Search results

This paper aims to introduce a heteroskedastic hidden truncation normal (HTN) model that allows for conditional volatilities, skewness and kurtosis, which evolve over time and are linked to economic dynamics and have economic interpretations.

The model consists of the HTN distribution introduced by Arnold et al. (1993) coupled with the NGARCH type (Engle and Ng, 1993). The HTN distribution nests two well-known distributions: the skew-normal family (Azzalini, 1985) and the normal distributions. The HTN family of distributions depends on a hidden truncation and has four parameters having economic interpretations in terms of conditional volatilities, kurtosis and correlations between the observed variable and the hidden truncated variable.

The model parameters are estimated using the maximum likelihood estimator. An empirical application to market data indicates the HTN-NGARCH model captures stylized facts manifested in financial market data, specifically volatility clustering, leverage effect, conditional skewness and kurtosis. The authors also compare the performance of the HTN-NGARCH model to the mixed normal (MN) heteroskedastic MN-NGARCH model.

The paper presents a structure dynamic, allowing us to explore the volatility spillover between the observed and the hidden truncated variable. The conditional volatilities and skewness have the ability at modeling persistence in volatilities and the leverage effects as well as conditional kurtosis of the S&P 500 index.

The purpose of this study is to unfold the existing information channel in the higher moments of currency futures for different time horizons.

The authors use a quasi-Bayesian local likelihood approach within a time-varying parameter vector autoregression (TVP-VAR) framework and a dynamic connectedness measure to study the volatility, skewness and kurtosis of most traded currency futures.

The authors’ results suggest a time-varying presence of dynamic connectedness within higher moments of currency futures. Most spillovers pertain to shorter time horizons. The authors find that in net terms, CHF, EUR and JPY are the most important contributors to the system, while the authors emphasize that the role of being a transmitter or a receiver varies for pairwise interactions and time windows.

To the best of the authors’ knowledge, this is the first study that looks upon the connectivity vis-á-vis uncertainty, asymmetry and fat tails in currency futures within a dynamic Bayesian paradigm. The authors extend the current literature by proposing new insights into asset distributions.

We propose a risk factor for idiosyncratic entropy and explore the relationship between this factor and expected stock returns.

We estimate a cross-sectional model of expected entropy that uses several common risk factors to predict idiosyncratic entropy.

We find a negative relationship between expected idiosyncratic entropy and returns. Specifically, the Carhart alpha of a low expected entropy portfolio exceeds the alpha of a high expected entropy portfolio by −2.37% per month. We also find a negative and significant price of expected idiosyncratic entropy risk using the Fama-MacBeth cross-sectional regressions. Interestingly, expected entropy helps us explain the idiosyncratic volatility puzzle that stocks with high idiosyncratic volatility earn low expected returns.

We propose a risk factor of idiosyncratic entropy and explore the relationship between this factor and expected stock returns. Interestingly, expected entropy helps us explain the idiosyncratic volatility puzzle that stocks with high idiosyncratic volatility earn low expected returns.

The study aims to test prospect theory (PT) predictions in the cryptocurrency (CC) market. It proposes a new asset pricing model that explores the potential of prospect theory value (PTV) as a significant predictor of CC returns.

The study comprehensively analyses a large sample set of 1,629 CCs, representing more than 95% of the CC market. The study uses a portfolio analysis approach, employing univariate and bivariate sorting techniques with equal-weighted and value-weighted portfolios. The study also employs ordinary least squares (OLS) regression, panel data methods and quantile regression (QR) to estimate the models.

This study demonstrates an average inverse relationship between PTV and CC returns. However, this relationship exhibits asymmetry across different quantiles, indicating that investor reactions vary based on market conditions. Moreover, PTV provides more robust predictions for smaller CCs characterized by high volatility and illiquidity. Notably, the findings highlight the dominant role of the probability weighting (PW) component in PT for predicting CC behaviors, suggesting a preference for lottery-like characteristics among CC investors.

The study is one of the early studies on CC price dynamics from the PT perspective. The study is the first to apply a QR approach to analyze the cross-section of CCs using a PT-based asset pricing model. The results shed light on CC investors' decision-making processes and risk perception, offering valuable insights to regulators, policymakers and market participants. From a practical perspective, a trading strategy centered around the PTV effect can be implemented.

Are franking credit balances priced? This paper aims to investigate the valuation of franking credit balances via a determinant analysis and value relevance analysis.

The determinant analysis examines the factors that contribute to the increasing cumulative level of franking credit balances. Value relevance studies explore whether franking credit balances are priced in the market.

The results provide strong evidence of a size effect that the level of franking credit balances increases with firm size and weak evidence of an international focus effect that the level of franking credit balances increases with international ownership. They also find an individual dividend clientele effect that the level of franking credit balances decreases with individual ownership. They find significant evidence that franking credit balances are priced in the market. One dollar of franking credit is worth 1.4 dollars in firm value. That franking balances are capitalized at more than their face value suggests that franking credits signal firms' future dividend policy. They also find that the market valuation of franking balances increases with firm size but decreases with international focus.

This study provides direct evidence that franking credit balances are capitalized into equity prices. In the determinant analysis, this paper improves Heaney's (2009) model by using the percentage of international ownership as the proxy of international focus, thus addressing the limitation of his measure. In the value relevance tests, the study uses a modified model that includes log-transformation to reduce the skewness of variables based on Tanza's (2014) value relevance model. Moreover, the study suggests that the market valuation of franking credit balances increases with firm size, which contradicts Heaney's (2009) findings.

