Final Activity Report Summary - COMPUTING ECONOMICS (Computational techniques for economic growth and management problems)
The work carried out during this project was concerned with three lines of research. The first was devoted to modelling and calibrating dynamic and stochastic economic problems, the second focussed on numerical methods for solving these problems and the last one applied the developed techniques to management modelling. Several research papers were submitted for their publication in international peer-refereed journals, and others were in progress by the time of the project completion.
All research results gave rise to the following manuscripts:
1. Reducing the curse of dimensionality in dynamic stochastic economic problems by decomposition methods, with F. J. Nogales. This paper introduced a decomposition methodology, based on a mathematical programming framework, to compute the equilibrium path in dynamic models by breaking the problem into a set of smaller independent sub-problems. We studied the performance of the method solving a set of dynamic stochastic economic models. The numerical results revealed that the proposed methodology was efficient in terms of computing time and accuracy.
2. Worst-case estimation and asymptotic theory for models with unobservables, with Jose M. Vidal Sanz. This paper proposed a worst-case approach for estimating econometric models containing unobservable variables. Worst-case estimators were robust against the adverse effects of unobservables and, unlike the classical literature, there were no assumptions made about the statistical nature of the unobservables. This methodology was useful for building robust decision-making models with limited and uncertain knowledge of empirical information.
3. Optimal duration of magazine promotions, with José M. Múgica and Jose M. Vidal Sanz. Planning promotion events and other marketing activities, often requires manufacturers to make decisions about the events duration. On the basis of the expected economic return associated to the dynamic response to stimuli, we considered how long it should last using dynamic programming optimisation. The results suggested that this methodology could help publishing managers to plan the optimal duration of promotion events. This paper was forthcoming, soon after the project completion, in Marketing Letters.
4.Diffusion in a two population world: when giving some away makes sense, with Donald R. Lehmann. Research consistently identified different segments of adopters of new products. Such categorisations often included innovators versus imitators, technophiles versus normal people and business versus consumer users. In this research work we proposed a model which captured this influence and examined the conditions under which it was, or was not, profitable to subsidise adoption by the first group. We focussed on studying some optimal firm behaviour when launching new products with a focus on subsidising some customers in order to speed the diffusion process.
5. Spatial density in retailing and its impact on business performance, with José M. Múgica, and Jose M. Vidal Sanz. In the line of management modelling, we offered an efficient and strong competition measurement which captured the interdependent nature of spatial relationships. The proposed methodology was applied to measure retail density in a medium-sized town for which there were data about the return expectations of retailers over 11 consecutive periods of three months. Our results confirmed that retail density had an impact on economic performance.
All research results gave rise to the following manuscripts:
1. Reducing the curse of dimensionality in dynamic stochastic economic problems by decomposition methods, with F. J. Nogales. This paper introduced a decomposition methodology, based on a mathematical programming framework, to compute the equilibrium path in dynamic models by breaking the problem into a set of smaller independent sub-problems. We studied the performance of the method solving a set of dynamic stochastic economic models. The numerical results revealed that the proposed methodology was efficient in terms of computing time and accuracy.
2. Worst-case estimation and asymptotic theory for models with unobservables, with Jose M. Vidal Sanz. This paper proposed a worst-case approach for estimating econometric models containing unobservable variables. Worst-case estimators were robust against the adverse effects of unobservables and, unlike the classical literature, there were no assumptions made about the statistical nature of the unobservables. This methodology was useful for building robust decision-making models with limited and uncertain knowledge of empirical information.
3. Optimal duration of magazine promotions, with José M. Múgica and Jose M. Vidal Sanz. Planning promotion events and other marketing activities, often requires manufacturers to make decisions about the events duration. On the basis of the expected economic return associated to the dynamic response to stimuli, we considered how long it should last using dynamic programming optimisation. The results suggested that this methodology could help publishing managers to plan the optimal duration of promotion events. This paper was forthcoming, soon after the project completion, in Marketing Letters.
4.Diffusion in a two population world: when giving some away makes sense, with Donald R. Lehmann. Research consistently identified different segments of adopters of new products. Such categorisations often included innovators versus imitators, technophiles versus normal people and business versus consumer users. In this research work we proposed a model which captured this influence and examined the conditions under which it was, or was not, profitable to subsidise adoption by the first group. We focussed on studying some optimal firm behaviour when launching new products with a focus on subsidising some customers in order to speed the diffusion process.
5. Spatial density in retailing and its impact on business performance, with José M. Múgica, and Jose M. Vidal Sanz. In the line of management modelling, we offered an efficient and strong competition measurement which captured the interdependent nature of spatial relationships. The proposed methodology was applied to measure retail density in a medium-sized town for which there were data about the return expectations of retailers over 11 consecutive periods of three months. Our results confirmed that retail density had an impact on economic performance.