Search results

The purpose of this paper is to examine the ability of hedge funds and funds of hedge funds to generate absolute returns using fund level data.

The absolute return profiles are identified using properties of the empirical distributions of fund returns. The authors use both Bayesian multinomial probit and frequentist multinomial logit regressions to examine the relationship between the return profiles and fund characteristics.

Some evidence is found that only some hedge funds strategies, but not all of them, demonstrate higher tendency to produce absolute returns. Also identified are some investment provisions and fund characteristics that can influence the chance of generating absolute returns. Finally, no evidence was found for performance persistence in terms of absolute returns for hedge funds but some limited evidence for funds of funds.

This paper is the first attempt to examine the hedge fund return profiles based on the notion of absolute return in great details. Investors and managers of funds of funds can utilize the identification method in this paper to evaluate the performance of their interested hedge funds from a new angle.

Using the properties of the empirical distribution of the hedge fund returns to classify them into different absolute return profiles is the unique contribution of this paper. The application of the multinomial probit and multinomial logit models in the fund performance and fund characteristics literature is also new since the dependent variable in the authors' regressions is multinomial.

Research on strategic choices available to the firm are often modeled as a limited number of possible decision outcomes and leads to a discrete limited dependent variable. A limited dependent variable can also arise when values of a continuous dependent variable are partially or wholly unobserved. This chapter discusses the methodological issues associated with such phenomena and the appropriate statistical methods developed to allow for consistent and efficient estimation of models that involve a limited dependent variable. The chapter also provides a road map for selecting the appropriate statistical technique and it offers guidelines for consistent interpretation and reporting of the statistical results.

Peers and friends are among the most influential social forces affecting adolescent behavior. In this chapter, the authors investigate peer effects on post high school career decisions and on school choice. The authors define peers as students who are in the same classes and social clubs and measure peer effects as spatial dependence among them. Utilizing recent developments in spatial econometrics, the authors formalize a spatial multinomial choice model in which individuals are spatially dependent in their preferences. The authors estimate the model via pseudo maximum likelihood using data from the Texas Higher Education Opportunity Project. The authors do find that individuals are positively correlated in their career and college preferences and examine how such dependencies impact decisions directly and indirectly as peer effects are allowed to reverberate through the social network in which students reside.

Interest in car-sharing initiatives, as a tool for improving transport network efficiency in urban areas and on interurban links, has grown in recent years. They have often been proposed as a more cost effective alternative to other modal shift and congestion relief initiatives, such as public transport or highway improvement schemes; however, with little implementation in practice, practitioners have only limited evidence for assessing their likely impacts.

This study reports the findings of a Stated Preference (SP) study aimed at understanding the value that car drivers put on car sharing as opposed to single occupancy trips. Following an initial pilot period, 673 responses were received from a web-based survey conducted in June 2008 amongst a representative sample of car driving commuters in Scotland.

An important methodological aspect of this study was the need to account for differences in behaviour to identify those market segments with the greatest propensity to car share. To this end, we estimated a range of choice model forms and compared the ability of each to consistently identify individual behaviours. More specifically, this included a comparison of:

Standard market segmentation approaches based on multinomial logit with attribute coefficients estimated by reported characteristics (e.g. age, income, etc.);

A two-stage mixed logit approach involving the estimation of random parameters logit models followed by an examination of individual respondent's choices to arrive at estimates of their parameters, conditional on know distributions across the population (following Revelt & Train, 1999); and

A latent-class model involving the specification of C classes of respondent, each with their own coefficients, and assigning each individual a probability that they belongs to a given class based upon their observed choices, socioeconomic characteristics and their reported attitudes.

As hypothesised, there are significant variations in tastes and preferences across market segments, particularly for household car ownership, gender, age group, interest in car pooling, current journey time and sharing with a stranger (as opposed to family member/friend). Comparing the sensitivity of demand to a change from a single occupancy to a car-sharing trip, it can be seen that the latter imposes a ‘penalty’ equivalent to 29.85 IVT minutes using the mixed logit structure and 26.68 IVT minutes for the multinomial specification. Segmenting this latter value according to the number of cars owner per household results in ‘penalties’ equivalent to 46.51 and 26.42 IVT minutes for one and two plus car owning households respectively.

Purpose – This chapter gives an overview of methods for defining and analysing crash severity.

