Search

In a random environment, the growth of a population subjected to harvesting can be described by a stochastic differential equation.We consider a population with natural growth following a Gompertz model with harvesting proportional to population size and to the exerted fishing effort. The main goal of this work is to compare the performance of three fishing policies: one with variable effort, named optimal policy, the second based on variable effort but with small periods with constant effort, named stepwise policy, and another with constant effort, denoted by optimal sustainable policy.We will show that the first policy is inapplicable from the practical point of view, whereas the second one, although being suboptimal, is applicable but has some shortcomings common to the optimal policy. On the contrary, the constant effort policy is easily implemented and predicts the sustainability of the population as well as the existence of a stationary density for its size. The performance of the policies will be assessed by the profit obtained over a finite time horizon. We also show how changes in the parameter values affect the profit differences between the variable effort policy and the constant effort policy.

We analyze the auto-correlations of all European Union (EU) indices and the cross-correlation between the UK stock market and the other EU markets. This analysis took into account the BREXIT referendum, on the 23rd of June 2016 and the entire period was partitioned in two periods, before and after the BREXIT referendum. First of all, we applied the Detrended Fluctuation Analysis method (with the regular and with a sliding windows approach) in order to evaluate market efficiency. In this case, we found that in general the referendum did not change efficiency levels significantly. With the main purpose of measuring the markets interdependence in relation to the UK index, following the referendum, we calculated the Δ ρ D C C A coefficient. Our results point to a decrease in the cross-correlation coefficient ( Δ ρ D C C A 0 ), meaning that the UK is more segmented now, in relation to other EU partners, than in the past. With Δ ρ D C C A it was possible to identify how much the referendum influenced the interdependence, but not the efficiency, of European markets.

Este trabalho objetivou propor e avaliar uma metodologia estatística para o melhoramento genético do valor extremo das distribuições de caracteres quantitativos. Essa abordagem baseia-se nos quantis superiores da GEV (Distribuição de Valores Extremos Generalizada) e da DEV (Distribuições de Valores Extremos) dos valores genotípicos individuais entre e dentro de famílias de plantas ou animais. Usando bases de dados reais e simulados de progênies ou famílias de cana-de-açúcar, distribuições de valores extremos (Gumbel, Fréchet e Weibull) foram ajustadas aos máximos das famílias. Simulações estocásticas e reamostragens de dados experimentais indicaram consistentemente que a avaliação de 200 famílias maximiza a eficiência do melhoramento visando à seleção de indivíduos extremos. A distribuição Weibull foi a de melhor ajuste (seguida pela Gumbel) e indicou aumento da eficiência seletiva de 1,10 (ganho de 10%) quando se passa de 20 para 100 indivíduos por família e de 1,12 (ganho de 2%) quando se passa de 100 para 200 indivíduos. Esses números são aproximadamente constantes independentemente do número de famílias avaliadas. Uma boa opção prática seria a avaliação de 200 famílias com 100 indivíduos, num total de 20000 indivíduos. A metodologia é adequada também para classificar famílias pela capacidade de geração de indivíduos superiores e informar os tamanhos amostrais em cada família para capturar esses indivíduos. Made available in DSpace on 2018-11-27T23:34:36Z (GMT). No. of bitstreams: 1 2018M.DeonRBBTeoria.pdf: 426793 bytes, checksum: 10517f6b7ea1667d8ef091dcc9a18c0b (MD5) Previous issue date: 2018-11-26

Stochastic ordering of distributions of random variables may be defined by the relative convexity of the tail functions. This has been extended to higher order stochastic orderings, by iteratively reassigning tail-weights. The actual verification of those stochastic orderings is not simple, as this depends on inverting distribution functions for which there may be no explicit expression. The iterative definition of distributions, of course, contributes to make that verification even harder. We have a look at the stochastic ordering, introducing a method that allows for explicit usage, applying it to the Gamma and Weibull distributions, giving a complete description of the order relations within each of those families.

We consider a special class of weak dependent random variables with control on covariances of Lipschitz transformations. This class includes, but is not limited to, positively, negatively associated variables and a few other classes of weakly dependent structures. We prove the Strong Law of Large Numbers with the characterization of convergence rates which is almost optimal, in the sense that it is arbitrarily close to the optimal rate for independent variables. Moreover, we prove an inequality comparing the joint distributions with the product distributions of the margins, similar to the well known Newman's inequality for characteristic functions of associated variables. As a consequence, we prove the Central Limit Theorem together with its functional counterpart, and also the convergence of the empirical process for this class of weak dependent variables.

Stock market comovements are examined using cointegration, Granger causality tests and nonlinear approaches in context of mutual information and correlations. Underlying data sets are affected by non-stationarities and trends, we also apply AMF-DFA and AMF-DXA. We find only 170 pair of Stock markets cointegrated, and according to the Granger causality and mutual information, we realize that the strongest relations lies between emerging markets, and between emerging and frontier markets. According to scaling exponent given by AMF-DFA, $h(q=2)>1$, we find that all underlying data sets belong to non-stationary process. According to EMH, only 8 markets are classified in uncorrelated processes at $2\sigma$ confidence interval. 6 Stock markets belong to anti-correlated class and dominant part of markets has memory in corresponding daily index prices during January 1995 to February 2014. New-Zealand with $H=0.457\pm0.004$ and Jordan with $H=0.602\pm 0.006$ are far from EMH. The nature of cross-correlation exponents based on AMF-DXA is almost multifractal for all pair of Stock markets. The empirical relation, $H_{xy}\le [H_{xx}+H_{yy}]/2$, is confirmed. Mentioned relation for $q>0$ is also satisfied while for $q, Comment: 16 pages, 13 figures and 4 tables, major revision and match to published version

