1,721,078 research outputs found
A Monte Carlo EM Algorithm for the Estimation of a Logistic Auto-logistic Model with Missing Data
Full text linkThis paper proposes an algorithm for the estimation of the parameters of a Logistic Auto-logistic Model when some values of the target variable are missing at random but the auxiliary information is known for the same areas. First, we derive a Monte Carlo EM algorithm in the setup of maximum pseudo-likelihood estimation; given the analytical intractability of the conditional expectation of the complete pseudo-likelihood function, we implement the E-step by means of Monte Carlo simulation. Second, we give an example using a simulated dataset. Finally, a comparison with the standard non-missing data case shows that the algorithm gives consistent results.Spatial Missing Data, Monte Carlo EM Algorithm, Logistic Auto-logistic Model, Pseudo-Likelihood.
Spatial models for flood risk assessment
Full text linkThe problem of computing risk measures associated to flood events is extremely important not only from the point of view of civil protection systems but also because of the necessity for the municipalities of insuring against the damages. In this work we propose, in the framework of an integrated strategy, an operating solution which merges in a conditional approach the information usually available in this setup. First we use a Logistic Auto-Logistic (LAM) model for the estimation of the univariate conditional probabilities of flood events. This approach has two fundamental advantages: it allows to incorporate auxiliary information and does not require the target variables to be indepen- dent. Then we simulate the joint distribution of floodings by means of the Gibbs Sampler. Finally we propose an algorithm to increase ex post the spatial autocorrelation of the simulated events. The methodology is shown to be effective by means of an application to the estimation of the flood probability of Italian hydrographic regions.Flood Risk, Conditional Approach, LAM Model, Pseudo-Maximum Likelihood Estimation, Spatial Autocorrelation, Gibbs Sampler.
A note on maximum likelihood estimation of a Pareto mixture
Full text linkIn this paper we study Maximum Likelihood Estimation of the parameters of a Pareto mixture. Application of standard techniques to a mixture of Pareto is problematic. For this reason we develop two alternative algorithms. The first one is the Simulated Annealing and the second one is based on Cross-Entropy minimization. The Pareto distribution is a commonly used model for heavy-tailed data. It is a two-parameter distribution whose shape parameter determines the degree of heaviness of the tail, so that it can be adapted to data with different features. This work is motivated by an application in the operational risk measurement field: we fit a Pareto mixture to operational losses recorded by a bank in two different business lines. Losses below an unknown threshold are discarded, so that the observed data are truncated. The thresholds used in the two business lines are unknown. Thus, under the assumption that each population follows a Pareto distribution, the appropriate model is a mixture of Pareto where all the parameters have to be estimated.
Measuring industrial agglomeration with inhomogeneous K-function: the case of ICT firms in Milan (Italy)
Full text linkWhy do industrial clusters occur in space? Is it because industries need to stay close together to interact or, conversely, because they concentrate in certain portions of space to exploit favourable conditions like public incentives, proximity to communication networks, to big population concentrations or to reduce transport costs? This is a fundamental question and the attempt to answer to it using empirical data is a challenging statistical task. In economic geography scientists refer to this dichotomy using the two categories of spatial interaction and spatial reaction to common factors. In economics we can refer to a distinction between exogenous causes and endogenous effects. In spatial econometrics and statistics we use the terms of spatial dependence and spatial heterogeneity. A series of recent papers introduced explorative methods to analyses the spatial patterns of firms using micro data and characterizing each firm by its spatial coordinates. In such a setting a spatial distribution of firms is seen as a point pattern and an industrial cluster as the phenomenon of extra-concentration of one industry with respect to the concentration of a benchmarking spatial distribution. Often the benchmarking distribution is that of the whole economy on the ground that exogenous factors affect in the same way all branches. Using such an approach a positive (or negative) spatial dependence between firms is detected when the pattern of a specific sector is more aggregated (or more dispersed) than the one of the whole economy. In this paper we suggest a parametric approach to the analysis of spatial heterogeneity, based on the socalled inhomogeneous K-function (Baddeley et al., 2000). We present an empirical application of the method to the spatial distribution of high-tech industries in Milan (Italy) in 2001. We consider the economic space to be non homogenous, we estimate the pattern of inhomogeneity and we use it to separate spatial heterogeneity from spatial dependence.
