Optimal two-sided tests for instrumental variables regression with heteroskedastic and autocorrelated errors

This paper considers two-sided tests for the parameter of an endogenous variable in an instrumental variable (IV) model with heteroskedastic and autocorrelated errors. We develop the nite-sample theory of weighted-average power (WAP) tests with normal errors and a known long-run variance. We introduce two weights which are invariant to orthogonal transformations of the instruments; e.g., changing the order in which the instruments appear. While tests using the MM1 weight can be severely biased, optimal tests based on the MM2 weight are naturally two-sided when errors are homoskedastic. We propose two boundary conditions that yield two-sided tests whether errors are homoskedastic or not. The locally unbiased (LU) condition is related to the power around the null hypothesis and is a weaker requirement than unbiasedness. The strongly unbiased (SU) condition is more restrictive than LU, but the associated WAP tests are easier to implement. Several tests are SU in nite samples or asymptotically, including tests robust to weak IV (such as the Anderson-Rubin, score, conditional quasi-likelihood ratio, and I. Andrews' (2015) PI-CLC tests) and two-sided tests which are optimal when the sample size is large and instruments are strong. We refer to the WAP-SU tests based on our weights as MM1-SU and MM2-SU tests. Dropping the restrictive assumptions of normality and known variance, the theory is shown to remain valid at the cost of asymptotic approximations. The MM2-SU test is optimal under the strong IV asymptotics, and outperforms other existing tests under the weak IV asymptotics.

A Theory of voter experimentation in repeated elections

Nesse artigo, eu desenvolvo e analiso um modelo de dois perí odos em que dois polí ticos competem pela preferência de um eleitor representativo, que sabe quão benevolente é um dos polí ticos mas é imperfeitamente informado sobre quão benevolente é o segundo polí tico. O polí tico conhecido é interpretado como um incumbente de longo prazo, ao passo que o polí tico desconhecido é interpretado como um desa fiante menos conhecido. É estabelecido que o mecanismo de provisão de incentivos inerente às elei cões - que surge através da possibilidade de não reeleger um incumbente - e considerações acerca de aquisi cão de informa cão por parte do eleitor se combinam de modo a determinar que em qualquer equilí brio desse jogo o eleitor escolhe o polí tico desconhecido no per íodo inicial do modelo - uma a cão à qual me refi ro como experimenta cão -, fornecendo assim uma racionaliza cão para a não reelei cão de incumbentes longevos. Especifi camente, eu mostro que a decisão do eleitor quanto a quem eleger no per odo inicial se reduz à compara cão entre os benefí cios informacionais de escolher o polí tico desconhecido e as perdas econômicas de fazê-lo. Os primeiros, que capturam as considera cões relacionadas à aquisi cão de informa cão, são mostrados serem sempre positivos, ao passo que as últimas, que capturam o incentivo à boa performance, são sempre não-negativas, implicando que é sempre ótimo para o eleitor escolher o polí tico desconhecido no per íodo inicial.

The spenders-hoarders theory of capital accumulations, wealth distribution and fiscal policy

This paper proposes a simple OLG model which is consistent with the essential facts about consumer behavior, capital accumulation and wealth distribution, and yields some new and surprising conclusions about fiscal policy. By considering a society in which individuais are distinguished according to two characteristics, altruism and wealth preference, we show that those who in the long run hold the bulk of private capital are not so rnuch motivated by dynastic altruism as by preference for wealth. Two types of social segmentation can result with different wcalth distribution. To a large extcnt our results seem to fit reality better than those obtained with standard optimal growth models in which dynastic altruism ( or r ate o f impatience) is the only source of heterogeneity: overaccumulation can appear, public debt and unfunded pensions are not neutra!, estate taxation can improve the welfare of the top wealthy.

