Separating a mixture of two normals with proportional covariances

We propose a simple affine equivariant clustering method, based on the idea of best linear classification, for samples from a mixture of two multivariate normal distributions with different mean vectors but proportional covariance matrices. To ameliorate the curse of dimensionality, a non-parametric approach to find candidates for a best linear discriminant function is presented. By using simulation studies and a real example, we show that for large samples in high dimensions, the proposed method can be a useful supplement to general-purpose multivariate outlier detection methods.     

Risk,jumps, and diversification

We test for price discontinuities, or jumps, in a panel of high-frequency intraday stock returns and an equiweighted index constructed from the same stocks. Using a new test for common jumps that explicitly utilizes the cross-covariance structure in the returns to identify non-diversifiable jumps, we find strong evidence for many modest-sized, yet highly significant, cojumps that simply pass through standard jump detection statistics when applied on a stock-by-stock basis. Our results are further corroborated by a striking within-day pattern in the significant cojumps, with a sharp peak at the time of regularly scheduled macroeconomic news announcements.     

Jump tails,extreme dependencies,and the distribution of stock returns

We provide a new framework for estimating the systematic and idiosyncratic jump tail risks in financial asset prices. Our estimates are based on in-fill asymptotics for directly identifying the jumps, together with Extreme Value Theory (EVT) approximations and methods-of-moments for assessing the tail decay parameters and tail dependencies. On implementing the procedures with a panel of intraday prices for a large cross-section of individual stocks and the S&P 500 market portfolio, we find that the distributions of the systematic and idiosyncratic jumps are both generally heavy-tailed and close to symmetric, and show how the jump tail dependencies deduced from the high-frequency data together with the day-to-day variation in the diffusive volatility account for the “extreme” joint dependencies observed at the daily level.     

Option values,stipends and the returns to educational investment

In this paper we use a dynamic model of the returns to educational investment to analyze the flow of students moving through the various stages of an educational system. Dropout and graduation rate are linked to the profitability of an educational stage and thus may be influenced by an appropriate choice of stipend level. To determine the effects of changes in stipends on the output of the educational system we hypothesize a probability distribution of abilities in the population. The parameters of this distribution permit the estimation of the effects of stipends on the graduation rate of each educational stage.     

Corporate takeovers,stockholder returns and executive rewards

Various motives for making corporate acquisitions have been forwarded in the managerial economics literature. Two that have received a lot of attention are the maximization of stockholder wealth and the maximization of senior management's utility. These two alternative views can lead to different acquisition decisions. The paper examines the returns to senior management and the returns to stockholders following corporate takeovers in the United Kingdom. The evidence suggests that if shareholders profit from takeovers then so do the senior' management. Of more interest, however, is the finding that if acquisitions result in a reduction in stock market value for the acquiring firm, their senior management appear to gain. In particular, senior management remuneration increases substantially after an acquisition. This evidence is consistent with the maximization of senior management's utility being an important motive in many corporate-acquisition decisions.     

Market index returns,macroeconomic variables,and tax-loss selling

This study provides the most direct macro-level test to date of the tax-loss selling hypothesis as an explanation of the January effect. By examining relationships between macroeconomic variables that should be related to tax-loss selling and market index measures of the January effect, this study provides an approach that addresses the market microstructure problems that are inherent in much of the prior research regarding tax-loss selling. This study also addresses some of the methodological and variable specification concerns in prior macro-level testing, resulting in stronger support for taxloss selling. The authors wish to acknowledge the editor and anonymous referees for helpful comments and suggestions.     

Autocorrelation,return horizons,and momentum in stock returns

In this study we examine Lewellen’s (Rev Financ Stud 15:533–563 2002) claim that momentum in stock returns is not due to positive autocorrelation as behavioral models suggest. Using portfolio-specific data, we find the autocovariance component of the momentum profit to be negative, suggesting no return continuations. However, we also find that the autocorrelations calculated from short-term (e.g., monthly) returns are quite different from long-horizon (e.g., annual) autocorrelations. While the first-order autocorrelations of 6– and 12-month returns tend to be negative, the autocorrelations across twelve lags in monthly returns of the industry, size, and B/M portfolios are in general positive. Our results show that these portfolios exhibit return continuations when returns are measured on a monthly basis. Therefore, our finding appears to be consistent with the behavioral models, which suggest positive autocorrelation in stock returns.     

