2014: Vol. 38, Núm. 2
http://hdl.handle.net/2099/15901
Sun, 12 Jul 2020 03:53:55 GMT2020-07-12T03:53:55ZAn extension of the slash-elliptical distribution
http://hdl.handle.net/2117/89022
An extension of the slash-elliptical distribution
Rojas, Mario A.; Bolfarine, Heleno; Gómez, Héctor W.
This paper introduces an extension of the slash-elliptical distribution. This new distribution is generated as the quotient between two independent random variables, one from the elliptical family (numerator) and the other (denominator) a beta distribution. The resulting slash-elliptical distribution potentially has a larger kurtosis coefficient than the ordinary slash-elliptical distribution. We investigate properties of this distribution such as moments and closed expressions for the density function. Moreover, an extension is proposed for the location scale situation. Likelihood equations are derived for this more general version. Results of a real data application reveal that the proposed model performs well, so that it is a viable alternative to replace models with lesser kurtosis flexibility. We also propose a multivariate extension.
Thu, 21 Jul 2016 09:57:43 GMThttp://hdl.handle.net/2117/890222016-07-21T09:57:43ZRojas, Mario A.Bolfarine, HelenoGómez, Héctor W.This paper introduces an extension of the slash-elliptical distribution. This new distribution is generated as the quotient between two independent random variables, one from the elliptical family (numerator) and the other (denominator) a beta distribution. The resulting slash-elliptical distribution potentially has a larger kurtosis coefficient than the ordinary slash-elliptical distribution. We investigate properties of this distribution such as moments and closed expressions for the density function. Moreover, an extension is proposed for the location scale situation. Likelihood equations are derived for this more general version. Results of a real data application reveal that the proposed model performs well, so that it is a viable alternative to replace models with lesser kurtosis flexibility. We also propose a multivariate extension.Untangling the influence of several contextual variables on the respondents‘lexical choices. A statistical approach
http://hdl.handle.net/2117/88566
Untangling the influence of several contextual variables on the respondents‘lexical choices. A statistical approach
Bécue-Bertaut, Mónica; Pagès, Jérôme; Kostov, Belchin
This work proposes an original textual statistical method to uncover the relationships between opinions, expressed as free-text answers, and respondents’ characteristics. This method also identifies the specific links between each characteristic and certain words used in these answers. Promising results are obtained as shown by an application to real data collected to know what health means for non-experts, essential knowledge for effective public health interventions.
Wed, 06 Jul 2016 14:06:11 GMThttp://hdl.handle.net/2117/885662016-07-06T14:06:11ZBécue-Bertaut, MónicaPagès, JérômeKostov, BelchinThis work proposes an original textual statistical method to uncover the relationships between opinions, expressed as free-text answers, and respondents’ characteristics. This method also identifies the specific links between each characteristic and certain words used in these answers. Promising results are obtained as shown by an application to real data collected to know what health means for non-experts, essential knowledge for effective public health interventions.Balancing properties. A need for the application of propensity score methods in estimation of treatment effects
http://hdl.handle.net/2117/88565
Balancing properties. A need for the application of propensity score methods in estimation of treatment effects
Urkaregi, Arantza; Martinez-Indart, Lorea; Pijoán, José Ignacio
There has been recently a striking increase in the use of propensity score methods in health sciences research as a tool to adjust for selection bias in making causal inferences from observational controlled studies. However, reviews of published studies that use these techniques suggest that investigators often do not pay proper attention to thorough verification of appropriate fulfilment of propensity score adjusting properties. By using a case study in which balance is not achieved, we illustrate the need to systematically asses the accomplishment of the balancing property of the propensity score as a critical requirement for obtaining unbiased treatment effects estimates
Wed, 06 Jul 2016 14:04:35 GMThttp://hdl.handle.net/2117/885652016-07-06T14:04:35ZUrkaregi, ArantzaMartinez-Indart, LoreaPijoán, José IgnacioThere has been recently a striking increase in the use of propensity score methods in health sciences research as a tool to adjust for selection bias in making causal inferences from observational controlled studies. However, reviews of published studies that use these techniques suggest that investigators often do not pay proper attention to thorough verification of appropriate fulfilment of propensity score adjusting properties. By using a case study in which balance is not achieved, we illustrate the need to systematically asses the accomplishment of the balancing property of the propensity score as a critical requirement for obtaining unbiased treatment effects estimatesNew approaches in the chemometric analysis of infrared spectra of extra-virgin olive oils
http://hdl.handle.net/2117/88564
New approaches in the chemometric analysis of infrared spectra of extra-virgin olive oils
Sánchez-Rodríguez, María Isabel; Sánchez-López, Elena M.; Marinas, Alberto; Caridad, José Mª; Urbano, Francisco José; Marinas, José Mª
The aim of this paper is to apply new chemometric approaches to obtain quantitative information from near and mid infrared spectra of Andalusian extra-virgin olive oils, using gas chromatography as a classical reference analytical technique. Estimations of the content in saturated, monounsaturated and polyunsaturated fatty acids are given using partial least squares regression from the near and mid infrared data matrices as well as their concatenated matrix. The different estimations are evaluated in terms of goodness of fit (calibration) and prediction (validation), as a function of the number of partial least squares factors in the regression model and the used matrix of data. Furthermore, the nature, systematic or random, of the prediction errors is studied by a decomposition of their mean squared error. Finally, procedures of cross-validation are implemented in order to generalize the previous results.
