2005, Vol. 29, Núm. 2
http://hdl.handle.net/2099/3724
2020-01-26T06:45:13ZBook review: Models for discrete longitudinal data (Molenberghs, G.; Verbeke, G.)
http://hdl.handle.net/2099/3779
Book review: Models for discrete longitudinal data (Molenberghs, G.; Verbeke, G.)
Tobías Garcés, Aureli
This book covers a wide variety of statistical techniques for longitudinal data analysis. The autors, Geert Molenberghs and Beert Verbeke -both well known in this field- have extended their previous textbook (Verbeke and Molenberghs, 1997), mainly focused on linear mixed model for continuous data, to the non-Gaussian setting, including binary, ordinal, and counts repeated measures.
2007-11-14T19:10:15ZTobías Garcés, AureliThis book covers a wide variety of statistical techniques for longitudinal data analysis. The autors, Geert Molenberghs and Beert Verbeke -both well known in this field- have extended their previous textbook (Verbeke and Molenberghs, 1997), mainly focused on linear mixed model for continuous data, to the non-Gaussian setting, including binary, ordinal, and counts repeated measures.Likelihood for random-effect models (invited article)
http://hdl.handle.net/2099/3768
Likelihood for random-effect models (invited article)
Lee, Youngjo; Nelder, J. A.
HolaFor inferences from random-effect models Lee and Nelder (1996) proposed to use
hierarchical likelihood (h-likelihood). It allows inference from models that may include
both fixed and random parameters. Because of the presence of unobserved random variables h-likelihood is not a likelihood in the Fisherian sense. The Fisher likelihood
framework has advantages such as generality of application, statistical and computational
efficiency. We introduce an extended likelihood framework and discuss why it is
a proper extension, maintaining the advantages of the original likelihood framework. The new framework allows likelihood inferences to be drawn for a much wider class of models.
2007-11-12T19:54:20ZLee, YoungjoNelder, J. A.HolaFor inferences from random-effect models Lee and Nelder (1996) proposed to use
hierarchical likelihood (h-likelihood). It allows inference from models that may include
both fixed and random parameters. Because of the presence of unobserved random variables h-likelihood is not a likelihood in the Fisherian sense. The Fisher likelihood
framework has advantages such as generality of application, statistical and computational
efficiency. We introduce an extended likelihood framework and discuss why it is
a proper extension, maintaining the advantages of the original likelihood framework. The new framework allows likelihood inferences to be drawn for a much wider class of models.Muliere and Scarsini's bivariate Pareto distribution: sums, products, and ratios
http://hdl.handle.net/2099/3767
Muliere and Scarsini's bivariate Pareto distribution: sums, products, and ratios
Nadarajah, Saralees; Kotz, Samuel
HolaWe derive the exact distributions of R = X +Y , P = X Y andW = X/(X +Y ) and the corresponding moment properties when X and Y follow Muliere and Scarsini’s bivariate Pareto distribution. The expressions turn out to involve special functions.
We also provide extensive tabulations of the percentage points associated with the distributions.These tables –obtained using intensive computing power– will be of use to
practitioners of the bivariate Pareto distribution.
2007-11-12T19:52:41ZNadarajah, SaraleesKotz, SamuelHolaWe derive the exact distributions of R = X +Y , P = X Y andW = X/(X +Y ) and the corresponding moment properties when X and Y follow Muliere and Scarsini’s bivariate Pareto distribution. The expressions turn out to involve special functions.
We also provide extensive tabulations of the percentage points associated with the distributions.These tables –obtained using intensive computing power– will be of use to
practitioners of the bivariate Pareto distribution.On the role played by the fixed bandwidth in the Bickel-Rosenblatt goodness-of-fit test
http://hdl.handle.net/2099/3766
On the role played by the fixed bandwidth in the Bickel-Rosenblatt goodness-of-fit test
Tenreiro, Carlos
HolaFor the Bickel-Rosenblatt goodness-of-fit test with fixed bandwidth studied by Fan
(1998) we derive its Bahadur exact slopes in a neighbourhood of a simple hypothesis
f = f0 and we use them to get a better understanding on the role played by the smoothing parameter in the detection of departures from the null hypothesis. When f0 is a univariate normal distribution and we take for kernel the standard normal density function, we compute these slopes for a set of Edgeworth alternatives which give us a description of the test properties in terms of the bandwidth h. A simulation study is presented which indicates that finite sample properties are in good accordance with the theoretical properties based on Bahadur local efficiency. Comparisons with the quadratic classical EDF tests lead us to recommend a test based on a combination of bandwidths in alternative to Anderson-Darling or Cram´er-von Mises tests.
