Portfolio-optimization models for small investors

Since 2010, the client base of online-trading service providers has grown significantly. Such companies enable small investors to access the stock market at advantageous rates. Because small investors buy and sell stocks in moderate amounts, they should consider fixed transaction costs, integral transaction units, and dividends when selecting their portfolio. In this paper, we consider the small investor’s problem of investing capital in stocks in a way that maximizes the expected portfolio return and guarantees that the portfolio risk does not exceed a prescribed risk level. Portfolio-optimization models known from the literature are in general designed for institutional investors and do not consider the specific constraints of small investors. We therefore extend four well-known portfolio-optimization models to make them applicable for small investors. We consider one nonlinear model that uses variance as a risk measure and three linear models that use the mean absolute deviation from the portfolio return, the maximum loss, and the conditional value-at-risk as risk measures. We extend all models to consider piecewise-constant transaction costs, integral transaction units, and dividends. In an out-of-sample experiment based on Swiss stock-market data and the cost structure of the online-trading service provider Swissquote, we apply both the basic models and the extended models; the former represent the perspective of an institutional investor, and the latter the perspective of a small investor. The basic models compute portfolios that yield on average a slightly higher return than the portfolios computed with the extended models. However, all generated portfolios yield on average a higher return than the Swiss performance index. There are considerable differences between the four risk measures with respect to the mean realized portfolio return and the standard deviation of the realized portfolio return.

Choosing a random distribution with prescribed risks

We describe several simulation algorithms that yield random probability distributions with given values of risk measures. In case of vanilla risk measures, the algorithms involve combining and transforming random cumulative distribution functions or random Lorenz curves obtained by simulating rather general random probability distributions on the unit interval. A new algorithm based on the simulation of a weighted barycentres array is suggested to generate random probability distributions with a given value of the spectral risk measure.

Portfolio-optimization models for small investors

Since 2010, the client base of online-trading service providers has grown significantly. Such companies enable small investors to access the stock market at advantageous rates. Because small investors buy and sell stocks in moderate amounts, they should consider fixed transaction costs, integral transaction units, and dividends when selecting their portfolio. In this paper, we consider the small investor’s problem of investing capital in stocks in a way that maximizes the expected portfolio return and guarantees that the portfolio risk does not exceed a prescribed risk level. Portfolio-optimization models known from the literature are in general designed for institutional investors and do not consider the specific constraints of small investors. We therefore extend four well-known portfolio-optimization models to make them applicable for small investors. We consider one nonlinear model that uses variance as a risk measure and three linear models that use the mean absolute deviation from the portfolio return, the maximum loss, and the conditional value-at-risk as risk measures. We extend all models to consider piecewise-constant transaction costs, integral transaction units, and dividends. In an out-of-sample experiment based on Swiss stock-market data and the cost structure of the online-trading service provider Swissquote, we apply both the basic models and the extended models; the former represent the perspective of an institutional investor, and the latter the perspective of a small investor. The basic models compute portfolios that yield on average a slightly higher return than the portfolios computed with the extended models. However, all generated portfolios yield on average a higher return than the Swiss performance index. There are considerable differences between the four risk measures with respect to the mean realized portfolio return and the standard deviation of the realized portfolio return.

Coherence and Elicitability

The risk of a financial position is usually summarized by a risk measure. As this risk measure has to be estimated from historical data, it is important to be able to verify and compare competing estimation procedures. In statistical decision theory, risk measures for which such verification and comparison is possible, are called elicitable. It is known that quantile-based risk measures such as value at risk are elicitable. In this paper, the existing result of the nonelicitability of expected shortfall is extended to all law-invariant spectral risk measures unless they reduce to minus the expected value. Hence, it is unclear how to perform forecast verification or comparison. However, the class of elicitable law-invariant coherent risk measures does not reduce to minus the expected value. We show that it consists of certain expectiles.

Aplicação de métodos computacionais multidisciplinares de engenharia para otimização de carteiras de investimentos.

