Threshold effect in the relationship between investor sentiment and stock market returns: a PSTR specification

This article verifies whether the hypothesis of heterogeneous agent modelling and the behavioural heterogeneity framework can reproduce recent stylized facts regarding stock markets (e.g. the 1987 crash, internet bubble, and subprime crisis). To this end, we investigate the relationship between investor sentiment and stock market returns for the G7 countries from June 1987 to February 2014. We propose an empirical non-linear panel data specification based on the panel switching transition model to capture the investor sentiment-stock return relationship, while enabling investor sentiment to act asymmetrically, non-linearly, and time varyingly according to the market state and investor attitude towards risk. Our findings are twofold. First, we show that the hypotheses of efficiency, rationality, and representative agent do not hold in reproducing stock market dynamics. Second, investor sentiment affects stock returns significantly and non-linearly, but its effects vary with the market conditions. Indeed, the market appears predominated by fundamental investors in the first regime. In the second regime, investor sentiment effect is positively activated, increasing stock returns; however, when their overconfidence sentiment exceeds some threshold, this effect becomes inverse in the third regime for a high threshold level of market confidence and investor over-optimism.     

Modelling a mixed system of air pollution fee and tradable permits for controlling nitrogen oxide: a case study of Taiwan*

A mixed-integer non-linear programming model that minimises the total regulatory costs of controlling nitrogen oxide is used to investigate how a newly proposed permit trading scheme in Taiwan, which incorporates the features of banking and a non-one-to-one trading ratio, may affect firms’ emission reduction strategies and permit trading decisions. Compared to the previous regulation where only an air pollution fee is used, the new regulation that requires a reduction in emissions by 10 per cent from the emission level in the year 2000 for a 5 year period will increase the costs by 77 per cent, which is equivalent to US$9.87 million. The design of banking and the increasing returns to scale characteristic of pollution control among firms might lead to an uneven reduction in emissions in each year. Setting a lower reservation rate for banking would, however, help maintain a more stable environmental quality without a significant loss to the government in terms of air pollution fee revenue.     

基于指导型盲源分离和非高斯准则的全双工认知

为了克服半双工认知中存在的静态感知问题和常规全双工认知中残余自干扰限制的影响,提出了一种基于指导型盲源分离和非高斯准则的新型全双工认知方法。该方法将频谱感知和数据传输设计于同位置执行,避免在感知信息中的任何不匹配和资源损失,利用同位置配置中已知的次用户信号作为指导信号辅助执行盲源分离工作。在分离处理后,利用相关性识别出次用户自发信号,另一个信号通过非高斯准则判定,进而判决主用户的活动状态。仿真实验分析和讨论验证了所提方法的有效性,与基于自干扰消除的全双工频谱感知方案相比在计算复杂度和感知性能上具有明显的优越性。     

资产价格产生非线性特征的内在原因分析——基于异质信念资产定价模型的蒙特卡罗法模拟

基于异质信念资产定价模型,运用蒙特卡罗模拟的方法产生异质信念下资产均衡价格的时间序列数据,并对其非线性特征进行相关检验。研究发现,该时间序列具有尖峰肥尾特征、波动率聚类现象和自相似特征,但没能捕捉到长期记忆现象。说明投资者的并质信念是资产价格产生非线性特征的重要内在原因。     

科技要素投入配置与经济增长非线性相关的预测研究——以江西省赣州市为例

科技要素投入对科学技术由知识形态的生产力向现实的生产力转化起到了至关重要的作用。文章通过实证研究,在基于达到全国平均水平的基础上,建立了赣州科技人力资源投入与地区生产总值的非线性回归模型,并通过对江西省赣州市科技人力资源及R＆D投入相互作用的分析,对非线性回归模型所体现的问题进行分析,对当前经济社会中所存在的问题进行剖析,以期对科技要素投入配置提供相应的决策依据。     

Horseshoe Regularisation for Machine Learning in Complex and Deep Models1

Since the advent of the horseshoe priors for regularisation, global–local shrinkage methods have proved to be a fertile ground for the development of Bayesian methodology in machine learning, specifically for high-dimensional regression and classification problems. They have achieved remarkable success in computation and enjoy strong theoretical support. Most of the existing literature has focused on the linear Gaussian case; for which systematic surveys are available. The purpose of the current article is to demonstrate that the horseshoe regularisation is useful far more broadly, by reviewing both methodological and computational developments in complex models that are more relevant to machine learning applications. Specifically, we focus on methodological challenges in horseshoe regularisation in non-linear and non-Gaussian models, multivariate models and deep neural networks. We also outline the recent computational developments in horseshoe shrinkage for complex models along with a list of available software implementations that allows one to venture out beyond the comfort zone of the canonical linear regression problems.     

