Gérard Letac
Gérard Letac has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Shaul K. Bar-Lev
Faculty of Industrial Engineering and Technology Management, HIT—Holon Institute of Technology, Holon 5810201, Israel
3 shared publications A. Joffe
2 shared publications- Jacek Wesołowski
Politechnika Warszawska
2 shared publications Dhafer Malouche
Laboratoire de Statistique et Probabilités, 118, Route de Narbonne, 31062 Toulouse Cedex, France. FR
1 shared publicationH. Massam
York University
1 shared publicationHélène Massam
Department of Statistics, University of Virginia, Halsey Hall, Charlottesville, VA 22903, USA
1 shared publication
Latest Publications
- 1 June 2012
- Published by Cambridge University Press (CUP) in Advances in Applied Probability
- Vol. 44 (02) , 373-390
Increasing Hazard Rate of Mixtures for Natural Exponential Families
Hazard rates play an important role in various areas, e.g. reliability theory, survival analysis, biostatistics, queueing theory, and actuarial studies. Mixtures of distributions are also of great preeminence in such areas as most populations of components are indeed heterogeneous. In this study we present a sufficient condition for mixtures of two elements of the same natural exponential family (NEF) to have an increasing hazard rate. We then apply this condition to some classical NEFs having either quadratic or cubic variance functions (VFs) and others as well. Particular attention is paid to the hyperbolic cosine NEF having a quadratic VF, the Ressel NEF having a cubic VF, and the NEF generated by Kummer distributions of type 2. The application of such a sufficient condition is quite intricate and cumbersome, in particular when applied to the latter three NEFs. Various lemmas and propositions are needed to verify this condition for such NEFs. It should be pointed out, however, that our results are mainly applied to a mixture of two populations.
- 1 June 2012
- Published by Cambridge University Press (CUP) in Advances in Applied Probability
- Vol. 44 (02) , 373-390
Increasing Hazard Rate of Mixtures for Natural Exponential Families
Hazard rates play an important role in various areas, e.g. reliability theory, survival analysis, biostatistics, queueing theory, and actuarial studies. Mixtures of distributions are also of great preeminence in such areas as most populations of components are indeed heterogeneous. In this study we present a sufficient condition for mixtures of two elements of the same natural exponential family (NEF) to have an increasing hazard rate. We then apply this condition to some classical NEFs having either quadratic or cubic variance functions (VFs) and others as well. Particular attention is paid to the hyperbolic cosine NEF having a quadratic VF, the Ressel NEF having a cubic VF, and the NEF generated by Kummer distributions of type 2. The application of such a sufficient condition is quite intricate and cumbersome, in particular when applied to the latter three NEFs. Various lemmas and propositions are needed to verify this condition for such NEFs. It should be pointed out, however, that our results are mainly applied to a mixture of two populations.
- 1 June 2012
- Published by Cambridge University Press (CUP) in Advances in Applied Probability
- Vol. 44 (2) , 373-390
Increasing Hazard Rate of Mixtures for Natural Exponential Families
Hazard rates play an important role in various areas, e.g. reliability theory, survival analysis, biostatistics, queueing theory, and actuarial studies. Mixtures of distributions are also of great preeminence in such areas as most populations of components are indeed heterogeneous. In this study we present a sufficient condition for mixtures of two elements of the same natural exponential family (NEF) to have an increasing hazard rate. We then apply this condition to some classical NEFs having either quadratic or cubic variance functions (VFs) and others as well. Particular attention is paid to the hyperbolic cosine NEF having a quadratic VF, the Ressel NEF having a cubic VF, and the NEF generated by Kummer distributions of type 2. The application of such a sufficient condition is quite intricate and cumbersome, in particular when applied to the latter three NEFs. Various lemmas and propositions are needed to verify this condition for such NEFs. It should be pointed out, however, that our results are mainly applied to a mixture of two populations.
- 1 June 2012
- Published by Cambridge University Press (CUP) in Advances in Applied Probability
- Vol. 44 (2) , 373-390
Increasing Hazard Rate of Mixtures for Natural Exponential Families
Hazard rates play an important role in various areas, e.g. reliability theory, survival analysis, biostatistics, queueing theory, and actuarial studies. Mixtures of distributions are also of great preeminence in such areas as most populations of components are indeed heterogeneous. In this study we present a sufficient condition for mixtures of two elements of the same natural exponential family (NEF) to have an increasing hazard rate. We then apply this condition to some classical NEFs having either quadratic or cubic variance functions (VFs) and others as well. Particular attention is paid to the hyperbolic cosine NEF having a quadratic VF, the Ressel NEF having a cubic VF, and the NEF generated by Kummer distributions of type 2. The application of such a sufficient condition is quite intricate and cumbersome, in particular when applied to the latter three NEFs. Various lemmas and propositions are needed to verify this condition for such NEFs. It should be pointed out, however, that our results are mainly applied to a mixture of two populations.