Este trabalho apresenta uma nova metodologia para otimizar carteiras de ativos financeiros. A metodologia proposta, baseada em interpoladores universais tais quais as Redes Neurais Artificiais e a Krigagem, permite aproximar a superfície de risco e consequentemente a solução do problema de otimização associado a ela de forma generalizada e aplicável a qualquer medida de risco disponível na literatura. Além disto, a metodologia sugerida permite que sejam relaxadas hipóteses restritivas inerentes às metodologias existentes, simplificando o problema de otimização e permitindo que sejam estimados os erros na aproximação da superfície de risco. Ilustrativamente, aplica-se a metodologia proposta ao problema de composição de carteiras com a Variância (controle), o Valor-em-Risco (VaR) e o Valor-em-Risco Condicional (CVaR) como funções objetivo. Os resultados são comparados àqueles obtidos pelos modelos de Markowitz e Rockafellar, respectivamente.

CVaR minimization by the SRA algorithm

Using the risk measure CV aR in �nancial analysis has become more and more popular recently. In this paper we apply CV aR for portfolio optimization. The problem is formulated as a two-stage stochastic programming model, and the SRA algorithm, a recently developed heuristic algorithm, is applied for minimizing CV aR.

CVaR számítás SRA algoritmussal (CVaR minimization by the SRA algorithm)

A CV aR kockázati mérték egyre nagyobb jelentőségre tesz szert portfóliók kockázatának megítélésekor. A portfolió egészére a CVaR kockázati mérték minimalizálását meg lehet fogalmazni kétlépcsős sztochasztikus feladatként. Az SRA algoritmus egy mostanában kifejlesztett megoldó algoritmus sztochasztikus programozási feladatok optimalizálására. Ebben a cikkben az SRA algoritmussal oldottam meg CV aR kockázati mérték minimalizálást. ___________ The risk measure CVaR is becoming more and more popular in recent years. In this paper we use CVaR for portfolio optimization. We formulate the problem as a two-stage stochastic programming model. We apply the SRA algorithm, which is a recently developed heuristic algorithm, to minimizing CVaR.

Stress events in the Hungarian stock market

Central clearing and the role of central counterparties (CCP) has gained on importance in the financial sector, since counterparty risk of the trading is to be managed by them. The regulation has turned towards them lately, by defining several processes, how CCPs should measure and manage their risk. Stress situation is an important term of the regulation, however it is not specified clearly, how stress should be identified. This paper provides a possible definition of stress event based on the existing risk management methodology: the usage of risk measure oversteps, and investigates the potential stress periods of the last years on the Hungarian stock market. According to the results the definition needs further calibration based on the magnitude of the cross-sectional data. The paper examines furthermore whether stress is to be predicted from market liquidity. The connection of liquidity and market turmoil proved to be contrary to the expectations; liquidity shortage was rather a consequence, than a forecaster phenomenon in the tested period.

AT-RISK ALCOHOL USE IN YOUNG ADULTS - EFFECTIVENESS AND MECHANISMS OF BRIEF MOTIVATIONAL INTERVENTION AS A PRIMARY AND SECONDARY PREVENTION MEASURE

