Computational Economics最新文献

We examine the default risk spillover for two groups of global energy firms, including top energy firms from seven different sectors as well as energy firms scoring highest in terms of environment disclosure. We first perform a bibliometric review to uncover the trends in existing literature related to our research objectives. We then utilize novel, daily frequency data of ‘distance to default’ measure to perform two important co-movement techniques namely wavelet and TVP-VAR. The sample period is from 29 June 2009 to 30 June 2021. Our wavelet results reveal that both the groups exhibit spillover of default risk. However, there is higher interdependence of default risk in environment conscious energy firms during normal as well as crisis periods. The TVP-VAR results portray the interaction across both groups of firms and show heightened connectedness between the sampled firms for the sample period. We also identify net transmitters and receivers of shocks. The results carry important implications for investors and policymakers.

This study employs the cross-sectional absolute deviation model and Carhart pricing model to examine the existence and authenticity of various market sizes and liquidity levels within cryptocurrency markets. Additionally, we introduce a herding effect measurement index tailored for the cryptocurrency market and predict cryptocurrency prices by integrating the long short-term memory (LSTM) neural network model. Empirical results reveal the presence of both genuine and pseudo herding phenomena in cryptocurrency markets, with information acquisition asymmetry identified as a significant driver of herding behavior. Specifically, during market downturns in the overall market, only pseudo herding is observed in the upward market, whereas during periods of market prosperity, both genuine and pseudo herding are evident in the downward market. In markets of different sizes, herding is absent in cryptocurrency markets with small market value, while in large market value cryptocurrency markets, pseudo herding is not statistically significant. Genuine herding occurs in both upward and downward markets during non-downturn periods. Regarding cryptocurrency markets with different liquidity levels, herding behavior is not observed in markets with small trading volume. Conversely, in markets with large trading volume, pseudo herding is observed in both upward and downward markets during non-downturn periods, with genuine herding occurring in both markets during boom periods. Additionally, the LSTM model demonstrates superior capability in fitting the price trends of different cryptocurrencies, and considering the herding effect index significantly enhances the accuracy of cryptocurrency price prediction.

In discrete choice experiments (DCEs), differences between respondents’ preferences may be associated with observable or unobservable factors. Unobservable heterogeneity, related to latent factors associated with the choices of individuals, may be modelled using correlated (i.e. informative heterogeneity) or uncorrelated (i.e. uninformative heterogeneity) individual-specific parameters of a logit model. In this study, we simulated unobservable heterogeneity among DCE respondents and compared the results of the maximum simulated likelihood (MSL) estimation of the mixed logit model when correctly specified and mis-specified. These results show that the MSL estimates are biased and can differ greatly from the true parameters, even when correctly specified. Before estimating a mixed logit model, we highly recommend that choice modellers conduct simulation analyses to assess the potential extent of biases before relying on the MSL estimates, particularly their variances and correlations, and then ultimately determine which model specification produces the least bias.

This paper addresses the issue of foresight bias in the Longstaff and Schwartz (Rev Financ Stud 14(1):113–147, 2001) algorithm for American option pricing. Using standard regression theory, we estimate approximations of the local foresight bias caused by in-sample overfitting. Complementing the local sub-optimality bias estimator previously identified by Kan and Reesor (Appl Math Financ 19(3):195–217, 2012), recursive local bias corrections significantly reduce overall bias for the in-sample pricing approach where the estimated early-exercise policy depends on future simulated cash flows. The bias reduction scheme holds for general asset price processes and square-integrable option payoffs, and is computationally efficient across a wide range of option characteristics. Extensive numerical experiments show that the relative efficiency gain generally increases with the frequency of exercise opportunities and with the number of basis functions, producing the most favorable time-accuracy trade-offs when using a small number of sample paths.

Structural breaks are considered as permanent changes in the series mainly because of shocks, policy changes, and global crises. Hence, making estimations by ignoring the presence of structural breaks may cause the biased parameter value. In this context, it is vital to identify the presence of the structural breaks and the break dates in the series to prevent misleading results. Accordingly, the first aim of this study is to compare the performance of unit root with structural break tests allowing a single break and multiple structural breaks. For this purpose, firstly, a Monte Carlo simulation study has been conducted through using a generated homoscedastic and stationary series in different sample sizes to evaluate the performances of these tests. As a result of the simulation study, Zivot and Andrews (J Bus Econ Stat 20(1):25–44, 1992) are the best-performing tests in capturing a single break. The most powerful tests for the multiple break setting are those developed by Kapetanios (J Time Ser Anal 26(1):123–133, 2005) and Perron (Palgrave Handb Econom 1:278–352, 2006). A new Bootstrap algorithm has been proposed along with the study’s primary aim. This newly proposed Bootstrap algorithm calculates the optimal number of statistically significant structural breaks under more general assumptions. Therefore, it guarantees finding an accurate number of optimal breaks in real-world data. In the empirical part, structural breaks in the real interest rate data of the US and Australia resulting from policy changes have been examined. The results concluded that the bootstrap sequential break test is the best-performing approach due to the general assumption made to cover real-world data.