Default-risky bond prices with jumps,liquidity risk and incomplete information

This paper provides a default-risky bond valuation model, which assumes that the issuer’s credit quality, modelled by the intensity of default, is driven by a continuous-time Markov chain. The model accounts for default and liquidity risk as well as incomplete information. A full-information semimartingale representation of a liquid defaultable bond price, which separates three different types of risks—default, interest-rate and credit-quality, is obtained. The illiquidity is modelled as exogenously specified stochastic reduction in the price of the bond, which adds more risks for the investors. A model of a market with partially informed investors, belonging to specific investor classes and having access to discrete information sets about credit quality, was specified. Valuations of defaultable bonds in this market were provided as well as price impacts of the new information releases.      

Hedge funds,fund attributes and risk adjusted returns

We use proprietary data to examine factors that lead hedge fund managers to offer hurdle rates and investigate relative hedge fund performance based on risk-adjusted returns. Using data from 3,571 hedge funds over a 15 year period, we find that funds that do not offer a hurdle rate outperform those that do. Funds offering a high watermark charge substantially higher performance fees. Further, emerging market, fixed income, and funds of funds are significantly more likely to offer a hurdle rate than other types of funds. Performance fees have a positive impact on the likelihood of offering a hurdle rate. Fund leverage and management fees are negatively associated with hurdle rates. The cross-sectional regressions show that funds, which offer a hurdle rate, underperform those that do not. Funds that charge a high performance fee appear to outperform those that charge a relatively low fee. The results are consistent with the view that those managers who wish to improve risk-adjusted returns should not focus on hurdle rates.     

Abnormal returns, risk, and options in large data sets

Large data sets in finance with millions of observations have become widely available. Such data sets enable the construction of reliable semi-parametric estimates of the risk associated with extreme price movements. Our approach is based on semi-parametric statistical extreme value analysis, and compares favorably with the conventional finance normal distribution based approach. It is shown that the efficiency of the estimator of the extreme returns may benefit from high frequency data. Empirical tail shapes are calculated for the German Mark—US Dollar foreign exchange rate, and we use the semi-parametric tail estimates in combination with the empirical distribution function to evaluate the returns on exotic options.     

On the estimation of returns to scale, technical progress and monopolistic markups

A number of theoretical results on estimating returns to scale, technical progress and monopolistic markups are derived when there are multiple outputs and inputs. The choice of value added versus gross output and problems that arise in aggregation across sectors of an economy are also considered. Using US data on manufacturing, evidence is found of increasing returns to scale across all levels of aggregation. Technical progress is typically found to be insignificant implying that economic growth has been driven by increasing returns to scale rather than technical progress. Such findings have important implications for the macroeconomic modeling of economic fluctuations.     

Demographics and the long-horizon returns of dividend-yield strategies

This paper investigates the relationship between demographic changes and the long-run returns of dividend-yield investment strategies. We hypothesise that in a world where components of wealth are mentally treated as being non-fungible, the preference for high dividend-paying stocks by older investors means that the excess returns of high dividend-yielding stocks, relative to other stocks, should be positively related to demographic clientele variation. In particular, we find that, consistent with the behavioural life-cycle hypothesis, long-run returns of dividend-yield investment strategies are positively driven by changes in the proportion of the older population. Our results are robust when controlled for the Fama–French factors, inflation rate, consumption growth rate, interest rates, tax clienteles, time trend and alternative definitions of both dividend-yield strategies and demographic variation.     

A simple,robust and powerful test of the trend hypothesis

In this paper we develop a simple test procedure for a linear trend which does not require knowledge of the form of serial correlation in the data, is robust to strong serial correlation, and has a standard normal limiting null distribution under either I(0)$I(0)$ or I(1)$I(1)$ shocks. In contrast to other available robust linear trend tests, our proposed test achieves the Gaussian asymptotic local power envelope in both the I(0)$I(0)$ and I(1)$I(1)$ cases. For near-I(1)$I(1)$ errors our proposed procedure is conservative and a modification for this situation is suggested. An estimator of the trend parameter, together with an associated confidence interval, which is asymptotically efficient, again regardless of whether the shocks are I(0)$I(0)$ or I(1)$I(1)$, is also provided.     