This study aims to determine how changes in macroeconomic indicators and the housing prices index (HPI) are related. These factors can cause short-term and long-term changes in the housing market in Spain.

The study used cointegrating regression, fully modified ordinary least squares and dynamic ordinary least squares methodologies. The models are trained using quarterly time series data for these parameters from 2010 to 2022. A comprehensive examination is conducted to explore the relationship between macroeconomic issues and fluctuations in the HPI.

The results indicate statistically significant short-run effects (p < 0.05) of economic growth, inflation, Spanish stock indices, foreign trade and the interest rate on HPI. The inflation variables, Spain’s stock indices, interest rate and monetary rate, have statistically significant long-run effects (p < 0.05) on HPI. The exchange rate, unemployment and money supply have no substantial impact on HPI in Spain.

The study’s findings significantly contribute to increased information concerning the level of investing activity in the Spanish housing sector. After conducting an in-depth study of both the long-run and short-run connections with HPI, the study proved to be highly effective in formulating appropriate policies.

This study examines the influence of stock liquidity on stock price crash risk and the moderating role of institutional blockholders in Vietnam’s stock market.

Crash risk is measured by the negative coefficient of skewness of firm-specific weekly returns (NCSKEW) and the down-to-up volatility of firm-specific weekly stock returns (DUVOL). Liquidity is measured by adjusted Amihud illiquidity. The two-stage least squares method is used to address endogeneity issues.

Using firm-level data from Vietnam, we find that crash risk increases with stock liquidity. The relationship is stronger in firms owned by institutional blockholders. Moreover, intensive selling by institutional blockholders in the future will positively moderate the relationship between liquidity and crash risk.

Since stock liquidity could exacerbate crash risk through institutional blockholder trading, firm managers should avoid bad news accumulation and practice timely information disclosures. Investors should be mindful of the risk associated with liquidity and blockholder trading.

We contribute to the literature by showing that the activities of blockholders could partly explain the relationship between liquidity and crash risk. High liquidity encourages blockholders to exit upon receiving private bad news.

The authors’ conclusions are based on mathematical derivations that are supported by computer simulations and three worked examples in applications of economics and finance. Finally, the authors provide a link to a computer program so that researchers can perform the analyses easily.

Based on a parameter estimation goal, the present work is concerned with determining the minimum sample size researchers should collect so their sample medians can be trusted as good estimates of corresponding population medians. The authors derive two solutions, using a normal approximation and an exact method.

The exact method provides more accurate answers than the normal approximation method. The authors show that the minimum sample size necessary for estimating the median using the exact method is substantially smaller than that using the normal approximation method. Therefore, researchers can use the exact method to enjoy a sample size savings.

In this paper, the a priori procedure is extended for estimating the population median under the skew normal settings. The mathematical derivation and with computer simulations of the exact method by using sample median to estimate the population median is new and a link to a free and user-friendly computer program is provided so researchers can make their own calculations.

Identifying the flow regime is a prerequisite for accurately modeling two-phase flow. This paper aims to introduce a comprehensive data-driven workflow for flow regime identification.

A numerical two-phase flow model was validated against experimental data and was used to generate dynamic pressure signals for three different flow regimes. First, four distinct methods were used for feature extraction: discrete wavelet transform (DWT), empirical mode decomposition, power spectral density and the time series analysis method. Kernel Fisher discriminant analysis (KFDA) was used to simultaneously perform dimensionality reduction and machine learning (ML) classification for each set of features. Finally, the Shapley additive explanations (SHAP) method was applied to make the workflow explainable.

The results highlighted that the DWT + KFDA method exhibited the highest testing and training accuracy at 95.2% and 88.8%, respectively. Results also include a virtual flow regime map to facilitate the visualization of features in two dimension. Finally, SHAP analysis showed that minimum and maximum values extracted at the fourth and second signal decomposition levels of DWT are the best flow-distinguishing features.

This workflow can be applied to opaque pipes fitted with pressure sensors to achieve flow assurance and automatic monitoring of two-phase flow occurring in many process industries.

This paper presents a novel flow regime identification method by fusing dynamic pressure measurements with ML techniques. The authors’ novel DWT + KFDA method demonstrates superior performance for flow regime identification with explainability.

Since stock return and volatility matters to investors, this study proposes to incorporate the textual sentiment of annual reports in stock price crash risk prediction.

Specific sentences gathered from management discussions and their subsequent analyses are tokenized and transformed into numeric vectors using textual mining techniques, and then the Naïve Bayes method is applied to score the sentiment, which is used as an input variable for crash risk prediction. The results are compared between a collection of predictive models, including linear regression (LR) and machine learning techniques.

The experimental results find that those predictive models that incorporate textual sentiment significantly outperform the baseline models with only accounting and market variables included. These conclusions hold when crash risk is proxied by either the negative skewness of the return distribution or down-to-up volatility (DUVOL).

It should be noted that the authors' study focuses on examining the predictive power of textual sentiment in crash risk prediction, while other dimensions of textual features such as readability and thematic contents are not considered. More analysis is needed to explore the predictive power of textual features from various dimensions, with the most recent sample data included in future studies.

The authors' study provides implications for the information value of textual data in financial analysis and risk management. It suggests that the soft information contained within annual reports may prove informative in crash risk prediction, and the incorporation of textual sentiment provides an incremental improvement in overall predictive performance.