Using Daily High/Low Time to Test for Intraday Random Walk in Two Index Futures Markets

This paper investigates the time of the daily high/low price in the Hang Seng and S&P 500 index futures and uses it to test for deviation from the predictive behavior of an intraday random walk model. Theoretical distributions of the daily high/low time under the random walk model are derived assuming either uniform or time-varying intraday trading speed. We show that under a random walk model, daily high/low time is more likely to occur near market open/close than in the middle of the trading day. Empirical distributions of the daily high/low time are compared with its theoretical distributions to test for the random walk model. It is found that for the intraday movement of the S&P 500 futures, the random walk hypothesis cannot be rejected. However, it is discovered that in the Hong Kong market, daily high/low time tends to appear significantly more often than is predicted by the random walk model in the first 15-minute time interval when the market opens in the morning or in the afternoon. The results remain valid even after we have taken the time-varying trading speed into account. By comparing the price behavior across markets, we can better understand the microstructure of the futures market.     

A statistical model of speculative bubbles,with applications to the stock markets of the United States,Japan, and China

It is common knowledge that the more prices deviate from fundamentals, the more likely it is for prices to reverse. Taking this into account, we propose a simple statistical model to identify speculative bubbles in financial markets. Through the estimates of the time varying parameters, including transition probabilities, we can identify when and how newly born bubbles grow and burst over time. The model can be estimated by recursive computations, which require a huge storage capacity for standard computers. For this reason, we introduce an approximation in the computation, maintaining the recursive nature of our estimation technique. We then apply this model to the stock markets of the United States, Japan, and China, estimate its parameters and the probabilities of a bubble crash, and obtain several interesting results: the time series data of the stock price bubble show an inherently non-stationary development and the probability of a bubble crash indeed increases as the stock price becomes too high or too low.     

The social organization of time

If all social life has been structured around a single model of employment founded on standard working hours, the reduction in working time, and in particular the diversification of working hours, is likely to effect radical transformation from both the economic and social points of view. This diversification will continue, it is argued, because of the new economic imperatives as much as sociocultural developments. It is forecasted that the old standard model is being replaced by much more flexible management of working hours and, hence, free time. What is not so clear is whether this flexibility in working conditions, which will bring with it a revolution at the individual, company and societal levels, will be equally benign for all.     

Estimating Systematic Risk Using Time Varying Distributions

This article proposes a dynamic vector GARCH model for the estimation of time-varying betas. The model allows the conditional variances and the conditional covariance between individual portfolio returns and market portfolio returns to respond asymmetrically to past innovations depending on their sign. Covariances tend to be higher during market declines. There is substantial time variation in betas but the evidence on beta asymmetry is mixed. Specifically, in 50% of the cases betas are higher during market declines and for the remaining 50% the opposite is true. A time series analysis of estimated time varying betas reveals that they follow stationary mean-reverting processes. The average degree of persistence is approximately four days. It is also found that the static market model overstates non-market or, unsystematic risk by more than 10%. On the basis of an array of diagnostics it is confirmed that the vector GARCH model provides a richer framework for the analysis of the dynamics of systematic risk.     

Exploiting the monthly data flow in structural forecasting

A quarterly stochastic general equilibrium (DSGE) model is combined with a now-casting model designed to read timely monthly information as it becomes available. This implies (1) mapping the structural quarterly DSGE with a monthly version that maintains the same economic restrictions; (2) augmenting the model with a richer data set and (3) updating the estimates of the DSGE׳s structural shocks in real time following the publication calendar of the data. Our empirical results show that our methodology enhances the predictive accuracy in now-casting. An analysis of the Great Recession also shows that our framework would have helped tracing the DSGE׳s structural shocks in real time, obtaining, for example, a more timely account of the 2008 contraction.     

Predicting bankruptcy using the discrete-time semiparametric hazard model

The usual bankruptcy prediction models are based on single-period data from firms. These models ignore the fact that the characteristics of firms change through time, and thus they may suffer from a loss of predictive power. In recent years, a discrete-time parametric hazard model has been proposed for bankruptcy prediction using panel data from firms. This model has been demonstrated by many examples to be more powerful than the traditional models. In this paper, we propose an extension of this approach allowing for a more flexible choice of hazard function. The new method does not require the assumption of a parametric model for the hazard function. In addition, it also provides a tool for checking the adequacy of the parametric model, if necessary. We use real panel datasets to illustrate the proposed method. The empirical results confirm that the new model compares favorably with the well-known discrete-time parametric hazard model.     

