Invito: Giornata Studio Centro Modellistica e Statistica-Univ. di Ferrara

["Luigi Salmaso" <salmaso@gest.unipd.it>]

Giornata di studio:
Modelli Matematici e Statistici per l’Economia e le Imprese
Centro per la Modellistica, il Calcolo e la Statistica (CMCS)
Università di Ferrara (HTTP://CMCS.UNIFE.IT)

26 Novembre 2004, ore 15
Sala Affrescata del Dipartimento di Economia, istituzioni e territorio,
Università di Ferrara
Corso Ercole I D'este, 44, 44100, FERRARA

Microscopic Dynamics and Mathematical Modelling in Economy
Lorenzo Pareschi, Dipartimento di Matematica, Università di Ferrara

We consider simple models of economic systems which are originated from
microscopic interactions between economic agents.
First, we refer to closed economic systems where the total money or wealth
is conserved. A generalized Boltzmann equation which takes into account
several types of monetary transactions is derived and its properties
analyzed. For time reversible trading rules it is shown that the stationary
state is given by a Boltzmann-Gibbs law independently on the characteristic
of the market. For non reversible trading we characterize all monetary
transactions in a symmetric way through the three concepts of saving
propensity, potential transaction and risk. Nontrivial stationary states
then may occur and the market behavior becomes more complex.
Next, we consider the effects of an open economy where the inclusion of
investments lead to a growing total amount of money. Other effects, like
taxes and subsidies, are also discussed. Fokker-Planck asymptotics are
derived which present Pareto power law tails. Monte Carlo methods are also
constructed.

Nonparametric Permutation Tests with Applications in Management
F. Pesarin, L. Salmaso, L. Corain, Dipartimento di Scienze Statistiche,
Università di Padova

In many scientific disciplines and industrial fields researchers and
practitioners are often faced with complex problems when dealing with
comparisons between two or more groups using classical parametric methods
although real problems rarely agree with the stringent assumptions required
by such methods. The NPC methodology (Pesarin, 2001) frees the researcher
from stringent assumptions of parametric methods and allows a more flexible
analysis both in terms of specification of multivariate hypotheses and in
terms of the nature of the variables involved in the analysis. One of the
most relevant features of NPC Test is that it does not need a modelling for
dependence among variables.
The methodology of the NonParametric Combination (NPC) of Dependent
Permutation Tests has been applied in the area of management studies to
explore the differences in behavior between those companies that develop
successful products and those that are less successful. The research is
based on a sample of 85 Italian companies working in a B2B (business to
business) market in two specific manufacturing industries and considers New
Products launched over a three year period. The sample has been divided into
four groups, on the basis of the performances of the new product on the
market and on the performances of the NPD process. We assume that each group
of companies has different configurations in Product Architecture Approach,
Organizational Mechanisms, Development Process and Strategic Capabilities.
The results confirm the differences in Product Architecture Approach and
Strategic Capability variables, whereas only a few of the Development
Process and Organizational Mechanisms variables are different among groups.

La giornata di studio è coordinata dal Prof. Fausto Segala, Direttore del
Dipartimento di Economia, istituzioni e territorio.

cmcs.pdf