexible and can be used to model highly non‐linear relationships. Polynomial splines are also computationally very efficient. The serial correlation in the data is accounted for by modelling the noise as an autoregressive integrated moving average (ARIMA) process, by doing so, the efficiency in nonparametric estimation is improved and correct inferences can be obtained. The explicit structure of the ARIMA model allows the correlation information to be used to improve forecasting performance. An algorithm is developed to automatically select and estimate the polynomial spline model and the ARIMA model through backfitting. This method is applied on a real‐life data set to forecast hourly electricity usage. The non‐linear effect of temperature on hourly electricity usage is allowed to be different at different hours of the day and days of the week. The forecasting performance of the developed method is evaluated in post‐sample forecasting and compared with several well‐accepted models. The results show the performance of the proposed model is comparable with a long short‐term memory deep learning model.