Wed, 06 Jul 2016 14:02:27 GMThttp://hdl.handle.net/2117/885642016-07-06T14:02:27ZSánchez-Rodríguez, María IsabelSánchez-López, Elena M.Marinas, AlbertoCaridad, José MªUrbano, Francisco JoséMarinas, José MªThe aim of this paper is to apply new chemometric approaches to obtain quantitative information from near and mid infrared spectra of Andalusian extra-virgin olive oils, using gas chromatography as a classical reference analytical technique. Estimations of the content in saturated, monounsaturated and polyunsaturated fatty acids are given using partial least squares regression from the near and mid infrared data matrices as well as their concatenated matrix. The different estimations are evaluated in terms of goodness of fit (calibration) and prediction (validation), as a function of the number of partial least squares factors in the regression model and the used matrix of data. Furthermore, the nature, systematic or random, of the prediction errors is studied by a decomposition of their mean squared error. Finally, procedures of cross-validation are implemented in order to generalize the previous results.Estimators for the parameter mean of Morgenstern type bivariate generalized exponential distribution using ranked set sampling
http://hdl.handle.net/2117/88563
Estimators for the parameter mean of Morgenstern type bivariate generalized exponential distribution using ranked set sampling
Tahmasebi, Saeid; Jafari, Ali Akbar
In situations where the sampling units in a study can be more easily ranked based on the measurement of an auxiliary variable, ranked set sampling provides unbiased estimators for the mean of a population that are more efficient than unbiased estimators based on simple random sampling. In this paper, we consider the Morgenstern type bivariate generalized exponential distribution and obtain several unbiased estimators for the mean parameter of its marginal distribution, based on different ranked set sampling schemes. The efficiency of all considered estimators are evaluated and several numerical illustrations are given.
Wed, 06 Jul 2016 13:59:38 GMThttp://hdl.handle.net/2117/885632016-07-06T13:59:38ZTahmasebi, SaeidJafari, Ali AkbarIn situations where the sampling units in a study can be more easily ranked based on the measurement of an auxiliary variable, ranked set sampling provides unbiased estimators for the mean of a population that are more efficient than unbiased estimators based on simple random sampling. In this paper, we consider the Morgenstern type bivariate generalized exponential distribution and obtain several unbiased estimators for the mean parameter of its marginal distribution, based on different ranked set sampling schemes. The efficiency of all considered estimators are evaluated and several numerical illustrations are given.Exact prediction intervals for future current records and record range from any continuous distribution
http://hdl.handle.net/2117/88562
Exact prediction intervals for future current records and record range from any continuous distribution
Barakat, Haroon; Nigm, Elsayed; Aldallal, Ramy
In this paper, a general method for predicting future lower and upper current records and record range from any arbitrary continuous distribution is proposed. Two pivotal statistics with the same explicit distribution for lower and upper current records are developed to construct prediction intervals for future current records. In addition, prediction intervals for future observations of the record range are constructed. A simulation study is applied on normal and Weibull distributions to investigate the efficiency of the suggested method. Finally, an example for real lifetime data with unknown distribution is analysed.
Wed, 06 Jul 2016 13:57:49 GMThttp://hdl.handle.net/2117/885622016-07-06T13:57:49ZBarakat, HaroonNigm, ElsayedAldallal, RamyIn this paper, a general method for predicting future lower and upper current records and record range from any arbitrary continuous distribution is proposed. Two pivotal statistics with the same explicit distribution for lower and upper current records are developed to construct prediction intervals for future current records. In addition, prediction intervals for future observations of the record range are constructed. A simulation study is applied on normal and Weibull distributions to investigate the efficiency of the suggested method. Finally, an example for real lifetime data with unknown distribution is analysed.Assessing the impact of early detection biases on breast cancer survival of Catalan women
http://hdl.handle.net/2117/88561
Assessing the impact of early detection biases on breast cancer survival of Catalan women
Roso-Llorach, Albert; Forné, Carles; Macià, Francesc; Galceran, Jaume; Marcos-Gragera, Rafael; Rué, Montserrat
Survival estimates for women with screen-detected breast cancer are affected by biases specific to early detection. Lead-time bias occurs due to the advance of diagnosis, and length-sampling bias because tumors detected on screening exams are more likely to have slower growth than tumors symptomatically detected. Methods proposed in the literature and simulation were used to assess the impact of these biases. If lead-time and length-sampling biases were not taken into account, the median survival time of screen-detected breast cancer cases may be overestimated by 5 years and the 5-year cumulative survival probability by between 2.5 to 5 percent units.