Methodology – Commonly used methods for defining crash severity are surveyed and reviewed. Factors commonly found to be associated with crash severity are discussed. Approaches for formulating and estimating models for predicting crash severity are presented and critiqued. Two examples of crash severity modelling exercises are presented and findings are discussed. Suggestions are offered for future research in crash severity modelling.

Findings – Crash severity is usually defined according to the outcomes for the persons involved. The definition of severity levels used by law enforcement or crash investigation professionals is less detailed and consistent than what is used by medical professionals. Defining crash severity by vehicle damage can be more consistent, as vehicle response to crash forces is more consistent than that of humans. Factors associated with crash severity fall into three categories – human, vehicle/equipment and environmental/road – and can apply before, during or after the crash event. Crash severity can be modelled using ordered, nominal or several different types of mixed models designed to overcome limitations of the ordered and nominal approaches. Two mixed modelling examples demonstrate better prediction accuracy than ordered or nominal modelling.

Research Implications – Linkage of crash, roadway and healthcare data sets could create a more accurate picture of crash severity. Emerging statistical analysis methods could address remaining limitations of the current best methods for crash severity modelling.

Practical Implications – Medical definitions of injury severity require observation by trained medical professionals and access to private medical records, limiting their use in routine crash data collection. Crash severity is more sensitive to human and vehicle factors than environmental or road factors. Unfortunately, human and vehicle factor data are generally not available for aggregate forecasting.

This paper offers an alternative approach to assessing contagions in price and load in the Australian interconnected power markets. This approach enabled us to identify a high-risk region and assess the direction of contagions from both buyers' and sellers' perspectives.

The author used a multinomial logit method to measure contagions. Having identified the exceedance and coexceedances, the author estimated the multinomial logit coefficients of the covariates explaining the probability of a certain number of coexceedances.

Market participants should recognize the presence of contagion risk and scrutinize price and load dynamics in the NSW and VIC regions to anticipate any simultaneous extreme changes. Regulators need to stabilize the demand and supply sides in those regions to minimize any possible contagions.

This paper presents a pioneering study investigating contagion in the Australian interconnected power markets.

The purpose of this study is to examine tax stamp evasion at Twifu Atti-Morkwa and Hemang Lower Denkyira districts in the central region of Ghana.

A cross-sectional survey design was adopted to sample 305 micro-taxpayers through the use of multi-stage sampling technique. Primary data were collected from the micro-taxpayers using structured interview. Binary and multinomial logit regression models were used to regress the tax stamp evasion on economic and non-economic factors.

The study found that the likelihood of micro taxpayers to evade tax stamp is predicted by age, application of sanctions, guilt feeling, transportation cost to tax office and rate of tax audit. Thus, the study found partial support for expected utility, planned behaviour and attributory theories in explaining tax evasion behaviour of micro-taxpayers.

There are several measures of addressing tax evasion behaviour of micro taxpayers. Evasion behaviour can be deterred by enforcement strategies such as application of sanctions and regular tax audit, establishment of more tax offices in the districts and writing normative messages on the faces of tax stamp stickers.

This study helps explains the tax evasion behaviour of micro-taxpayers of a developing economy like Ghana using a special type of tax design meant to capture such taxpayers in the tax bracket. To the best of our knowledge, the study is unique in terms of the means of measuring tax evasion and the methodologies used.

The search for flexible models has led the simple multinomial logit model to evolve into the powerful but computationally very demanding mixed multinomial logit (MMNL) model. That flexibility search lead to discrete choice hybrid choice models (HCMs) formulations that explicitly incorporate psychological factors affecting decision making in order to enhance the behavioral representation of the choice process. It expands on standard choice models by including attitudes, opinions, and perceptions as psychometric latent variables.

In this paper we describe the classical estimation technique for a simulated maximum likelihood (SML) solution of the HCM. To show its feasibility, we apply it to data of stated personal vehicle choices made by Canadian consumers when faced with technological innovations.

We then go beyond classical methods, and estimate the HCM using a hierarchical Bayesian approach that exploits HCM Gibbs sampling considering both a probit and a MMNL discrete choice kernel. We then carry out a Monte Carlo experiment to test how the HCM Gibbs sampler works in practice. To our knowledge, this is the first practical application of HCM Bayesian estimation.

We show that although HCM joint estimation requires the evaluation of complex multi-dimensional integrals, SML can be successfully implemented. The HCM framework not only proves to be capable of introducing latent variables, but also makes it possible to tackle the problem of measurement errors in variables in a very natural way. We also show that working with Bayesian methods has the potential to break down the complexity of classical estimation.