SummaryThe alcohol use of adolescents and young adults is one of the world's most important and costliest health problems. Particularly, binge drinking (i.e. drinking an important amount of alcohol in one occasion) among young people increase the risk of detrimental consequences such as blackouts, injuries, at-risk sexual behaviors, involvement in violent acts, academic failure, and suicide attempts. In countries with mandatory conscription mechanisms, such as Switzerland, the army provides a unique opportunity to reach a large portion of this high risk population. We used this sample to evaluate the prevalence of binge drinking among young men, to test the efficacy of brief motivational interventions (BMI) as a primary and secondary preventive measure, and to examine the mechanisms underlying BMI in this age group.We showed that binge drinking among young French-speaking Swiss men is less of an exception than it is the norm. Of those using alcohol, 75.5% had a binge drinking episode at least monthly, and 69.3% of all consumption reported in a one-week diary was due to binge drinking days.We used two different inclusion modes to evaluate the success of alcohol BMI. In the first randomized controlled trial, inclusion relied on a random selection of conscripts. BMI efficacy was evaluated in a sample of conscripts who visited the army recruitment centre that is potentially generalizable to the entire population. In the second randomized controlled trial, we included subjects voluntarily participating in BMI. This venue might be more realistic for young adults; it is more akin to the MI spirit, in which it is crucial for individuals to control their own decisions.Regarding BMI efficacy as a secondary prevention measure (i.e. to help decrease alcohol use among at-risk drinkers, defined here as those having a binge drinking episode at least monthly), it was effective among randomly selected at-risk drinkers, whereas it was not effective among at-risk drinkers who voluntarily showed up. Individuals who showed interest in BMI had more severe patterns of alcohol use, which may have made change more difficult and calls for treatment that is more intensive. BMI demonstrated a 20% reduction in weekly alcohol use among randomly selected participants, indicating potential interest in BMI implementation within similar community settings.Regarding BMI efficacy as a primary prevention measure (i.e. to help maintain low levels of use among low-risk drinkers), it had significant protective effects among low-risk drinkers voluntarily showing up whereas it was not effective among low-risk drinkers randomly selected. This suggests that BMI might help young individuals keep their drinking at low levels, especially when they are interested in discussing their alcohol use. Therefore, BMI has potentially promising uses in primary prevention efforts. The content of these interventions for low-risk drinkers who do not seek BMI on their own should be further evaluated.BMI mechanisms were addressed since little is known about exactly which elements of it work, or which of the counselor and subject communication behaviors are most effective in triggering behavior changes. The causal chain hypothesis developed in the motivational interviewing (MI) theory was followed, and it was found that counselor behaviors consistent with the MI approach (MICO) were significantly more likely to be followed by participant language in favor of change (change talk, CT), while behaviors inconsistent with MI (MIIN) were significantly less likely to do so. Several CT dimensions measured during BMI (particularly Ability, Desire, and Need to change) were predictive of change in alcohol use. Our findings lend strong support for the use of MICO behaviors and the avoidance of MIIN behaviors in eliciting CT, and point out that particular attention should be paid to the utterances in several sub-dimensions of CT and to the strength of expression, since these are good indicators of potential actual behavior change in future.RésuméLa consommation d'alcool chez les adolescents et les jeunes adultes est un des problèmes de santé les plus importants et les plus coûteux dans le monde. En particulier, les consommations importantes d'alcool en une occasion (binge drinking) parmi les jeunes adultes ont été liées à des conséquences telles que pertes de connaissance, accidents et blessures, comportements sexuels à risque, violences, difficultés scolaires et tentatives de suicide. Les pays qui, comme la Suisse, connaissent un processus de recrutement obligatoire pour l'armée offrent une opportunité unique d'atteindre une large portion de cette population à hauts risques. Nous avons utilisé cet échantillon pour évaluer la prévalence du binge drinking parmi les jeunes hommes, pour tester l'efficacité de l'intervention brève motivationnelle (IBM) comme mesure de prévention primaire et secondaire, et pour examiner les mécanismes sous-tendant ce type d'interventions.La première partie de cette étude montre que le binge drinking est moins une exception que la norme parmi les jeunes hommes suisses francophones. 75.5% des personnes consommant de l'alcool avaient au moins un épisode de binge drinking par mois et 69.3% du total des boissons alcoolisées reportées comme consommation de la semaine précédant le questionnaire avaient été consommées lors d'épisodes de binge drinking.Pour évaluer l'efficacité de l'IBM dans ce cadre, nous avons utilisé deux modes d'inclusion. Dans une première étude randomisée contrôlée, nous avons inclus des personnes sélectionnées au hasard parmi toutes celles se présentant au centre de recrutement, créant ainsi un groupe potentiellement représentatif de l'ensemble du collectif. Dans la deuxième étude randomisée contrôlée, nous avons inclus des sujets se présentant volontairement pour recevoir une IBM, prendre des volontaires pouvant être plus proche de la réalité et plus proche de l'esprit motivationnel dans lequel il est crucial que l'individu contrôle ses décisions.En regardant l'IBM comme mesure de prévention secondaire (c'est-à-dire aider à diminuer la consommation d'alcool chez les consommateurs à risque, définis ici comme au moins un épisode de binge drinking par mois), l'IBM était efficace lorsque les participants étaient inclus au hasard et inefficace lorsqu'ils étaient volontaires. Les jeunes hommes volontaires pour un IBM avaient un mode de consommation particulièrement sévère qui pourrait