2007-11-12T19:51:01ZTenreiro, CarlosHolaFor the Bickel-Rosenblatt goodness-of-fit test with fixed bandwidth studied by Fan
(1998) we derive its Bahadur exact slopes in a neighbourhood of a simple hypothesis
f = f0 and we use them to get a better understanding on the role played by the smoothing parameter in the detection of departures from the null hypothesis. When f0 is a univariate normal distribution and we take for kernel the standard normal density function, we compute these slopes for a set of Edgeworth alternatives which give us a description of the test properties in terms of the bandwidth h. A simulation study is presented which indicates that finite sample properties are in good accordance with the theoretical properties based on Bahadur local efficiency. Comparisons with the quadratic classical EDF tests lead us to recommend a test based on a combination of bandwidths in alternative to Anderson-Darling or Cram´er-von Mises tests.On sequential and fixed designs for estimation with comparisons and applications
http://hdl.handle.net/2099/3765
On sequential and fixed designs for estimation with comparisons and applications
Terbeche, Mekki; Broderick O. Oluyede; Barbour, Ahmed
HolaA fully sequential approach to the estimation of the difference of two population means for distributions belonging to the exponential family of distributions is adopted and compared with the best fixed design. Results on the lower bound for the Bayes risk due to estimation and expected cost are presented and shown to be of first order effi-ciency. Applications involving the Poisson and exponential distributions with gamma priors as well as the Bernoulli distribution with beta priors are given. Finally, some numerical results are presented.
2007-11-12T19:49:26ZTerbeche, MekkiBroderick O. OluyedeBarbour, AhmedHolaA fully sequential approach to the estimation of the difference of two population means for distributions belonging to the exponential family of distributions is adopted and compared with the best fixed design. Results on the lower bound for the Bayes risk due to estimation and expected cost are presented and shown to be of first order effi-ciency. Applications involving the Poisson and exponential distributions with gamma priors as well as the Bernoulli distribution with beta priors are given. Finally, some numerical results are presented.On the probability of reaching a barrier in an Erlang(2) risk process
http://hdl.handle.net/2099/3764
On the probability of reaching a barrier in an Erlang(2) risk process
Claramunt Bielsa, M. Mercè; Mármol, M. Teresa; Lacayo, Ramón A.
HolaIn this paper the process of aggregated claims in a non-life insurance portfolio as
defined in the classical model of risk theory is modified. The Compound Poisson process is replaced with a more general renewal risk process with interoccurrence times of Erlangian type. We focus our analysis on the probability that the process of surplus reaches a certain level before ruin occurs, χ(u,b). Our main contribution is the generalization obtained in the computation of χ(u,b) for the case of interoccurrence time between claims distributed as Erlang(2, β) and the individual claim amount as Erlang
(n, γ).
2007-11-12T19:47:48ZClaramunt Bielsa, M. MercèMármol, M. TeresaLacayo, Ramón A.HolaIn this paper the process of aggregated claims in a non-life insurance portfolio as
defined in the classical model of risk theory is modified. The Compound Poisson process is replaced with a more general renewal risk process with interoccurrence times of Erlangian type. We focus our analysis on the probability that the process of surplus reaches a certain level before ruin occurs, χ(u,b). Our main contribution is the generalization obtained in the computation of χ(u,b) for the case of interoccurrence time between claims distributed as Erlang(2, β) and the individual claim amount as Erlang
(n, γ).Factorial experimental designs and generalized linear models
http://hdl.handle.net/2099/3763
Factorial experimental designs and generalized linear models
Dossou-Gbété, Simplice; Tinsson, Walter
HolaThis paper deals with experimental designs adapted to a generalized linear model. We introduce a special link function for which the orthogonality of design matrix obtained under Gaussian assumption is preserved. We investigate by simulation some of its properties.
2007-11-12T19:45:58ZDossou-Gbété, SimpliceTinsson, WalterHolaThis paper deals with experimental designs adapted to a generalized linear model. We introduce a special link function for which the orthogonality of design matrix obtained under Gaussian assumption is preserved. We investigate by simulation some of its properties.A comparison of parametric models for mortality graduation. Application to mortality data of the Valencia Region (Spain)
http://hdl.handle.net/2099/3762
A comparison of parametric models for mortality graduation. Application to mortality data of the Valencia Region (Spain)
Debón, Ana; Montes, F. (Francisco); Sala, Ramon
HolaThe parametric graduation of mortality data has as its objective the satisfactory estimation of the death rates based on mortality data but using an age-dependent function whose parameters are adjusted from the crude rates obtainable directly from the data. This paper proposes a revision of the most commonly used parametric methods and
compares the results obtained with each of them when they are applied to the mortality
data for the Valencia Region. As a result of the comparison, we conclude that the
Gompertz-Makeham functions estimated by means of generalized linear models lead
to the best results. Our working method is of additional interest for being applicable to mortality data for a wide range of ages from any geographical conditions, allowing us
to select the most appropriate life table for the case in hand.
2007-11-12T19:44:17ZDebón, AnaMontes, F. (Francisco)Sala, RamonHolaThe parametric graduation of mortality data has as its objective the satisfactory estimation of the death rates based on mortality data but using an age-dependent function whose parameters are adjusted from the crude rates obtainable directly from the data. This paper proposes a revision of the most commonly used parametric methods and
compares the results obtained with each of them when they are applied to the mortality
data for the Valencia Region. As a result of the comparison, we conclude that the
Gompertz-Makeham functions estimated by means of generalized linear models lead
to the best results. Our working method is of additional interest for being applicable to mortality data for a wide range of ages from any geographical conditions, allowing us
to select the most appropriate life table for the case in hand.