Sub-Optimal Orbital Maneuvers for Artificial Satellites

The determination of a specific orbit and the procedure to calculate orbital maneuvers of artificial satellites are problems of extreme importance in the study of orbital mechanics. Therefore, the transferring problem of a spaceship from one orbit to another, and the attention due to this subject has in increased during the last years. Many applications can be found in several space activities, for example, to put a satellite in a geostationary orbit, to change the position of a spaceship, to maintain a specific satellite's orbit, in the design of an interplanetary mission, and others. The Brazilian Satellite SCD-1 (Data Collecting Satellite) will be used as example in this paper. It is the first satellite developed entirely in Brazil, and it remains in operation to this date. SCD-1 was designed, developed, built, and tested by Brazilian scientists, engineers, and technicians working at INPE (National Institute for Space Research, and in Brazilian Industries. During the lifetime, it might be necessary do some complementary maneuvers, being this one either an orbital transferring, or just to make periodical corrections. The purpose of transferring problem is to change the position, velocity and the satellite's mass to a new pre determined state. This transfer can be totally linked (in the case of "Rendezvous") or partially free (free time, free final velocity, etc). In the global case, the direction, the orientation and the magnitude of the thrust to be applied must be chosen, respecting the equipment's limit. In order to make this transferring, either sub-optimal or optimal maneuvers may be used. In the present study, only the sub-optimal will be shown. Hence, this method will simplify the direction of thrust application, to allow a fast calculation that may be used in real time, with a very fast processing. The thrust application direction to be applied will be assumed small and constant, and the purpose of this paper is to find the time interval that the thrust is applied. This paper is basically divided into three parts: during the first one the sub-optimal maneuver is explained and detailed, the second presents the Satellite SCD-1, and finally the last part shows the results using the sub-optimal maneuver applied to the Brazilian Satellite.

H-2 and H-infinity-optimal control for the tracking problem with zero variation

The problem of signal tracking, in the presence of a disturbance signal in the plant, is solved using a zero-variation methodology. A state feedback controller is designed in order to minimise the H-2-norm of the closed-loop system, such that the effect of the disturbance is attenuated. Then, a state estimator is designed and the modification of the zeros is used to minimise the H-infinity-norm from the reference input signal to the error signal. The error is taken to be the difference between the reference and the output signals, thereby making it a tracking problem. The design is formulated in a linear matrix inequality framework, such that the optimal solution of the stated control problem is obtained. Practical examples illustrate the effectiveness of the proposed method.

Multi Objective Evolutionary Algorithm Applied to the Optimal Power Flow Problem

This work presents the application of a multiobjective evolutionary algorithm (MOEA) for optimal power flow (OPF) solution. The OPF is modeled as a constrained nonlinear optimization problem, non-convex of large-scale, with continuous and discrete variables. The violated inequality constraints are treated as objective function of the problem. This strategy allows attending the physical and operational restrictions without compromise the quality of the found solutions. The developed MOEA is based on the theory of Pareto and employs a diversity-preserving mechanism to overcome the premature convergence of algorithm and local optimal solutions. Fuzzy set theory is employed to extract the best compromises of the Pareto set. Results for the IEEE-30, RTS-96 and IEEE-354 test systems are presents to validate the efficiency of proposed model and solution technique.

KT-invexity in optimal control problems

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

THE EFFECT OF RECENT DIET ON PREY ODOR DISCRIMINATION BY JUVENILE TEGU LIZARD, TUPINAMBIS-TEGUIXIN (SAURIA, TEIIDAE)

Teiid lizards are intesive foragers supposed to rely lagerly on chemoreception for prey detection, an ability that can be modified by previous feeding experiences. We investigated the ability of juvenile lizards, Tupinambis teguixin, in discriminate prey from non-prey odors as well as the effects of recent diet on these ability. Tegu lizards were able to discriminate prey odors and this ability probably is inate. The effect of recent diet was analysed through optimal foraging models and our results does not support in a broad sense the predictions made by theoretical models.