Machine learning loss given default for corporate debt

We apply multiple machine learning (ML) methods to model loss given default (LGD) for corporate debt using a common dataset that is cross-sectional but collected over different time periods and shows much variation over time. We investigate the efficacy of three cross-validation (CV) schemes for hyper-parameter tuning and bootstrap aggregation (Bagging) in preventing out-of-time model performance deterioration. The three CV methods are shuffled K-fold, unshuffled K-fold and sequential blocked, which completely destroys, keeps some and completely retains the chronological order in the data, respectively. We find that it is important to keep the chronological order in the data when creating the training and testing samples, and the more the chronological order that can be retained, the more stable the out-of-time ML LGD model performance. By contrast, although bagging improves out-of-time fit in some cases, its effectiveness is rather marginal relative to that from the unshuffled K-fold and sequential blocked CV methods. Substantial uncertainty in relative out-of-time performance remains, however, thus ongoing model performance monitoring and benchmarking are still essential for sound model risk management for corporate LGD and other ML models.     

Factors influencing the performance of activity based costing teams: a field study of ABC model development time in the automobile industry

This paper examines how the group dynamics of activity based costing (ABC) development teams and the level of organizational resources devoted to model development affect model complexity and development time. A theoretical framework is developed based on the organizational literature on teams. The framework is tested using objective data from 18 ABC projects in two automobile manufacturing firms and survey data from ABC team members. Results show that ABC team cohesion is the key determinant of the time it takes to develop the first ABC model. Further, ABC models become more complex in the presence of an external consultant and as the level of competition increases.     

The Effect of Uncertainty on Optimal Control Models in the Neighbourhood of a Steady State

For both discrete and continuous time this paper derives the Taylor approximation to the effect of uncertainty (in the simple sense of risk, not Knightian uncertainty) on expected utility and optimal behaviour in stochastic control models when the uncertainty is small enough that one can focus on only the first term that involves uncertainty. There is a close and illuminating relationship between the discrete-time and continuous-time results. The analysis makes it possible to spell out a tight connection between the behaviour of a dynamic stochastic general equilibrium model and the corresponding perfect foresight model. However, the quantitative analytics of the stochastic model local to a certainty model calls for a more thorough investigation of the nearby certainty model than is typically undertaken.     

Why does book-to-market value of equity forecast cross-section stock returns?

In this paper, we derive a model of book-to-market value of equity based on the present value model and estimate it using panel data on individual stocks. We explicitly include in the model all the determinants of book-to-market except the firm-specific discount rate, which we capture using fixed individual effects in the panel data model. The model is particularly successful, explaining nearly 90% of the time series and cross-section variation in the ratio of book-to-market value of equity. Moreover, the estimated firm-specific fixed effects are more successful than the most recent book-to-market value of equity in forecasting subsequent returns. This is consistent with an efficient market in which book-to-market is a proxy for risk.     

银行信用评估模型效果的量化比较

信用评估模型能有效提高信用评估过程的科学性与结果的准确性.本文围绕主流信用评估模型在性能方面的差异化特征,基于德国信贷数据集、我国个人经营贷数据集与小微企业贷数据集,从六个模型性能评价维度对十二个代表性信用评估模型的拟合能力与泛化能力进行了深入研究.研究发现:(1)逻辑回归模型的总体性能最为优异,其次为判别分析、反向传播神经网络模型,其中逻辑回归模型与反向传播神经网络模型更适用于我国信贷场景;(2)基于无监督学习理论的自组织特征映射神经网络和k均值聚类模型,以及基于惰性学习理论的k最近邻模型的泛化能力较弱,表明各类有监督式主动学习模型更适用于解决信用评估问题;(3)模型理论与结构的复杂性并不必然能够使其在特定应用场景下获得较优的性能评价,结构简单、可解释性更强的模型往往稳健性更好.     

Capital budgeting and delegation

As part of our ongoing research into capital budgeting processes as responses to decentralized information and incentive problems, we focus in this paper on when a level of a managerial hierarchy will delegate the allocation of capital across projects and time to the level below it. In our model, delegation is a way to save on costly investigation of proposed projects. Therefore, it is more extensive the larger are the costs of such investigations. This delegation takes advantage of the fact that the lower-level manager's preferences are assumed to be similar (though not identical) to those of the higher level.     

The effect of board‐manager agency conflicts on non‐profit organisations’ earnings and cost allocation manipulations

Taking into account agency problems between board and management within non‐profit organisations, for the first time a comprehensive formal model of earnings manipulations is developed. Both organisational earnings as well as disaggregated financial performance indicators are looked at, the last ones being affected by possible indirect cost allocation manipulations. The model takes into consideration the impact of disclosed earnings and performance indicators on externally raised funds, and assumes risk‐neutral managers. In the last section, it is generalised by introducing risk‐averse managers.

