Search results

We compare the finite sample power of short- and long-horizon tests in nonlinear predictive regression models of regime switching between bull and bear markets, allowing for time varying transition probabilities. As a point of reference, we also provide a similar comparison in a linear predictive regression model without regime switching. Overall, our results do not support the contention of higher power in longer horizon tests in either the linear or nonlinear regime switching models. Nonetheless, it is possible that other plausible nonlinear models provide stronger justification for long-horizon tests.

To capture the last hour momentum over the intraday session, the authors develop a trading strategy for the exchange-traded fund (ETF) that is effective because of the T+0 trading rule. This strategy generates annualized excess return of 9.673%.

In this study, the authors identify a last hour momentum pattern in which the sixth (seventh) half-hour return predicts the next half-hour return by employing high frequency 2012–2017 data from the China Securities Index (CSI) 300 and its ETF.

Overall, both the predictability and the trading strategy are statistically and economically significant. In addition, the strategy performs more strongly on high volatility days, high trading volume days, high order-imbalance days and days without economic news releases than on other days.

Noise trading, late-information trading, infrequent rebalancing and disposition effects from retail investors may account for this phenomenon.

The author develops and extends the asymptotic F- and t-test theory in linear regression models where the regressors could be deterministic trends, unit-root processes, near-unit-root processes, among others. The author considers both the exogenous case where the regressors and the regression error are independent and the endogenous case where they are correlated. In the former case, the author designs a new set of basis functions that are invariant to the parameter estimation uncertainty and uses them to construct a new series long-run variance estimator. The author shows that the F-test version of the Wald statistic and the t-statistic are asymptotically F and t distributed, respectively. In the latter case, the author shows that the asymptotic F and t theory is still possible, but one has to develop it in a pseudo-frequency domain. The F and t approximations are more accurate than the more commonly used chi-squared and normal approximations. The resulting F and t tests are also easy to implement – they can be implemented in exactly the same way as the F and t tests in a classical normal linear regression.

I review the burgeoning literature on applications of Markov regime switching models in empirical finance. In particular, distinct attention is devoted to the ability of Markov Switching models to fit the data, filter unknown regimes and states on the basis of the data, to allow a powerful tool to test hypotheses formulated in light of financial theories, and to their forecasting performance with reference to both point and density predictions. The review covers papers concerning a multiplicity of sub-fields in financial economics, ranging from empirical analyses of stock returns, the term structure of default-free interest rates, the dynamics of exchange rates, as well as the joint process of stock and bond returns.

The purpose of this study is to explore and use artificial intelligence (AI) techniques for identifying the relevant attributes necessary to file a suspicious activity report (SAR) using historical customer transactions. This method is known as predictive modeling, a statistical approach which uses machine learning algorithm to predict outcomes by using historical data. The models are applied to a modified data set designed to mimic transactions of retail banking within the USA.

Machine learning classifiers, as a subset of AI, are trained using transactions that meet or exceed the minimum threshold amount that could generate an alert and report a SAR to the government authorities. The predictive models are developed to use customer transactional data to predict the probability that a transaction is reportable.

The performance of the machine learning classifiers is determined in terms of accuracy, misclassification, true positive rate, false positive rate and false negative rate. The decision tree model provided insight in terms of the attributes relevant for SAR filing based on the rule-based criteria of the algorithm.

This research is part of emerging studies in the field of compliance where AI/machine learning technology is used for transaction monitoring to identify relevant attributes for suspicious activity reporting. The research methodology may be replicated by other researchers, Bank Secrecy Act/anti-money laundering (BSA/AML) officers and model validation analysts for BSA/AML compliance models.

Purpose – The purpose of this chapter is to assess the role of collateralizable wealth and systemic risk in explaining future asset returns.

Methodology/approach – To test this hypothesis, the chapter uses the residuals of the trend relationship among housing wealth and labor income to predict both stock returns and government bond yields. Specifically, it shows that nonlinear deviations of housing wealth from its cointegrating relationship with labor income, hwy, forecast expected future returns.

Findings – Using data for a set of industrialized countries, the chapter finds that when the housing wealth-to-income ratio falls, investors demand a higher risk premium for stocks. As for government bond returns: (i) when they are seen as a component of asset wealth, investors react in the same manner and (ii) if, however, investors perceive the increase in government bond returns as signaling a future rise in taxes or a deterioration of public finances, then they interpret the fall in the housing wealth-to-income ratio as a fall in future bond premia. Finally, this work shows that the occurrence of crisis episodes amplifies the transmission of housing market shocks to financial markets.

Originality/value of chapter – These findings are novel. They also open new and challenging avenues for understanding the dynamics of the relationship between the housing sector, stock market and government bond developments, and the banking system.