- 1 January 2011
- Published by Societe Mathematique de France in Bulletin de la Société Mathématiques de France
- Vol. 139 (1) , 129-144
Why Jordan algebras are natural in statistics: quadratic regression implies Wishart distributions
- 1 January 2011
- Published by Societe Mathematique de France in Bulletin de la Société Mathématiques de France
- Vol. 139 (1) , 129-144
Why Jordan algebras are natural in statistics: quadratic regression implies Wishart distributions
- Open Access
The limiting behavior of some infinitely divisible exponential dispersion models
Consider an exponential dispersion model (EDM) generated by a probability $ \mu $ on $[0,\infty )$ which is infinitely divisible with an unbounded L\'{e}vy measure $\nu $. The Jorgensen set (i.e., the dispersion parameter space) is then $\mathbb{R}^{+}$, in which case the EDM is characterized by two parameters: $\theta _{0}$ the natural parameter of the associated natural exponential family and the Jorgensen (or dispersion) parameter $t$. Denote by $EDM(\theta _{0},t)$ the corresponding distribution and let $Y_{t}$ is a r.v. with distribution $EDM(\theta_0,t)$. Then if $\nu ((x,\infty ))\sim -\ell \log x$ around zero we prove that the limiting law $F_0$ of $ Y_{t}^{-t}$ as $t\rightarrow 0$ is of a Pareto type (not depending on $ \theta_0$) with the form $F_0(u)=0$ for $u<1$ and $1-u^{-\ell }$ for $ u\geq 1$. Such a result enables an approximation of the distribution of $ Y_{t}$ for relatively small values of the dispersion parameter of the corresponding EDM. Illustrative examples are provided.Open AccessThe limiting behavior of some infinitely divisible exponential dispersion models
Consider an exponential dispersion model (EDM) generated by a probability $ \mu $ on $[0,\infty )$ which is infinitely divisible with an unbounded L\'{e}vy measure $\nu $. The Jorgensen set (i.e., the dispersion parameter space) is then $\mathbb{R}^{+}$, in which case the EDM is characterized by two parameters: $\theta _{0}$ the natural parameter of the associated natural exponential family and the Jorgensen (or dispersion) parameter $t$. Denote by $EDM(\theta _{0},t)$ the corresponding distribution and let $Y_{t}$ is a r.v. with distribution $EDM(\theta_0,t)$. Then if $\nu ((x,\infty ))\sim -\ell \log x$ around zero we prove that the limiting law $F_0$ of $ Y_{t}^{-t}$ as $t\rightarrow 0$ is of a Pareto type (not depending on $ \theta_0$) with the form $F_0(u)=0$ for $u<1$ and $1-u^{-\ell }$ for $ u\geq 1$. Such a result enables an approximation of the distribution of $ Y_{t}$ for relatively small values of the dispersion parameter of the corresponding EDM. Illustrative examples are provided. - Open Access
Why Jordan algebras are natural in statistics:quadratic regression implies Wishart distributions
If the space $\mathcal{Q}$ of quadratic forms in $\mathbb{R}^n$ is splitted in a direct sum $\mathcal{Q}_1\oplus...\oplus \mathcal{Q}_k$ and if $X$ and $Y$ are independent random variables of $\mathbb{R}^n$, assume that there exist a real number $a$ such that $E(X|X+Y)=a(X+Y)$ and real distinct numbers $b_1,...,b_k$ such that $E(q(X)|X+Y)=b_iq(X+Y)$ for any $q$ in $\mathcal{Q}_i.$ We prove that this happens only when $k=2$, when $\mathbb{R}^n$ can be structured in a Euclidean Jordan algebra and when $X$ and $Y$ have Wishart distributions corresponding to this structure.Open AccessWhy Jordan algebras are natural in statistics:quadratic regression implies Wishart distributions
If the space $\mathcal{Q}$ of quadratic forms in $\mathbb{R}^n$ is splitted in a direct sum $\mathcal{Q}_1\oplus...\oplus \mathcal{Q}_k$ and if $X$ and $Y$ are independent random variables of $\mathbb{R}^n$, assume that there exist a real number $a$ such that $E(X|X+Y)=a(X+Y)$ and real distinct numbers $b_1,...,b_k$ such that $E(q(X)|X+Y)=b_iq(X+Y)$ for any $q$ in $\mathcal{Q}_i.$ We prove that this happens only when $k=2$, when $\mathbb{R}^n$ can be structured in a Euclidean Jordan algebra and when $X$ and $Y$ have Wishart distributions corresponding to this structure. - 16 January 2010
- Published by Springer Nature in Journal of Theoretical Probability
- Vol. 24 (2) , 330-341
The Mean Perimeter of Some Random Plane Convex Sets Generated by a Brownian Motion
- 16 January 2010
- Published by Springer Nature in Journal of Theoretical Probability
- Vol. 24 (2) , 330-341
The Mean Perimeter of Some Random Plane Convex Sets Generated by a Brownian Motion
- Open Access
- 3 June 2008
- Published by American Mathematical Society (AMS) in Transactions of the American Mathematical Society
- Vol. 360 (12) , 6475-6496
Laplace transforms which are negative powers of quadratic polynomials