Clusters of firms in space and time
Full text linkThe use of the K-functions (Ripley, 1977) has become recently popular in the analysis of the spatial pattern of firms. It was first introduced in the economic literature by Arbia and Espa (1996) and then popularized by Marcon and Puech (2003), Quah and Simpson (2003), Duranton and Overman (2005) and Arbia et al. (2008). In particular in Arbia et al. (2008) we used Ripley’s K-functions as instruments to study the inter-sectoral co-agglomeration pattern of firms in a single moment of time. All this researches have followed a static approach, disregarding the time dimension. Temporal dynamics, on the other hand, play a crucial role in understanding the economic and social phenomena, particularly when referring to the analysis of the individual choices leading to the observed clusters of economic activities. With respect to the contributions previously appeared in the literature, this paper uncovers the process of firm demography by studying the dynamics of localization through space-time K-functions. The empirical part of the paper will focus on the study of the long run localization of firms in the area of Rome (Italy), by concentrating on the ICT sector data collected by the Italian Industrial Union in the period 1920- 2005.Agglomeration, Non-parametric measures; Space-time K-functions, Spatial clusters, Spatial econometrics.
Un modello finanziario di breve periodo per il settore statale italiano: l’analisi relativa al contesto pre−unione monetaria
Full text linkIn this paper we study a structural model for the Italian public finance dealing with financial aspects while the real component of the public budget is considered exogenous on the path coherent with the actual dynamics and institutional constraints, on which we are also concerned. In this context we perform regressions and simulations to evaluate the impact and reactions of the Italian convergence process to EMU and to verify the condition of the Italian public finance in that period. In particular we consider some experiments on the average maturity of the public debt and the long−term benchmark interest−rate referred to the pre−union period
New developments in frontier models for objective assessments
Full text linkThis dissertation is the result of some innovative proposals, in the wide framework of production efficiency frontier models, that have the common goal of reducing subjective choices of the researcher by using, as far as possible, objective methods.
In particular, the first proposal links the economic efficiency theory to the spatial econometrics with the aim of taking into account - in the efficiency evaluation of a productive unit - the neighborhood effects in a global way avoiding the subjective selection of a set of variables identifying territorial effects. The method called Spatial Stochastic Frontier Analysis (SSFA) has been published in Fusco and Vidoli (2013) for the production efficiency analysis and generalized in this thesis to be able to also analyze the cost efficiency.
The second proposal, instead aims to introduce enhancements in the methods using frontier techniques to aggregate simple indicators in a composite indicator. Subjectivity is avoided in the identification of the set of aggregation weights necessary for constructing the composite indicator, in the definition of a preference structure among simple indicators and in the extreme values and outliers influence
removal. The two methods proposed, called respectively Directional Benefit of the Doubt (D-BoD) and Robust Directional Benefit of the Doubt (RD-BoD), have been published in Fusco (2015) and Vidoli, Fusco and Mazziotta (2015). The dissertation consists of four parts: the first one introduces the foundations of the economic efficiency analysis and gives key economic concepts and definitions needed for a proper understanding of the following parts, focusing both on parametric and on nonparametric methods for cross-sectional and panel data and for mono-output and multi-output production processes; the second one discusses the fundamentals of the spatial econometrics, on the main connection proposals with the efficiency theory and shows in detail the SSFA method and the related R package called SSFA implemented to allow other researchers to use it; in the third part the concept of composite indicator and the required steps for its construction are discussed and D-BoD and RD-BoD are shown, moreover the related R package Compind is presented; all proposed methods have been tested both on simulated data and on real
data and the results are shown in the fourth part. In the last part, two innovative applications, respectively on the estimation of non performing loans of commercial banks (Fusco and Maggi, 2016) and on the estimation of the local governments’ expenditure needs (Vidoli and Fusco, 2017) by using the efficiency and spatial theories, are also included
Compliance by believing: an experimental exploration on social norms and impartial agreements
Full text linkThe main contribution of this paper is twofold. First of all, it focuses on the decisional process that leads to the creation of a social norm. Secondly, it analyses the mechanisms through which subjects conform their behaviour to the norm. In particular, our aim is to study the role and the nature of Normative and Empirical Expectations and their influence on people’s decisions. The tool is the Exclusion Game, a sort of ‘triple mini-dictator game’. It represents a situation where 3 subjects – players A - have to decide how to allocate a sum S among themselves and a fourth subject - player B - who has no decisional power. The experiment consists of three treatments. In the Baseline Treatment participants are randomly distributed in groups of four players and play the Exclusion Game. In the Agreement Treatment in each group participants are invited to vote for a specific non-binding allocation rule before playing the Exclusion Game. In the Outsider Treatment, after the voting procedure and before playing the Exclusion Game, a player A for each group (the outsider) is reassigned to a different group and instructed about the rule chosen by the new group. In all the treatments, at the end of the game and before players are informed about the decisions taken during the Exclusion Game by the other co-players, first order and second order expectations (both normative and empirical) are elicited through a brief questionnaire. The first result we obtained is that subjects’ choices are in line with their empirical (not normative) expectations. The second result is that even a non-binding agreement induces convergence of empirical expectations – and, consequently, of choices. The third results is that expectation of conformity is higher in the partner protocol. This implies that a single outsider breaks the ‘trust and cooperation’ equilibrium.fairness, social norms, beliefs, psychological games, experimental games
- …
