Volume 27, Issue 3

This paper proposes a ridge-type method for determining the number of factors in an approximate factor model. The new estimator of factor number is obtained by maximizing both the ratio of two adjacent eigenvalues and the cumulative contribution rate of the factors which represents the explanatory power of the common factors for response variables. Our estimator is proved to be as asymptotically consistent as those in (Ahn, S., and A. Horenstein. 2013. “Eigenvalue Ratio Test for the Number of Factors.” Econometrica 81: 1203–27). But Monte Carlo simulation experiments show our method has better correct selection rates in finite sample cases. A real data example is given for illustration.

Assessing the causal relationships between clean energy consumption and economic growth in China, a central actor in the world’s climate future, have received considerable attention among scholars. However, due to the lack of methodological rigour in the causality analysis, available literature failed to provide solid inferences on the links between the variables. Therefore, this study aims to re-examine the variables’ dynamic linkages with a more well-established approach from 1965 to 2020. We use a time-varying framework that relaxes the assumption of parameter stability, a remarkable feature that distinguishes our paper from the previous studies. Utilizing the conventional Granger causality test, we fail to detect causation between the variables. However, the evidence of substantial time variation in the causal relationships implies that the standard framework’s inference is unreliable. The findings of our time-varying analysis indicate different forms of causality flows in various subperiods. This can be a dependable reason for China to follow its enhanced carbon neutrality target safely. The results of our study also emphasize the significance of considering time-varying causality tests to avoid the risk of misleading inferences.

We develop threshold estimation methods for panel data models with two threshold variables and individual fixed specific effects covering short time periods. In the static panel data model, we propose least squares estimation of the threshold and regression slopes using fixed effects transformations; while in the dynamic panel data model, we propose maximum likelihood estimation of the threshold and slope parameters using first difference transformations. In both models, we propose to estimate the threshold parameters sequentially. We apply the methods to a 15-year sample of 565 U.S. firms to test whether financial constraints affect investment decisions.

This paper provides a theoretical investigation of possible sources of long-run economic growth in the future. Historically, in the industrial era and during the ongoing digital revolution (which began approximately in the 1980s) the main engine of global economic growth has been research and development (R&D), translating into systematic labor-augmenting technological progress and trend growth in labor productivity. If in the future all essential production or R&D tasks will eventually be subject to automation, though, the engine of growth will be shifted to the accumulation of programmable hardware (capital), and R&D will lose its prominence. Economic growth will then accelerate, no longer constrained by the scarce human input. By contrast, if some essential production and R&D tasks will never be fully automatable, then R&D may forever remain the main growth engine, and the human input may forever remain the scarce, limiting factor of global growth. Additional studied mechanisms include the accumulation of R&D capital and hardware-augmenting technical change.

Most previous studies that examined the relationship between the size of shadow economy and the pillars of sustainable development maintained that this relationship is linear. This paper provides an empirical contribution to the literature by arguing that this relationship is likely to be nonlinear, and it might be subject to threshold effects. For this purpose, in addition to the static threshold panel model of Hansen (1999. “Threshold Effects in Non-dynamic Panels: Estimation, Testing, and Inference.” Journal of Econometrics 93 (2): 345–68), the dynamic panel threshold model suggested by Seo and Shin (2016. “Dynamic Panels with Threshold Effect and Endogeneity.” Journal of Econometrics 195 (2): 169–86) has been applied to a larger panel-data set covering 83 developed and developing countries over the 1996–2017 period. Empirical results from both models yield evidence advocating the existence of threshold effects of the shadow economy on the economic, social, and environmental dimensions of sustainable development for the global sample as well as the sub-samples of developed and developing countries. Moreover, for the global sample and developing countries, our findings show that shadow economy would spoil the three sustainable development pillars only when its size exceeds a certain threshold critical size. While, the impact for developed countries was found negative even for low levels of underground activities. These finding are shown to be robust to alternative proxies for the size of the shadow economy and have important policy implications, especially for developing countries. In these countries, a moderate size of the shadow economy might have positive spillovers on long-term growth and sustainable development. Our research also suggests that, for developing and developed countries to achieve sustainable goal 8.3, the extent of the shadow activities should be taken into account.

This paper studies the tail behaviours of the stationary distribution of multiple-regime threshold AR models with multiple heavy-tailed innovations. It is shown that the marginal tail probability has the same order as that of the innovation with the heaviest tail. Other new results in this paper include the geometric ergodicity and the tail dependence of TAR models with multiple heavy-tailed innovations.

Stock price prediction has become a focal topic for relevant investors and scholars in these years. However, owning to the non-stationarity and complexity of stock price data, it is challenging to predict stock price accurately. This research develops a novel multi-scale nonlinear ensemble learning framework for stock price prediction, which consists of variational mode decomposition (VMD), evolutionary weighted support vector regression (EWSVR) and long short-term memory network (LSTM). The VMD is utilized to extract the basic features from an original stock price signal and eliminate the disturbance of illusive components. The EWSVR is utilized to predict each sub-signal with corresponding features, whose penalty weights are determined according to the time order and whose parameters are optimized by tree-structured Parzen estimator (TPE). The LSTM-based nonlinear ensemble learning paradigm is employed to integrate the predicted value of each sub-signal into the final prediction result of stock price. Four real prediction cases are utilized to test the proposed model. The proposed model’s prediction results of multiple evaluation metrics are significantly improved compared to other benchmark models both in stock market closing price forecasting.