Wed, 06 Jul 2016 13:55:39 GMThttp://hdl.handle.net/2117/885612016-07-06T13:55:39ZRoso-Llorach, AlbertForné, CarlesMacià, FrancescGalceran, JaumeMarcos-Gragera, RafaelRué, MontserratSurvival estimates for women with screen-detected breast cancer are affected by biases specific to early detection. Lead-time bias occurs due to the advance of diagnosis, and length-sampling bias because tumors detected on screening exams are more likely to have slower growth than tumors symptomatically detected. Methods proposed in the literature and simulation were used to assess the impact of these biases. If lead-time and length-sampling biases were not taken into account, the median survival time of screen-detected breast cancer cases may be overestimated by 5 years and the 5-year cumulative survival probability by between 2.5 to 5 percent units.Global hypothesis test to compare the likelihood ratios of multiple binary diagnostic tests with ignorable missing data
http://hdl.handle.net/2117/88560
Global hypothesis test to compare the likelihood ratios of multiple binary diagnostic tests with ignorable missing data
Marín Jiménez, Ana Eugenia; Roldán Nofuentes, José Antonio
In this article, a global hypothesis test is studied to simultaneously compare the likelihood ratios of multiple binary diagnostic tests when in the presence of partial disease verification the missing data mechanism is ignorable. The hypothesis test is based on the chi-squared distribution. Simulation experiments were carried out to study the type I error and the power of the global hypothesis test when comparing the likelihood ratios of two and three diagnostic tests respectively. The results obtained were applied to the diagnosis of coronary stenosis.
Wed, 06 Jul 2016 13:54:12 GMThttp://hdl.handle.net/2117/885602016-07-06T13:54:12ZMarín Jiménez, Ana EugeniaRoldán Nofuentes, José AntonioIn this article, a global hypothesis test is studied to simultaneously compare the likelihood ratios of multiple binary diagnostic tests when in the presence of partial disease verification the missing data mechanism is ignorable. The hypothesis test is based on the chi-squared distribution. Simulation experiments were carried out to study the type I error and the power of the global hypothesis test when comparing the likelihood ratios of two and three diagnostic tests respectively. The results obtained were applied to the diagnosis of coronary stenosis.Stochastic cash flows modelled by homogeneous and non-homogeneous discrete time backward semi-Markov reward processes
http://hdl.handle.net/2117/88559
Stochastic cash flows modelled by homogeneous and non-homogeneous discrete time backward semi-Markov reward processes
Gismondi, Fulvio; Janssen, Jacques; Manca, Raimondo; Volpe di Prignano, Ernesto
The main aim of this paper is to give a systematization on the stochastic cash flows evolution. The tools that are used for this purpose are discrete time semi-Markov reward processes. The paper is directed not only to semi-Markov researchers but also to a wider public, presenting a full treatment of these tools both in homogeneous and non-homogeneous environment. The main result given in the paper is the natural correspondence of the stochastic cash flows with the semi-Markov reward processes. Indeed, the semi-Markov environment gives the possibility to follow a multi-state random system in which the randomness is not only in the transition to the next state but also in the time of transition. Furthermore, rewards permit the introduction of a financial environment into the model. Considering all these properties, any stochastic cash flow can be naturally modelled by means of semi-Markov reward processes. The backward case offers the possibility of considering in a complete way the duration inside a state of the studied system and this fact can be very useful in the evaluation of insurance contracts
Wed, 06 Jul 2016 13:52:52 GMThttp://hdl.handle.net/2117/885592016-07-06T13:52:52ZGismondi, FulvioJanssen, JacquesManca, RaimondoVolpe di Prignano, ErnestoThe main aim of this paper is to give a systematization on the stochastic cash flows evolution. The tools that are used for this purpose are discrete time semi-Markov reward processes. The paper is directed not only to semi-Markov researchers but also to a wider public, presenting a full treatment of these tools both in homogeneous and non-homogeneous environment. The main result given in the paper is the natural correspondence of the stochastic cash flows with the semi-Markov reward processes. Indeed, the semi-Markov environment gives the possibility to follow a multi-state random system in which the randomness is not only in the transition to the next state but also in the time of transition. Furthermore, rewards permit the introduction of a financial environment into the model. Considering all these properties, any stochastic cash flow can be naturally modelled by means of semi-Markov reward processes. The backward case offers the possibility of considering in a complete way the duration inside a state of the studied system and this fact can be very useful in the evaluation of insurance contractsIntegrating network design and frequency setting in public transportation networks: a survey
http://hdl.handle.net/2117/88558
Integrating network design and frequency setting in public transportation networks: a survey
López-Ramos, Francisco
This work reviews the literature on models which integrate the network design and the frequency setting phases in public transportation networks. These two phases determine to a large extent the service for the passengers and the operational costs for the operator of the system. The survey puts emphasis on modelling features, i.e., objective cost components and constraints, as well as on algorithmic aspects. Finally, it provides directions for further research.
Wed, 06 Jul 2016 13:50:53 GMThttp://hdl.handle.net/2117/885582016-07-06T13:50:53ZLópez-Ramos, FranciscoThis work reviews the literature on models which integrate the network design and the frequency setting phases in public transportation networks. These two phases determine to a large extent the service for the passengers and the operational costs for the operator of the system. The survey puts emphasis on modelling features, i.e., objective cost components and constraints, as well as on algorithmic aspects. Finally, it provides directions for further research.