- GW Home
- Faculty and Staff
Speaker: Robin L. Dillon
McDonough School of Business
Although organizations appear to learn from obvious failures, we argue that it is harder for them to learn from "near-misses" events in which chance played a role in averting failure. In this paper, we formalize the concept of near-misses and hypothesize that organizations and managers fail to learn from near-misses because they evaluate such events as successes and thus feel safer about the situation. This lower level of subjective ("felt") risk encourages riskier subsequent decisions. In our first study, we confirm the tendency to evaluate near-misses as successes by having participants rate a project manager whose decisions result in either: a) mission success, b) near-miss, or c) failure. Participants gave similar ratings to managers whose decisions produced near-misses and to managers whose decisions resulted in successes; both significantly different than managers who experienced failures. We suggest that the failure to hold managers accountable for near-misses is a foregone learning opportunity for both the manager and the organization. In our second set of studies, we confirm that near-miss information leads people to choose a riskier alternative because of a lower subjective risk following near-miss events. We explore several alternative explanations for these findings, including the role of Bayesian updating in processing near-miss data. Ultimately, the analysis suggest that managers and organizations are reducing their subjective assessment of the risk while not necessarily updating (lowering) their objective probability of the failure event.
Time: Thursday, December 13th 11:00 am - 12:15 pm
Location: Funger Hall 520
Speaker: Simon Wilson
School of Computer Science and Statistics
Trinity College, Dublin, Ireland
Telecommunications products, such as make up a wireless network, are characterised by the requirement for very high availability, extensive production testing and the use of multiple back-up of critical components.
In this talk I will discuss two statistical issues that arise in the testing of telecomms products and in the analysis and prediction of their reliability. The first is the use Bayesian modelling through Bayesian networks to model the complicated structure and dependencies between components and software in these systems; these models are used to produce predictions for product reliablity while the product is in development. The second is an application to production testing, which is a very expensive process for these products. The use of Bayesian inference techniques to estimate test properties has helped to optimise this process.
Time: Friday, November 16th 4:00 - 5:30 pm
Location: Funger Hall 420
Speaker: Suleyman Ozekici
Professor of Industrial Engineering
Koc University, Istanbul, Turkey
We consider the optimal portfolio selection problem in a multiple period setting where the investor maximizes the expected utility of the terminal wealth in a stochastic market. The utility function belongs to the hyperbolic absolute risk aversion (HARA) class and the market states change according to a Markov chain. The states of the market describe the prevailing economic, financial, social and other conditions that affect the deterministic and probabilistic parameters of the model. This includes the distributions of the random asset returns as well as the utility function. The problem is solved using the dynamic programming approach to obtain an explicit characterization of the optimal policy and the value function. We also discuss the stochastic structure of the wealth process under the optimal policy and determine various quantities of interest including its Fourier transform. The return-risk frontiers of the terminal wealth are shown to have linear forms. Special cases are discussed with numerical illustrations.
Time: Friday, October 12th 4:00 - 5:30 pm
Location: Funger Hall 420