The application of forecasting to health care is not new. A frequent issue in many Inpatient Rehabilitation Facilities (IRFs) is the fluctuating and unpredictable census. With scarce resources, particularly physical therapists and occupational therapists, this unpredictability makes appropriate scheduling of these resources challenging. This research addresses the issue of patient admissions in an inpatient rehabilitation facility attached to an 861 bed level-one trauma hospital. The goal is to develop a predictive model for the IRF's Census to assist in resource planning (e.g., labor, beds, and materials).

This paper aims to map out multi-agency partnerships in the UK information assurance (UKIA) network in the UK.

The paper surveyed members of the UKIA community and achieved a 52 percent response rate (n=104). The paper used a multi-dimensional scaling (MDS) technique to map the multi-agency cooperation space and factor analysis and ordinary least squares regression to identify predictive factors of cooperation frequency. Qualitative data were also solicited via the survey and interviews with security managers.

Via the quantitative measures, the paper locates gaps in the multi-agency cooperation network and identifies predictors of cooperation. The data indicate an over-crowded cybersecurity space, problems in apprehending perpetrators, and poor business case justifications for SMEs as potential inhibitors to cooperation, while concern over certain cybercrimes and perceptions of organisational effectiveness were identified as motivators.

The data suggest that the neo-liberal rationality that has been evoked in other areas of crime control is also evident in the control of cybercrimes. The paper concludes divisions exist between the High Policing rhetoric of the UK's Cyber Security Strategy and the (relatively) Low Policing cooperation outcomes in “on the ground” cyber-policing. If the cooperation outcomes advocated by the UK Cyber Security Strategy are to be realised, UKIA organisations must begin to acknowledge and remedy gaps and barriers in cooperation.

This paper provides the first mixed-methods evidence on the multi-agency cooperation patterns amongst the UKIA community in the UK and highlights significant gaps in the network.

The purpose of this paper is to study a novel and direct measurement of investor sentiment index in the Tunisian stock market that overcomes the weaknesses of a well-known investor sentiment index by Baker and Wurgler (2006, 2007).

Based on the data of 43 firms of the Tunisian stock market index (Tunindex) over the period 2004–2016, the author constructs a monthly investor sentiment that reflects both the economic fundamentals and the investor sentiment components. Seven indirect indicators collected from investor sentiment literature and Tunisian stock exchange were analyzed. Specifically, after accounting to remove the sentiment component for macroeconomic factors, the author estimates each sentiment proxy with a number of controlling variables. The residual from the estimation is used to define the author’s measure of excessive investor sentiment. To determine the best timing of sentiment indicators, the author employs a factor sentiment series as the first principal component of these total seven sentiment proxies and their lags of a month. Furthermore, by capturing the highest saturations with the first factor analysis, the author regressed each selected indicator’s lead or one-month lag in a second linear principal component analysis to reach the author’s Tunisian market’s total sentiment index.

The results show that all employed indicators may reflect the investor sentiment on the Tunisian stock market. The findings also indicate significant evidence that the author’s sentiment index takes into consideration the political and economic events such as the Jasmine Revolution experienced by Tunisia during the period from January 2, 2004 to December 30, 2016. Moreover, investor sentiment index flow appears to be one leading mechanism for the performance of Tunindex.

Results found have clearly shown that the author’s seven indirect indicators can reflect investor sentiment in the Tunisian context. The various sentiment proxies are bullish indicators of investor sentiment. Brown and Cliff (2004) argue that the higher bull/bear ratio, the more investor sentiment is bullish. An important value of price–earnings ratio implies that the level of investor confidence as for change in market is also important. Liquidity measured by trading volume, market turnover ratio and liquidity ratio reflects individual investor sentiment. Otherwise, it seems that investors only invest when they are optimistic and reduce market liquidity once they became pessimistic. The monthly response rate to initial public offerings (IPOs) represents a bullish sentiment indicator. Indeed, the more optimistic investors are, the higher the response rate to IPOs. Investor satisfaction also reflects investor sentiment. In other words, a high level of satisfaction translates an important level of optimism. In addition, the author also recognizes that the authors’ Tunisian sentiment index follow general trend of stock market prices and appears to be an important determinant of Tunindex returns during the period of study, from January, 2004 to December, 2016. The author suggests investor sentiment can help predict Tunindex returns, distinguishing between turbulent and tranquil periods in the financial market. The graphical illustration of monthly investor sentiment index shows that it captures extreme events such as the Tunisian revolution of January, 2011, also known as the Jasmine revolution which marked the start of the Arab Spring and the consequences of economic and political turmoil in Tunisia that have disrupted economic activity in the next few years. Like all research work, the current research paper has certain limitations. The choice of control variables allowing the author to separate sentiment component of that fundamental might be criticized. Moreover, there is no unanimous number of control variables but they are chosen according to data availability. The author also believes that one of the study’s weaknesses is that the author has not examined the impact of investor sentiment on the Tunisian stock market. For future interesting avenues of research, the author proposes, first, to study the effect of investor sentiment on financial asset returns and check, second, if sentiment factor constitutes an additional source of business risk valued by the marketplace.