Large portfolio losses

This paper provide a large-deviations approximation of the tail distribution of total financial losses on a portfolio consisting of many positions. Applications include the total default losses on a bank portfolio, or the total claims against an insurer. The results may be useful in allocating exposure limits, and in allocating risk capital across different lines of business. Assuming that, for a given total loss, the distress caused by the loss is larger if the loss occurs within a smaller time period, we provide a large-deviations estimate of the likelihood that there will exist a sub-period of the future planning period during which a total loss of the critical severity occurs. Under conditions, this calculation is reduced to the calculation of the likelihood of the same sized loss over an initial time interval whose length is a property of the portfolio and the critical loss level.Received: March 2003Mathematics Subject Classification: 60F10, 91B28, 91B28JEL Classification: G21, G22, G33Amir Dembo is with the Department of Statistics, Stanford University. His research was partially supported by NSF grant #DMS-0072331. Jean-Dominique Deuschel is with the Department of Mathematics, Technische Universität, Berlin. His research was partially supported by DFG grant #663/2-3 and DFG FZT 86. Darrell Duffie is with the Graduate School of Business, Stanford University. We are extremely grateful for research assistance by Nicolae Gârleanu and Gustavo Manso, for conversations with Michael Gordy, and for comments from Michael Stutzer, Peter Carr, David Heath, and David Siegmund.     

Seasonality patterns in dry bulk shipping spot and time charter freight rates

This paper investigates the nature of seasonality (deterministic and/or stochastic) in dry bulk freight rates, and measures and compares it across freight rates of different vessel sizes (Capesize, Panamax and Handysize), contract duration (spot, 1-year and 3-year time charters) and market conditions (peaks and troughs). Although, there is no evidence of stochastic seasonality, deterministic seasonality in freight rates is found to be varying from −18.2% to 15.3% in individual months within a year. Spot rates for larger vessels exhibit higher seasonal fluctuations compared to smaller vessels, although differences in seasonal fluctuations between sectors are eliminated as the contract duration increases. Also, for each vessel size, the seasonality declines as the contract duration rises. Asymmetries in seasonal fluctuations in freight rates over different market conditions are attributed to the high and low elasticities of supply expected under the respective market conditions. The results have implications for tactical shipping operations such as timing of dry-docking, chartering strategies and switching between freight markets.     

Asset market games of survival: a synthesis of evolutionary and dynamic games

The paper examines a game-theoretic model of a financial market in which asset prices are determined endogenously in terms of a short-run equilibrium. Investors use general, adaptive strategies (portfolio rules) depending on the exogenous states of the world and the observed history of the game. The main goal is to identify portfolio rules, allowing an investor to “survive,” i.e., to possess a positive, bounded away from zero, share of market wealth over an infinite time horizon. The model under consideration combines a strategic framework characteristic for stochastic dynamic games with an evolutionary solution concept (survival strategies), thereby linking two fundamental paradigms of game theory.     

Risk, uncertainty, and learning in adoption of a crop innovation

Risk and uncertainty have often been suggested as causes of poor adoption of rural innovations, but empirical evidence has been scarce. This study focuses on a new crop‐type, chickpeas, in Western Australia to gather such evidence. The empirical models developed are based on a theoretical framework that conceptualizes adoption as a dynamic decision process involving information acquisition and learning‐by‐doing by growers who vary in their managerial abilities, risk preferences, and their perceptions of the profitability and riskiness of the innovation. Learning encompasses improvements in skill as well as reductions in uncertainty. An annual face‐to‐face survey of over 100 farmers was conducted over 3 years, eliciting the farmers' risk attitudes and their subjective distributions of yields and prices. Two limited dependent variable models, Tobit and Probit, are used to estimate the empirical model. There is a high degree of goodness‐of‐fit for both models. The study provides strong empirical support for the primarily economic character of the adoption decision, and highlight the importance of economic risk in the process. The two risk‐related factors with greatest impact on the adoption decision were risk aversion and relative riskiness of the innovation. Risk aversion tended to reduce adoption, and to do so to a greater extent as relative riskiness and scale increased. Results also reveal the key role that trialing of the innovation plays in adoption.     

Prioritizing Brand Equity Methods From Customers’ Perspective for the Food Industry

Brand equity assessment is an important measurement of strategic value for internal use as well as for external stakeholders. Although there are a number of methods available for brand evaluation, it is still uncertain which approach is best. Yet almost no research exists that has prioritized the existing brand equity methods from the perspective of different stakeholders through a survey. In this article a model is developed for prioritizing brand equity methodologies from the viewpoint of customers as a stakeholder of brand equity. The developed model can help businesses to deploy a brand equity methodology that best considers the criteria of their customers as one of their key stakeholders. The criteria of this process are the expectations of customers from a brand. The priority of these criteria sets via a structured questionnaire filled by customers. Then the analytical hierarchy process (AHP) incorporates to prioritize the methodologies versus these criteria. This study set out to prioritize the brand equity pool to help practitioners and academics in assessing the alternative techniques and selecting the most relevant one that measures the most important criteria of brand in the eyes of customers.     

Distribution of residual autocorrelations for multiplicative seasonal ARMA models with uncorrelated but nonindependent error terms

In this paper, we consider portmanteau tests for testing the adequacy of multiplicative seasonal autoregressive moving‐average models under the assumption that the errors are uncorrelated but not necessarily independent. We relax the standard independence assumption on the error terms in order to extend the range of applications of the seasonal autoregressive moving‐average models. We study the asymptotic distributions of residual and normalized residual empirical autocovariances and autocorrelations under weak assumptions on noise. We establish the asymptotic behavior of the proposed statistics. A set of Monte Carlo experiments and an application to monthly mean total sunspot number are presented.     

Economic evaluation of nivolumab for the treatment of second-line advanced squamous NSCLC in Canada: a comparison of modeling approaches to estimate and extrapolate survival outcomes

Background Lung cancer is the most common type of cancer in the world and is associated with significant mortality. Nivolumab demonstrated statistically significant improvements in progression-free survival (PFS) and overall survival (OS) for patients with advanced squamous non-small cell lung cancer (NSCLC) who were previously treated. The cost-effectiveness of nivolumab has not been assessed in Canada. A contentious component of projecting long-term cost and outcomes in cancer relates to the modeling approach adopted, with the two most common approaches being partitioned survival (PS) and Markov models. The objectives of this analysis were to estimate the cost-utility of nivolumab and to compare the results using these alternative modeling approaches.

Methods Both PS and Markov models were developed using docetaxel and erlotinib as comparators. A three-health state model was used consisting of progression-free, progressed disease, and death. Disease progression and time to progression were estimated by identifying best-fitting survival curves from the clinical trial data for PFS and OS. Expected costs and health outcomes were calculated by combining health-state occupancy with medical resource use and quality-of-life assigned to each of the three health states. The health outcomes included in the model were survival and quality-adjusted-life-years (QALYs).

Results Nivolumab was found to have the highest expected per-patient cost, but also improved per-patient life years (LYs) and QALYs. Nivolumab cost an additional $151,560 and $140,601 per QALY gained compared to docetaxel and erlotinib, respectively, using a PS model approach. The cost-utility estimates using a Markov model were very similar ($152,229 and $141,838, respectively, per QALY gained).

Conclusions Nivolumab was found to involve a trade-off between improved patient survival and QALYs, and increased cost. It was found that the use of a PS or Markov model produced very similar estimates of expected cost, outcomes, and incremental cost-utility.