être plus difficile à changer et nécessiter un traitement plus intensif. Parmi les personnes sélectionnées au hasard, l'IBM permettait une diminution de 20% de la consommation hebdomadaire d'alcool, montrant l'intérêt potentiel d'une implémentation de ce type de mesures dans des contextes communautaires similaires.En ce qui concerne l'IBM comme mesure de prévention primaire (c'est-à-dire aider à maintenir une consommation à bas risque chez les consommateurs à bas risque), l'IBM avaient un effet protectif significatif parmi les jeunes hommes volontaires pour une IBM, mais pas d'effet chez ceux sélectionnés au hasard. Ces résultats suggèrent que l'IBM pourrait aider de jeunes personnes à maintenir un niveau de consommation à bas risque si celles-ci s'intéressent à discuter cette consommation et aurait ainsi un potentiel intéressant comme mesure de prévention primaire. Le contenu de l'IBM pour des consommateurs à bas risque non-volontaires pour une IBM devra encore être évalué.Nous avons ensuite examiné les mécanismes de l'IBM car son fonctionnement est encore peu expliqué et les comportements de l'intervenant et du sujet les plus à même de provoquer le changement ne sont pas bien définis. En suivant l'hypothèse d'une chaine causale développée dans la littérature de l'entretien motivationnel (EM), nous avons pu montrer qu'un discours en faveur du changement chez le sujet était plus probable après des comportements de l'intervenant recommandés dans l'EM et moins probable après des comportements à éviter dans l'EM ; et que plusieurs dimensions de ce discours en faveur du changement (notamment la capacité, le désir et le besoin de changer) prédisaient un changement effectif dans la consommation d'alcool. Ces résultats encouragent donc à utiliser des comportements recommandés dans l'EM pour favoriser un discours en faveur du changement. Ils montrent aussi qu'une attention particulière doit être portée à la fréquence et à la force avec laquelle sont exprimées certaines dimensions de ce discours car ceux-ci indiquent un potentiel changement effectif de comportement.Résumé vulgariséLa consommation d'alcool chez les adolescents et les jeunes adultes est un des problèmes de santé les plus importants et les plus coûteux dans le monde. En particulier, les consommations importantes d'alcool en une occasion (binge drinking) parmi les jeunes adultes augmentent fortement les risques de conséquences telles que pertes de connaissance, accidents et blessures, comportements sexuels à risque, violences, difficultés scolaires et tentatives de suicide. Les pays qui, comme la Suisse, connaissent un processus de recrutement obligatoire pour l'armée offrent une opportunité unique d'atteindre une large portion de cette population à hauts risques. Nous avons utilisé cet échantillon pour évaluer l'importance du phénomène de binge drinking, pour tester l'efficacité de l'intervention brève motivationnelle (IBM) comme mesure de prévention de la consommation à risque d'alcool, et pour examiner comment fonctionne ce type d'interventions.La première partie de cette étude montre que le binge drinking est moins une exception que la norme parmi les jeunes hommes suisses francophones. Trois quart des personnes consommant de l'alcool avaient au moins un épisode de binge drinking par mois. Presque 70% du total des boissons alcoolisées consommées durant la semaine précédant le questionnaire avaient été consommées lors d'épisodes de binge drinking.Nous avons ensuite mené deux études pour évaluer l'efficacité de l'IBM dans ce cadre. Dans une première étude, nous avons sélectionné des personnes au hasard parmi toutes celles se présentant au centre de recrutement, créant ainsi un groupe potentiellement représentatif de l'ensemble du collectif. Dans la deuxième étude, nous avons inclus toutes les personnes se présentant volontairement pour recevoir une IBM, prendre des volontaires pouvant être plus proche de la réalité et plus proche de l'approche motivationnelle dans laquelle il est crucial que l'individu contrôle ses décisions. Dans les deux études, nous testions l'efficacité de l'IBM comme mesure de prévention primaire et secondaire (voir ci-dessous).En regardant l'IBM comme mesure de prévention secondaire (c'est-à-dire aider à diminuer la consommation d'alcool chez les consommateurs à risque, définis ici comme au moins un épisode de binge drinking par mois), l'IBM était efficace lorsque les participants étaient inclus au hasard et inefficace lorsqu'ils étaient volontaires. Les jeunes hommes volontaires pour un IBM avaient un mode de consommation particulièrement sévère qui pourrait être plus difficile à changer et nécessiter un traitement plus intensif. Parmi les personnes sélectionnées au hasard, l'IBM permettait une diminution de 20% de la consommation hebdomadaire d'alcool, montrant l'intérêt potentiel de la mise en place de ce type de mesures dans des contextes communautaires similaires.En ce qui concerne l'IBM comme mesure de prévention primaire (c'est-à-dire aider à maintenir une consommation à bas risque chez les consommateurs à bas risque), l'IBM avaient un effet protectif parmi les jeunes hommes volontaires pour une IBM, mais pas d'effet chez ceux sélectionnés au hasard. Ces résultats suggèrent que l'IBM pourrait aider de jeunes personnes à maintenir un niveau de consommation à bas risque si celles-ci s'intéressent à discuter de cette consommation. Le contenu de l'IBM pour des consommateurs à bas risque non-volontaires pour une IBM devra encore être évalué.Nous avons ensuite examiné le fonctionnement de l'IBM et cherché quels comportements de l'intervenant et du jeune homme pouvaient être les plus à même d'amener à un changement dans la consommation. Nous avons pu montrer que 1) un discours en faveur du changement chez le jeune homme était plus probable après des comportements de l'intervenant recommandés dans l'approche motivationnelle et moins probable après des comportements non-recommandés ; et 2) plusieurs dimensions de ce discours en faveur du changement (notamment la capacité, le désir et le besoin de changer) prédisaient un changement effectif dans la consommation d'alcool. Ces résultats encouragent donc à utiliser des comportements recommandés dans l'EM pour favoriser un discours en faveur du changement. Ils montrent aussi qu'une attention particulière doit être portée à certaines dimensions de ce discours car celles-ci indiquent un potentiel changement effectif de comportement.