Market efficiency, discount-rate changes, and stock returns: A long-term perspective

This paper examines the market efficiency issue by analyzing stock returns surrounding Fed announcements of discount-rate changes. Based on an analysis ofex post returns over a 58-year period, the results provide evidence of long-term market efficiency. Consistent with recent literature, the findings also reveal some predictability in return patterns where an active trading strategy based on directional reversals in the pattern of discount rate changes outperforms a passive buy-and-hold approach. The results indicate that the proposed active trading produces substantially higher risk-adjusted returns than the buy-and-hold strategy.     

Asymmetric loss functions and the rationality of expected stock returns

We combine the innovative approaches of Elliott, Komunjer, and Timmermann (2005) and Patton and Timmermann (2007) with a block bootstrap to analyze whether asymmetric loss functions can rationalize the S&P 500 return expectations of individual forecasters from the Livingston Surveys. Although the rationality of these forecasts has often been rejected, earlier studies have relied on the assumption that positive and negative forecast errors of identical magnitudes are equally important to forecasters. Allowing for homogenous asymmetric loss, our evidence still strongly rejects forecast rationality. However, if we allow for variation in asymmetric loss functions across forecasters, not only do we find significant differences in preferences, but also we can often no longer reject forecast rationality. Our conclusions raise serious doubts about the homogeneous expectations assumption often made in asset pricing, portfolio construction and corporate finance models.     

Decomposing TFP growth in the presence of cost inefficiency,nonconstant returns to scale,and technological progress

A thorough understanding of changes in productivity measures is important to economists and policymakers, because productivity growth is a major source of economic growth. This article explores the relationship between changes in total factor productivity (TFP) growth, defined using an index number approach, and changes in returns to scale, cost efficiency, and technology. Several decompositions are developed, using alternatively production and cost frontiers. The last decomposition developed also allows for multiple outputs.The refereeing process of this paper was handled through W.H. Greene.     

Acquiring firms' stock returns: Methods of payment,change in leverage,and management ownership

This study examines the effects of the method of payment, change in leverage, and management equity ownership on the acquiring firm's stock returns around the initial announcement date of the merger. Results indicate that stockholders of mergers financed with stocks suffer significant losses. These losses are larger when management ownership is low and smaller in mergers that resulted in acquiring firm leverage decreases. Stockholders of acquiring firms involved in cash mergers gain significant abnormal returns, provided that acquiring firms increase their leverage and that managerial ownership is high. When management equity ownership is low, leverage has no effect on stock returns. When management ownership is high, mergers which resulted in acquiring firm leverage increases have significant positive effects, and those which resulted in acquiring firm leverage decreases have negative but insignificant effects.     

Economic fluctuations,market power,and returns to scale: Evidence from firm-level data

Recent research on aggregate fluctuations, coupled with ongoing work in industrial organization, has renewed interest in the existence, magnitude, and cyclical pattern of market power and the extent of increasing returns to scale. By exploiting restrictions from dynamic theory and information from financial markets, we present a framework for generating quantitative evidence on market power and returns to scale. Tailoring the econometric model to firm-level panel data, we calculate the percentage differential between price and marginal cost (the Lerner index) in terms of the parameters from the econometric system. Results for firms in eleven industries indicate that there is a great deal of heterogeneity in the extent of market power. Industries with significantly positive Lerner indices tend to have substantial increasing returns in the production technology. We find that there is only a modest relation between our estimated Lerner indices and traditional measures of market power and that, when market power varies temporally, it is usually procyclical. Thus, variations in the markup of price over marginal cost may help dampen aggregate economic fluctuations.     

Spatial discounting and the gravity hypothesis

One of the central hypotheses in the study of spatial interaction behavior is the diminishing effect of distance on interaction. In this paper a parallel is drawn between two forms of this hypothesis: an external gravity interaction form which focuses directly on the empirically observable diminishing effect of distance on interaction, and an internal spatial discounting form which focuses rather on the diminishing effect of distance on spatial actors' preferences among interaction opportunities. The main result of the paper is to establish a connection between these two forms of the distance hypothesis. In particular, necessary and sufficient conditions on spatial actors' interaction preferences are established under which these two forms are equivalent, i.e., under which spatial discounting behavior is indistinguishable from gravity interaction behavior.