Asymmetric monetary policy rules in Australia

In this study, the hypothesis that the Reserve Bank of Australia (RBA) implements an asymmetric monetary policy rule is tested. We estimate both linear and asymmetric monetary policy reaction functions for the period before inflation targeting was adopted, for the period when inflation targeting was explicitly adopted and for the full sample period. The results of the linear monetary policy rules are consistent with the estimates reported from other studies that estimate linear monetary policy rules for Australia. On the other hand, the results of estimating the asymmetric monetary policy rules for the pre-inflation targeting period shows that the RBA had reacted symmetrically, suggesting that it had acted with the same aggressiveness towards both inflation and output gaps of the same magnitude, over both phases of the business cycle. However, for the inflation targeting period, the results show that the RBA had reacted asymmetrically in its policy response to the inflation gap, output gap or both. A similar result is found for the full sample period. This asymmetric response supports the view that a non-linear monetary policy rule emanated from asymmetric preferences, rather than from the existence of a non-linear Phillips curve.     

区域地下水开采与地面沉降控制三维全耦合数值模拟

针对第四纪松散沉积层中地下水开采所引起的地面沉降问题,以比奥固结理论为基础,考虑到土体的非线性特征及土体的渗透性随应力状态的动态变化,引入邓肯-张非线性模型和渗透率动态模型,将地下水渗流场和土体应力场耦合起来,并以江阴市浅层地下水开采为例,建立了浅层地下水开采与地面沉降三维全耦合数值模型。在对模型进行校正、识别的基础上,以第Ⅰ承压含水层未来10年内地下水位埋深不低于含水层顶板埋深一半,地面沉降量不超过50mm为约束条件,预测了江阴市各镇的地下水可采资源量以及地面沉降量。实践表明,该模型不仅稳定性好,且收敛速度快。     

收入与出境旅游率的非线性关系——基于门槛面板模型的实证证据

在各种有关出境旅游市场影响因素的研究中,收入水平与出境旅游的关系存在着显著的争议。文章判断二者之间存在着非线性关系,且因国家而异。该研究引入门槛回归模型,以世界95个国家和地区为研究总样本,并按照面积大小划分为3组,利用其1995~2011年的人均国民收入、出境旅游率、年龄结构、教育水平和就业水平数据,对收入和出境旅游率之间的相关关系进行了深入分析。研究发现:(1)各样本中,收入与出境旅游率均呈显著非线性相关。(2)样本不同,收入门槛值的数量和位置不同,促使出境旅游快速发展的收入门槛值也不同。说明国土面积对收入与出境旅游的关系具有潜在影响。(3)各控制变量总体上对出境旅游率具有正面影响。(4)中国出境旅游实际表现超过理论基准,处于快速超前发展的阶段。以上研究结果可以为一个国家或地区判定出境旅游的发展阶段及制定合适的旅游政策提供依据。     

多元化对银行绩效的非线性影响——基于多元化水平的横向分析

金融领域有关多元化对银行绩效影响的研究主要是针对不同银行类别的探讨(纵向)。文章发现,多元化对银行绩效的不同影响与银行类别无关,而与多元化的不同水平相关(横向)。基于16家中国上市商业银行2005—2012年的面板数据,文章分别运用多个多元化和银行绩效指标进行回归分析,发现多元化水平对银行绩效存在倒U型影响;把所有样本分银行类别和分时间段进一步回归分析,确认了在多元化水平较低的前期,多元化带来银行绩效的改善,但是随着多元化的过度实施,对银行绩效产生负向影响。