We find the distributions in <!-- MATH $\mathbb{R}^n$ --> for the independent random variables and such that <!-- MATH $\mathbb{E}(X|X+Y)=a(X+Y)$ --> and <!-- MATH $\mathbb{E}(q(X)|X+Y)=bq(X+Y)$ --> where runs through the set of all quadratic forms on <!-- MATH $\mathbb{R}^n$ --> orthogonal to a given quadratic form The essential part of this class is provided by distributions with Laplace transforms <!-- MATH $(1-2\langle c,s\rangle+v(s))^{-p}$ --> that we describe completely, obtaining a generalization of a Gindikin theorem. This leads to the classification of natural exponential families with the variance function of type <!-- MATH $\frac{1}{p}m\otimes m-\varphi(m)M_v$ --> , where is the symmetric matrix associated to the quadratic form and <!-- MATH $m\mapsto \varphi(m)$ --> is a real function. These natural exponential families extend the classical Wishart distributions on Lorentz cones already considered by Jensen, and later on by Faraut and Korányi.- 3 June 2008
- Published by American Mathematical Society (AMS) in Transactions of the American Mathematical Society
- Vol. 360 (12) , 6475-6496
Open AccessLaplace transforms which are negative powers of quadratic polynomials
We find the distributions in <!-- MATH $\mathbb{R}^n$ --> for the independent random variables and such that <!-- MATH $\mathbb{E}(X|X+Y)=a(X+Y)$ --> and <!-- MATH $\mathbb{E}(q(X)|X+Y)=bq(X+Y)$ --> where runs through the set of all quadratic forms on <!-- MATH $\mathbb{R}^n$ --> orthogonal to a given quadratic form The essential part of this class is provided by distributions with Laplace transforms <!-- MATH $(1-2\langle c,s\rangle+v(s))^{-p}$ --> that we describe completely, obtaining a generalization of a Gindikin theorem. This leads to the classification of natural exponential families with the variance function of type <!-- MATH $\frac{1}{p}m\otimes m-\varphi(m)M_v$ --> , where is the symmetric matrix associated to the quadratic form and <!-- MATH $m\mapsto \varphi(m)$ --> is a real function. These natural exponential families extend the classical Wishart distributions on Lorentz cones already considered by Jensen, and later on by Faraut and Korányi. - Open Access
- 1 December 2006
- Published by Cambridge University Press (CUP) in Journal of Applied Probability
- Vol. 43 (4) , 1091-1106
Multitype linear fractional branching processes
We complete a paper written by Edward Pollak in 1974 on a multitype branching process the generating functions of whose birth law are fractional linear functions with the same denominator. The main tool is a parameterization of these functions adapted using the mean matrix M and an element w of the first quadrant. We use this opportunity to give a self-contained presentation of Pollak's theory.
- 1 December 2006
- Published by Cambridge University Press (CUP) in Journal of Applied Probability
- Vol. 43 (4) , 1091-1106
Open AccessMultitype linear fractional branching processes
We complete a paper written by Edward Pollak in 1974 on a multitype branching process the generating functions of whose birth law are fractional linear functions with the same denominator. The main tool is a parameterization of these functions adapted using the mean matrix M and an element w of the first quadrant. We use this opportunity to give a self-contained presentation of Pollak's theory.
- 1 March 2006
- Published by Cambridge University Press (CUP) in Journal of Applied Probability
- Vol. 43 (04) , 1091-1106
Multitype linear fractional branching processes
We complete a paper written by Edward Pollak in 1974 on a multitype branching process the generating functions of whose birth law are fractional linear functions with the same denominator. The main tool is a parameterization of these functions adapted using the mean matrix M and an element w of the first quadrant. We use this opportunity to give a self-contained presentation of Pollak's theory.
- 1 March 2006
- Published by Cambridge University Press (CUP) in Journal of Applied Probability
- Vol. 43 (04) , 1091-1106
Multitype linear fractional branching processes
We complete a paper written by Edward Pollak in 1974 on a multitype branching process the generating functions of whose birth law are fractional linear functions with the same denominator. The main tool is a parameterization of these functions adapted using the mean matrix M and an element w of the first quadrant. We use this opportunity to give a self-contained presentation of Pollak's theory.
- 29 January 2005
- Published by Elsevier in Statistics & Probability Letters
- Vol. 72 (2) , 137-143
Exponential stopping and drifted stable processes
- 29 January 2005
- Published by Elsevier in Statistics & Probability Letters
- Vol. 72 (2) , 137-143
Exponential stopping and drifted stable processes