This paper introduces an innovative paradigm in cryptocurrency market analysis and prediction by exploiting the potency of the gradient boosting neural network (GBNN). This pioneering machine learning model amalgamates neural networks and gradient boosting techniques to offer a robust methodology. To enhance the GBNN's predictive capabilities, we enriched its input data with a spectrum of technical indicators. Moreover, we employed the support vector regressor for feature engineering, contributing to the exclusion of insignificant variables. We coined the term "hybrid approach" to describe our pipeline, employing it to train the GBNN model using historical cryptocurrency data. A multitude of experiments were conducted to demonstrate the superior performance of our approach in terms of model accuracy and error on previously unseen data. Notably, our proposed method outperformed state-of-the-art machine learning models, showcasing its effectiveness.

Predictive ability of time series models is easily compromised in the presence of structural breaks, common among financial and economic variables amidst market shocks and policy regime shifts. We address this problem by estimating a semiparametric mixed-frequency model, that incorporate high frequency data either in the conditional mean or the conditional variance equation. The inclusion of high frequency data through non-parametric smoothing functions complements the low frequency data to capture possible non-linear relationships triggered by the structural change. Simulation studies indicate that in the presence of structural change, the varying frequency in the mean model provides improved in-sample fit and superior out-of-sample predictive ability relative to low frequency time series models. These hold across a broad range of simulation settings, such as varying time series lengths, nature of structural break points, and temporal dependencies. We illustrate the relative advantage of the method in predicting stock returns and foreign exchange rates in the case of the Philippines.

This paper describes a new multiplicative, generalized hyperbolic distance function (GHDF) that allows the researcher to measure technical efficiency while holding a subset of inputs or outputs fixed. This is useful when dealing with “bad” or undesirable outputs, or in applications where some inputs or outputs are regarded as quasi-fixed. The paper provides computational methods for both free-disposal hull and data envelopment analysis estimators of the GHDF. In addition, statistical properties of the estimators are derived, enabling researchers to make inference and test hypotheses. An empirical illustration using data on U.S. credit unions is provided, as well as Monte Carlo evidence on the performance of the estimators. As illustrated in the empirical example, estimates of the GHDF are easier to interpret than estimates of additive, directional distance functions that until know have been the only non-parametric estimator of efficiency allowing subsets of input our outputs to be held constant.

This paper presents the steps of the building of PAC (Active available population), PEMP (Population in employment) and TCHO (Unemployment rate) time series along the period 1959–2021 in order to complete those produced by INSEE along the period 1975–2021. Most of the annual macroeconomic INSEE’s data describe the period 1959–2020. So it seems relevant to complete the labor market INSEE’s time series (1975–2020). Our work was based on INSEE’s data which had various degrees of revision. In a first step, we used some rare overseas department data (1954 to 1974) and some data of France metropolitan (1987 and 1994) that we combined with those published in 2020. In a second step, we updated them thanks an other econometric adjustement with the last INSEE’s data published in 2022. During the discussion, we recalled the dilemma that INSEE systematically encounters, namely the dilemma Data quality/quick delivery. Finally, we proposed some assessement’s criteria of our results, based on econometric adjustement and a “confidential interval” that we built.

This paper presents an alternative and straightforward two-step estimation method for the Nelson–Siegel yield curve model. The goal is to generate smoothed time series for the time-varying decay parameter and establish stable yield curve factors. To rectify excessive parameter estimates such as jumps or spikes, the decay parameter is adjusted towards its long-run mean using a closed-form expression. Empirical studies conducted with U.S. Treasury data reveal that this method generates stable and easily interpretable outcomes while the confounding effect, which is characterized by large magnitudes with opposite signs among parameters, is effectively mitigated. In out-of-sample forecasting exercises, the proposed model demonstrates comparable or modest performance compared to other competing models, including the random walk model. In particular, the shifting endpoints technique enhances the overall forecasting ability. Finally, the proposed model demonstrates an effective smoothing effect robustly even when applied to other countries.