Isabel Proença

Mixed Logit Estimation of Radical Islamic Terrorism in Europe and North America

This article estimates what characteristics (e.g., location, number of casualties, and type of attack) are associated with an Islamic terrorist attack. This is established by identifying the significant determinants of the probability that an attack had been carried out by Islamic terrorists. For Europe, the United States, and Canada, the analysis employs ITERATE (International Terrorism: Attributes of Terrorist Events) data from October 1979 to December 2002 to ascertain the significant characteristics of Islamic terrorist attacks. A random-parameter logit model is used to analyze the probability of such attacks, taking into account the heterogeneity of the sample data. This model outperforms the standard logit model. Some policy implications are presented.

Measuring the Social Recreation Per-Day Net Benefit of the Wildlife Amenities of a National Park: A Count-Data Travel-Cost Approach

In this article, we apply count-data travel-cost methods to a truncated sample of visitors to estimate the Peneda-Gerês National Park (PGNP) average consumer surplus (CS) for each day of visit. The measurement of recreation demand is highly specific because it is calculated by number of days of stay per visit. We therefore propose the application of altered truncated count-data models or truncated count-data models on grouped data to estimate a single, on-site individual recreation demand function, with the price (cost) of each recreation day per trip equal to out-of-pocket and time travel plus out-of-pocket and on-site time costs. We further check the sensitivity of coefficient estimations to alternative models and analyse the welfare measure precision by using the delta and simulation methods by Creel and Loomis. With simulated limits, CS is estimated to be €194 (range €116 to €448). This information is of use in the quest to improve government policy and PNPG management and conservation as well as promote nature-based tourism. To our knowledge, this is the first attempt to measure the average recreation net benefits of each day of stay generated by a national park by using truncated altered and truncated grouped count-data travel-cost models based on observing the individual number of days of stay.

ARE USA CITIZENS AT RISK OF TERRORISM IN EUROPE

This paper analyzes the determinants of the probability of US citizens being victims of terrorist attacks in European countries, taking into account uncontrolled heterogeneity of the data. The analysis employs ITERATE data from February 1968 to December 2002 to ascertain significant characteristics that influence the probability (e.g. location, type of casualties, type of attack, and type of terrorists). To deal with the unobserved heterogeneity a random‐parameter logit model (mixed logit) is used. Some policy implications are presented.

A bootstrap test for single index models

Single index models are frequently used in econometrics and biometrics. Logit and Probit models arc special cases with fixed link functions. In this paper we consider a bootstrap specification test that detects nonparametric deviations of the link function. The bootstrap is used with the aim to rind a more accurate distribution under the null than the normal approximation. We prove that the statistic and its bootstrapped version have the same asymptotic distribution. In a simulation study we show that the bootstrap is able to capture the negative bias and the skewness of the test statistic. It yields better approximations to the true critical values and consequently it has a more accurate level than the normal approximation.

Trade Potential in an Enlarged European Union: A Recent Approach

This paper aims to evaluate the trade potential of manufactured products between countries belonging to the EU in the threshold of its Eastern enlargement. For this purpose we use a Gravity model which is estimated with a Poisson Pseudo-Maximum Likelihood Method. We extend the specification of the gravity model in order to capture bilateral trade specificities between groups of countries of the enlarged EU, allowing to test the statistical significance of these inter-groups’ trade potential. In addition, it includes the Commodity Composition of Trade. The estimated coefficients are used to project exports of each country. We conclude that in 2002 the CEEC as a group had exhausted their export potentialities to the enlarged EU, whereas the same does not apply to its imports from the EU members.

A Bootstrap Test for Single Index Models

Single index models are frequently used in econometrics and biometrics. Logit and Probit models are special cases with fixed link functions. In this paper we consider a bootstrap specification test that detects nonparametric deviations of the link function. The bootstrap is used with the aim to find a more accurate distribution under the null than the normal approximation. We prove that the statistic and its bootstrapped version have the same asymptotic distribution. In a simulation study we show that the bootstrap is able to capture the negative bias and the skewness of the test statistic. It yields better approximations to the true critical values and consequently it has a more accurate level and superior power properties. We propose a modification of the HH statistic which reduces considerably the dependency of the test performance on the bandwidth choice. We show that the bootstrap of this modified statistic works as well.

Trade Potential Revisited: A Panel Data Analysis for Zimbabwe

This paper notes that previous results on trade potential based on a panel data set may be biased and proposes the adequate Poisson Pseudo Maximum Likelihood method to estimate trade potential based on the elasticity estimates generated by a gravity model, with conclusions on trade potential based on confidence intervals estimated with the Delta method. This approach had not been yet considered in the literature for panel data. This methodology is used to evaluate Zimbabwe export potential in a period characterized by strong restrictions on trade, based on the elasticity estimates generated by an augmented gravity model for six Southern African Development Community member countries and their exports to the rest of the world. Results show that Zimbabwe has a large unexploited trade potential which will not be realized without political stability and structural reforms. For comparison purposes, we also present the gravity coefficients calculated with other estimation methods.

A Simple Deconvolving Kernel Density Estimator when Noise Is Gaussian

Deconvolving kernel estimators when noise is Gaussian entail heavy calculations. In order to obtain the density estimates numerical evaluation of a specific integral is needed. This work proposes an approximation to the deconvolving kernel which simplifies considerably calculations by avoiding the typical numerical integration. Simulations included indicate that the lost in performance relatively to the true deconvolving kernel, is almost negligible in finite samples.

Interactive Graphics for Teaching Simple Statistics

The progress of computer science, in association with the progress of computer hardware, is making computers a more accessible and important tool in assisting individuals in processing and computing information. This fact enhances the use of computers for educational and teaching purposes. That is, the current sophisticated potential of computers can be used to provide a means to acquire concepts and to develop reasoning and problem-solving skills. Computer-aided learning (CAL) and computer-aided instruction (CAI) have become established fields in computer science; they utilize the computer as a tool for learning and presenting instruction that is individualized, interactive, and guided.