The conditions for optimal manipulation levels (from a managerial point of view) are derived. Depending on the (dis) utility parameters involved, different solutions emerge. As to the agency problems, it is shown that, at least for all interior solutions, a single mechanism is at work in all the situations analysed: more agency problems lead to more manipulations, both at the organisational level and the disaggregated level.     

Capital budgeting and delegation

As part of our ongoing research into capital budgeting processes as responses to decentralized information and incentive problems, we focus in this paper on when a level of a managerial hierarchy will delegate the allocation of capital across projects and time to the level below it. In our model, delegation is a way to save on costly investigation of proposed projects. Therefore, it is more extensive the larger are the costs of such investigations. This delegation takes advantage of the fact that the lower-level manager's preferences are assumed to be similar (though not identical) to those of the higher level.     

Twenty‐five years of the Taffler z‐score model: Does it really have predictive ability?

Although copious statistical failure prediction models are described in the literature, appropriate tests of whether such methodologies really work in practice are lacking. Validation exercises typically use small samples of non‐failed firms and are not true tests of ex ante predictive ability, the key issue of relevance to model users. This paper provides the operating characteristics of the well‐known Taffler (1983) UK‐based z‐score model for the first time and evaluates its performance over the 25‐year period since it was originally developed. The model is shown to have clear predictive ability over this extended time period and dominates more naïve prediction approaches. This study also illustrates the economic value to a bank of using such methodologies for default risk assessment purposes. Prima facie, such results also demonstrate the predictive ability of the published accounting numbers and associated financial ratios used in the z‐score model calculation.     

THE PRICING OF OPTIONS WITH STOCHASTIC DIVIDEND YIELD

A formula is derived in discrete time for pricing options when the underlying stock has a stochastic dividend yield. The result implies that regarding the dividend yield as certain when it is not results in misestimation of the variance of the underlying stock. Comparative statics indicate that this adjustment could diminish a bias of the Black-Scholes model. This model systematically underprices deep-out-of-the-money options. A numerical example demonstrates that this stochastic adjustment may be more important for longer-lived options and warrants.     

Improved approximations for the aggregate claims distribution of a life insurance portfolio

Abstract

In an earlier paper the author derived a recursion formula which permits the exact computation of the aggregrate claims distribution in the individual life model. This exact procedure requires of course more computing time than approximative methods such as Kornya's algorithm, which seemed to be the best compromise between accuracy and computational effort. In the present paper it is shown that, to save time, the exact formula can be used in an approximative way and that the corresponding error bound is smaller than the one of the Kornya-type approximations.     

Partial adjustment toward optimal cash holding levels

Recognizing that industry and capital market conditions may impede a firm's desire to achieve its targeted cash holding levels, we estimate a dynamic model that allows firms to adjust their cash holding levels over time and find evidence consistent with a trade-off type behavior in cash holding levels. We estimate a partial adjustment model and find that firms rapidly correct any deviation from their targeted cash levels. A typical firm in our sample closes this gap within two years. Inconsistent with the agency view of excess cash holdings, we find that cash holding levels for firms with excess cash persists over time compared to those that have a deficit. We also find that smaller firms typically hold excess cash and are quicker to correct deviations than large firms consistent with the view that it is more costly for financially constrained firms to operate at sub-optimal levels of liquid assets.     

金融开放背景下利率、汇率的产出效应与价格效应研究——基于SVAR模型的实证分析

随着我国利率市场化改革和汇率体制改革的深入,金融市场的开放程度也越来越高。在金融市场开放的背景下,利率、汇率水平的变化对经济产出和价格有着复杂的影响。通过运用SVAR模型对我国2006年1月至2011年4月的数据进行实证分析,结果表明,单纯依靠提升利率不仅无法降低通货膨胀水平,反而会导致通货膨胀率更快地增长;人民币升值虽然有助于降低通胀,但会使我国的经济在很长时间内处于衰退状态。     

金融开放背景下利率、汇率的产出效应与价格效应研究——基于SVAR模型的实证分析

随着我国利率市场化改革和汇率体制改革的深入,金融市场的开放程度也越来越高。在金融市场开放的背景下,利率、汇率水平的变化对经济产出和价格有着复杂的影响。运用SVAR模型对我国2006年1月至2011年4月的数据进行实证分析,结果表明,单纯依靠提升利率不仅无法降低通货膨胀水平,反而会导致通货膨胀率更快增长;人民币升值虽然有助于降低通胀,但可能在很长时间内影响经济增长。