A Survey Measure of Risk Aversion

We Use Survey Data on the Well-Being of Individuals to Measure Attitude Toward Risk. Risk Neutrality Cannot Be Rejected by the Data.

Using extreme value theory to measure value-at-risk for daily electricity spot prices

The recent deregulation in electricity markets worldwide has heightened the importance of risk management in energy markets. Assessing Value-at-Risk (VaR) in electricity markets is arguably more difficult than in traditional financial markets because the distinctive features of the former result in a highly unusual distribution of returns-electricity returns are highly volatile, display seasonalities in both their mean and volatility, exhibit leverage effects and clustering in volatility, and feature extreme levels of skewness and kurtosis. With electricity applications in mind, this paper proposes a model that accommodates autoregression and weekly seasonals in both the conditional mean and conditional volatility of returns, as well as leverage effects via an EGARCH specification. In addition, extreme value theory (EVT) is adopted to explicitly model the tails of the return distribution. Compared to a number of other parametric models and simple historical simulation based approaches, the proposed EVT-based model performs well in forecasting out-of-sample VaR. In addition, statistical tests show that the proposed model provides appropriate interval coverage in both unconditional and, more importantly, conditional contexts. Overall, the results are encouraging in suggesting that the proposed EVT-based model is a useful technique in forecasting VaR in electricity markets. (c) 2005 International Institute of Forecasters. Published by Elsevier B.V. All rights reserved.

Comparison of surveys used to measure physical activity

Objective: To compare the level of agreement in results obtained from four physical activity (PA) measurement instruments that are in use in Australia and around the world. Methods: 1,280 randomly selected participants answered two sets of PA questions by telephone. 428 answered the Active Australia (AA) and National Health Surveys, 427 answered the AA and CDC Behavioural Risk Factor Surveillance System surveys (BRFSS), and 425 answered the AA survey and the short International Physical Activity Questionnaire (IPAQ). Results: Among the three pairs of survey items, the difference in mean total PA time was lowest when the AA and NHS items were asked (difference=24) (SE:17) minutes, compared with 144 (SE:21) mins for AA/BRFSS and 406 (SE:27) mins for AA/IPAQ). Correspondingly, prevalence estimates for 'sufficiently active' were similar for AA and NHS (56% and 55% respectively), but about 10% higher when BRFSS data were used, and about 26% higher when the IPAQ items were used, compared with estimates from the AA survey. Conclusions: The findings clearly demonstrate that there are large differences in reported PA times and hence in prevalence estimates of 'sufficient activity' from these four measures. Implications: It is important to consistently use the same survey for population monitoring purposes. As the AA survey has now been used three times in national surveys, its continued use for population surveys is recommended so that trend data ever a longer period of time can be established.