Football is a sport that moves thousands of people and millions of euros. Since 1983, several clubs entered the stock markets with shares, and now twenty two clubs are listed in the Stoxx Football Index. In this study, we analyse the behaviour of the return rates of such shares, with Detrended Fluctuation Analysis and Detrended Cross-Correlation Analysis (and its correlation coefficient). With Detrended Fluctuation Analysis, we are able to observe that the shares of several clubs are far from the behaviour of a random walk, which is expected by the theory. Using Detrended Cross-Correlation Analysis, we calculate the cross correlations of clubs’ returns with national indexes and then with the Stoxx Football Index. Although almost all of them are positive, they do not seem to be strong.

The Efficient Market Hypothesis (EMH), one of the most important hypothesis in financial economics, argues that return rates have no memory (correlation) which implies that agents cannot make abnormal profits in financial markets, due to the possibility of arbitrage operations. With return rates for the US stock market, we corroborate the fact that with a linear approach, return rates do not show evidence of correlation. However, linear approaches might not be complete or global, since return rates could suffer from nonlinearities. Using detrended cross-correlation analysis and its correlation coefficient, a methodology which analyzes long-range behavior between series, we show that the long-range correlation of return rates only ends in the 149th lag, which corresponds to about seven months. Does this result undermine the EMH?

We consider parametric accelerated failure time models with random effects to predict the probability of possibly correlated failures occurring in oil wells. In this context, we first consider empirical Bayes predictors (EBP) based on aWeibull distribution for the failure times and on a Gaussian distribution for the random effects.We also obtain empirical best linear unbiased predictors (EBLUP) using a linear mixed model for which the form of the distribution of the random effects is not specified. We compare both approaches using data obtained from an oil-drilling company and suggest how the results may be employed in designing a preventive maintenance program.

A random coefficient autoregressive process for count data based on a generalized thinning operator is presented. Existence and weak stationarity conditions for these models are established. For the particular case of the (generalized) binomial thinning, it is proved that the necessary and sufficient conditions for weak stationarity are the same as those for continuous-valued AR(1) processes. These kinds of processes are appropriate for modelling non-linear integer-valued time series. They allow for over-dispersion and are appropriate when including covariates. Model parameters estimators are calculated and their properties studied analytically and/or through simulation.

This paper proposes an iterative process, that can be implemented using GLIM, for fitting generalized linear models with linear inequality parameter constraints, when the maximum likelihood estimates exist and are unique. A one-step estimate is also introduced and some diagnostic measures are obtained. Finally an example is given for illustration.

On donne des exemples qui jettent un doute sur la validite generale de l'argument de vraisemblance partielle et suggerent que des conditions plus rigoureuses soient mises en place avant une utilisation generale de la methode

A new proof is given of the complete convergence theorem for the $d$-dimensional basic contact process provided that the infection parameter is larger than the critical value in the one-dimensional case. This proof is much more elementary than the known one since it does not depend on exponential estimates and does not use the subadditive ergodic theory in the extension from one to more dimensions.

Summary This paper shows how a result of Zyskind (1967) on characterization of best linear estimators for general linear models may be applied to generalize and unify the results of the theory of linear prediction in survey sampling. The robust linear predictor is characterized in a general situation. By using indicators of sample elements it is shown that the natural order of the population quantities may be maintained throughout the analysis.

Using data obtained by a multiple capture-recapture process with trap response, the problem of model choice and inference for the size of a closed animal population is considered from a Bayesian viewpoint. Four different models are discussed and for some estimators and tests developed there are no competitors from the classical sampling approach. A variety ofprior structures are considered with the purpose of studying the influence of the priors chosen on the posterior distribution. A special prior structure which takes into consideration the possible correlation between capture and recapture probabilities is also analyzed

We present a statistical procedure to test that a life distribution is exponential against the al ternative that it is continuous new better than used in expectation. The test is shown to be consistent and asymptotic relative efficiency resul ts are obtained against the competitor developed earlier by Hollander and Proschan [2], for certain families of alternatives.

In this paper we consider the observed lifetime of a multistate monotone system and ‘the critical lower set' which causes the system deterioration. Then, under suitable conditions, we identify the component lifetime distribution using a Newton–Kantorovic iterative procedure as in Meilijson (1981).

On repond a une question posee par Durett (1984): on demontre que le processus d'arete de percolation orientee en deux dimensions n'a pas une distribution stationnaire dans le cas sous-critique

The following results are proved: 1) For the upper invariant measure of the basic one-dimensional supercritical contact process the density of 1's has the usual large deviation behavior: the probability of a large deviation decays exponentially with the number of sites considered. 2) For supercritical two-dimensional nearest neighbor site (or bond) percolation the densityY Λ of sites inside a square Λ which belong to the infinite cluster has the following large deviation properties. The probability thatY Λ deviates from its expected value by a positive amount decays exponentially with the area of Λ, while the probability that it deviates from its expected value by a negative amount decays exponentially with the perimeter of Λ. These two problems are treated together in this paper because similar techniques (renormalization) are used for both.

The probability disaibution associated with the multisample CMRa generalized sequential sampling process are obtained by using an analogy with a single urn model. Some statistical features are also discussed.