Pattern recognition theory in nonlinear signal processing

A body of research has developed within the context of nonlinear signal and image processing that deals with the automatic, statistical design of digital window-based filters. Based on pairs of ideal and observed signals, a filter is designed in an effort to minimize the error between the ideal and filtered signals. The goodness of an optimal filter depends on the relation between the ideal and observed signals, but the goodness of a designed filter also depends on the amount of sample data from which it is designed. In order to lessen the design cost, a filter is often chosen from a given class of filters, thereby constraining the optimization and increasing the error of the optimal filter. To a great extent, the problem of filter design concerns striking the correct balance between the degree of constraint and the design cost. From a different perspective and in a different context, the problem of constraint versus sample size has been a major focus of study within the theory of pattern recognition. This paper discusses the design problem for nonlinear signal processing, shows how the issue naturally transitions into pattern recognition, and then provides a review of salient related pattern-recognition theory. In particular, it discusses classification rules, constrained classification, the Vapnik-Chervonenkis theory, and implications of that theory for morphological classifiers and neural networks. The paper closes by discussing some design approaches developed for nonlinear signal processing, and how the nature of these naturally lead to a decomposition of the error of a designed filter into a sum of the following components: the Bayes error of the unconstrained optimal filter, the cost of constraint, the cost of reducing complexity by compressing the original signal distribution, the design cost, and the contribution of prior knowledge to a decrease in the error. The main purpose of the paper is to present fundamental principles of pattern recognition theory within the framework of active research in nonlinear signal processing.

Bayesian L-optimal exact design of experiments for biological kinetic models

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

A cooperative game theory analysis for transmission loss allocation

This paper presents an analysis and discussion, based on cooperative game theory, for the allocation of the cost of losses to generators and demands in transmission systems. We construct a cooperative game theory model in which the players are represented by equivalent bilateral exchanges and we search for a unique loss allocation solution, the Core. Other solution concepts, such as the Shapley Value, the Bilateral Shapley Value and the Kernel are also explored. Our main objective is to illustrate why is not possible to find an optimal solution for allocating the cost of losses to the users of a network. Results and relevant conclusions are presented for a 4-bus system and a 14-bus system. (c) 2007 Elsevier B.V. All rights reserved.

Necessary conditions for optimal impulsive control problems

A Maximum Principle is derived for a class of optimal control problems arising in midcourse guidance, in which certain controls are represented by measures and, the state trajectories are functions of bounded variation. The optimality conditions improves on previous optimality conditions by allowing nonsmooth data, measurable time dependence, and a possibly time varying constraint set for the conventional controls.

Optimal design of smart structures using bonded piezoelectrics for vibration control

Smart material technology has become an area of increasing interest for the development of lighter and stronger structures which are able to incorporate actuator and sensor capabilities for collocated control. In the design of actively controlled structures, the determination of the actuator locations and the controller gains, is a very important issue. For that purpose, smart material modelling, modal analysis methods, control and optimization techniques are the most important ingredients to be taken into account. The optimization problem to be solved in this context presents two interdependent aspects. The first one is related to the discrete optimal actuator location selection problem, which is solved in this paper using genetic algorithms. The second is represented by a continuous variable optimization problem, through which the control gains are determined using classical techniques. A cantilever Euler-Bernoulli beam is used to illustrate the presented methodology.

A new solution to the optimal power flow problem

A new approach to solving the Optimal Power Flow problem is described, making use of some recent findings, especially in the area of primal-dual methods for complex programming. In this approach, equality constraints are handled by Newton's method inequality constraints for voltage and transformer taps by the logarithmic barrier method and the other inequality constraints by the augmented Lagrangian method. Numerical test results are presented, showing the effective performance of this algorithm. © 2001 IEEE.

Optimal Boussinesq model for shallow-water waves interacting with a microstructure

In this paper, we consider the propagation of water waves in a long-wave asymptotic regime, when the bottom topography is periodic on a short length scale. We perform a multiscale asymptotic analysis of the full potential theory model and of a family of reduced Boussinesq systems parametrized by a free parameter that is the depth at which the velocity is evaluated. We obtain explicit expressions for the coefficients of the resulting effective Korteweg-de Vries (KdV) equations. We show that it is possible to choose the free parameter of the reduced model so as to match the KdV limits of the full and reduced models. Hence the reduced model is optimal regarding the embedded linear weakly dispersive and weakly nonlinear characteristics of the underlying physical problem, which has a microstructure. We also discuss the impact of the rough bottom on the effective wave propagation. In particular, nonlinearity is enhanced and we can distinguish two regimes depending on the period of the bottom where the dispersion is either enhanced or reduced compared to the flat bottom case. © 2007 The American Physical Society.