Adolescent reputation enhancement: Differentiating delinquent, nondelinquent, and at-risk youths

This research reports the findings of two studies conducted to measure and then investigate differences between delinquent, nondelinquent, and at-risk youths' orientations towards reputation enhancement. In the first study, concerning item selection and scale development, the factor structure and content validity of a potential Reputation Enhancement Scale were tested by examining the item responses of the scale completed by 230 high-school students. In the second study, the scale was validated by comparing the item responses of 80 delinquent, 90 at-risk, and 90 nondelinquent adolescents with the responses of the original students. The instrument was found to be reliable (alphas from .64 to .92), indicating that the factors are dependable across different samples, and the coefficients of congruence were sufficiently high to investigate meaningful group differences. Three second-order factors (Conforming Reputation, Nonconforming Reputation, Self-presentation) were derived from the 15 first-order factors. Although multivariate analyses revealed significant differences between the reputational orientations of delinquent, at-risk, and nondelinquent participants, the self-presentation second-order factor did not differentiate the three groups.

Teen Triple P: A universal approach to reducing risk factors for behavioural and emotional problems in adolescents at the transition to high school

Teen Triple P is a multilevel system of intervention that is designed to provide parents with specific strategies to promote the positive development of their teenage children as they make the transition into high school and through puberty. The program is based on a combination of education about the developmental needs of adolescents, skills training to improve communication and problem-solving, plus specific modules to deal with common problems encountered by parents and adolescents that can escalate into major conflict and violence. It is designed to increase the engagement of parents of adolescent and pre-adolescent children by providing them with easy access to evidencebased parenting advice and support. This paper presents data collected as part of a survey of over 1400 students in first year high school at 9 Brisbane schools. The survey instrument was constructed to obtain students' reports about behaviour which is known to be associated with their health and wellbeing, and also on the extent to which their parents promoted or discouraged such behaviour at home, at school, and in their social and recreational activities in the wider community. Selected data from the survey were extracted and presented to parents at a series of parenting seminars held at the schools to promote appropriate parenting of teenagers. The objectives were to provide parents with accurate data about teenagers' behaviour, and about teenagers' reports of how they perceived their parents' behaviour. Normative data on parent and teenager behaviour will be presented from the survey as well as psychometric data relating to the reliability and validity of this new measure. Implications of this strategy for increasing parent engagement in parenting programs that aim to reduce behavioural and emotional problems in adolescents will be discussed.

Physicians` attitudes and adherence to use of risk scores for primary prevention of cardiovascular disease: cross-sectional survey in three world regions

Objective: To evaluate physicians` attitudes and adherence to the use of risk scores in the primary prevention of cardiovascular disease (CVD). Design and methods: A cross-sectional survey of 2056 physicians involved in the primary prevention of CVD. Participants included cardiologists (47%), general practitioners (42%), and endocrinologists (11%) from several geographical regions: Brazil (n=968), USA (n=381), Greece (n=275), Chile (n=157), Venezuela (n=128), Portugal (n=42), The Netherlands (n=41), and Central America (Costa Rica, Panama, El Salvador and Guatemala; n=64). Results: The main outcome measure was the percentage of responses on a multiple-choice questionnaire describing a hypothetical asymptomatic patient at intermediate risk for CVD according to the Framingham Risk Score. Only 48% of respondents reported regular use of CVD risk scores to tailor preventive treatment in the case scenario. Of non-users, nearly three-quarters indicated that `It takes up too much of my time` (52%) or `I don`t believe they add value to the clinical evaluation` (21%). Only 56% of respondents indicated that they would prescribe lipid-lowering therapy for the hypothetical intermediate-risk patient. A significantly greater proportion of regular users than non-users of CVD risk scores identified the need for lipid-lowering therapy in the hypothetical patient (59 vs. 41%; p<0.0001).