En este trabajo se proponen dos posibles estimadores del parámetro de dependencia de una familia de distribuciones bivariantes con marginales dadas y se realiza un estudio de Monte Carlo de sus respectivos sesgo y eficiencia, a fin de determinar cuál de ambos estimadores es preferible. También se propone y se estudia, de forma similar, una posible versión "Jackknife" del mejor de los dos estimadores anteriores. En este estudio se emplean técnicas de reducción de la varianza. Para poder realizar...

Generalized F tests were introduced for linear models by Michalski and Zmyślony (1996, 1999). When the observations are taken in not perfectly standardized conditions the F tests have generalized F distributions with random non-centrality parameters, see Nunes and Mexia (2006). We now study the case of nearly normal perturbations leading to Gamma distributed non-centrality parameters.

Generalized length biased distribution is defined as $h\left(x\right)={\phi }_r\left(x\right)f\left(x\right),x>0$, where $f\left(x\right)$ is a probability density function, ${\phi }_r\left(x\right)$ is a polynomial of degree $r$, that is, ${\phi }_r\left(x\right)=a_1(x/{\mu }_1^{\text{'}})+...+a_r(x^r/{\mu }_r^{\text{'}})$, with $a_i>0,i=1,...,r,a_1+...+a_r=1,{\mu }_i^{\text{'}}=E\left(x^i\right)$ for $f\left(x\right),i=1,2...,r$. If $r=1$, we have the simple length biased distribution of Gupta and Keating [1]. First, characterizations of exponential, uniform and beta distributions are given in terms of simple length biased distributions. Next, for the case of generalized distribution, the distribution of the sum of $n$ independent variables is put in the closed form when $f\left(x\right)$...

We consider two continuous time processes; the first one is valued in a semi-metric space, while the second one is real-valued. In some sense, we extend the results of F. Ferraty and P. Vieu in ``Nonparametric models for functional data, with application in regression, time-series prediction and curve discrimination'' (2004), by establishing the convergence, with rates, of the generalized regression function when a real-valued continuous time response is considered. As corollaries, we deduce the...

The concepts of geometric infinite divisibility and stability extend the classical properties of infinite divisibility and stability to geometric convolutions. In this setting, a random variable X is geometrically infinitely divisible if it can be expressed as a random sum of $N_p$ components for each p ∈ (0,1), where $N_p$ is a geometric random variable with mean 1/p, independent of the components. If the components have the same distribution as that of a rescaled X, then X is (strictly) geometric stable....

A generalized form of the usual Lognormal distribution, denoted with ${}_{\gamma }$, is introduced through the γ-order Normal distribution ${}_{\gamma }$, with its p.d.f. defined into (0,+∞). The study of the c.d.f. of ${}_{\gamma }$ is focused on a heuristic method that provides global approximations with two anchor points, at zero and at infinity. Also evaluations are provided while certain bounds are obtained.

The aim of the paper is to present a test of goodness of fit with weigths in the classes based on weighted $\left(h,\phi \right)$-divergences. This family of divergences generalizes in some sense the previous weighted divergences studied by Frank et al [frank] and Kapur [kapur]. The weighted $\left(h,\phi \right)$-divergence between an empirical distribution and a fixed distribution is here investigated for large simple random samples, and the asymptotic distributions are shown to be either normal or equal to the distribution of a linear...

Using characterization conditions of continuous distributions in terms of moments of order statistics given in [12], [23], [6] and [7] we present new goodness-of-fit techniques.

In this paper a new family of statistics based on $K_{\phi }$-divergence for testing goodness-of-fit under composite null hypotheses are considered. The asymptotic distribution of this test is obtained when the unspecified parameters are estimated by maximum likelihood as well as minimum $K_{\phi }$-divergence.

Using characterization conditions of continuous distributions in terms of moments of order statistics and moments of record values we present new goodness-of-fit techniques.