Diego Ignacio Gallardo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Diego Ignacio Gallardo has a total of 93 co-authors. Here are the top co-authors by number of shared publications:
- Hector W. Gomez
Departamento de Estadística y Ciencia de Datos, Facultad de Ciencias Básicas, Universidad de Antofagasta, Antofagasta 1240000, Chile
37 shared publications - Marcelo Bourguignon
Department of Statistics, Federal University of Rio Grande do Norte, Natal, Brazil
24 shared publications - Osvaldo Venegas
Departamento de Ciencias Matemáticas y Físicas, Facultad de Ingeniería, Universidad Católica de Temuco, Temuco 4780000, Chile
16 shared publications - Yolanda M. Gomez
Departamento de Estadística, Facultad de Ciencias, Universidad del Bío-Bío, Concepción 4081112, Chile
16 shared publications - Tiago Maia Magalhães
Department of Statistics, Institute of Exact Sciences, Federal University of Juiz de Fora, Juiz de Fora, Brazil
10 shared publications - Karol I. Santoro
Departamento de Estadística y Ciencia de Datos, Facultad de Ciencias Básicas, Universidad de Antofagasta, Antofagasta 1240000, Chile
7 shared publications
Latest Publications
- Open Access
A Flexible Geometric Mixture Distribution for Actuarial Claim Counts
This paper introduces a new two-parameter discrete distribution obtained by mixing the geometric distribution with a particular case of the Log-Gamma distribution; equivalently, it is a geometric distribution whose success probability is driven by a gamma latent variable. The proposed model is unimodal, presents a zero vertex, and accommodates over-dispersion, which are features commonly observed in automobile insurance-claim data. For , it is shown to be more dispersed and to have more zeros than the geometric distribution with the same mean. Closed-form expressions are derived for several actuarial quantities and reliability measures, including the failure rate, mean residual life, Value at Risk (VaR), through the Lambert W function, and Tail Value at Risk (TVaR). In addition, the geometric distribution is obtained as a limiting case of the proposed model when . We study parameter estimation using a zero-proportion and mean estimator, maximum-likelihood estimation, and an ECME algorithm. The practical performance of the proposed model is illustrated through a Monte Carlo study that explicitly accounts for boundary solutions, and through three automobile insurance datasets, where it is compared with the Poisson and negative binomial distributions using asymptotic and parametric bootstrap goodness-of-fit tests. The proposed model performs as well as the negative binomial distribution in two classical datasets, whereas for a portfolio of 100,000 policies it attains the smallest AIC but, like the negative binomial model, it is rejected by the goodness-of-fit tests.Open AccessA Flexible Geometric Mixture Distribution for Actuarial Claim Counts
This paper introduces a new two-parameter discrete distribution obtained by mixing the geometric distribution with a particular case of the Log-Gamma distribution; equivalently, it is a geometric distribution whose success probability is driven by a gamma latent variable. The proposed model is unimodal, presents a zero vertex, and accommodates over-dispersion, which are features commonly observed in automobile insurance-claim data. For , it is shown to be more dispersed and to have more zeros than the geometric distribution with the same mean. Closed-form expressions are derived for several actuarial quantities and reliability measures, including the failure rate, mean residual life, Value at Risk (VaR), through the Lambert W function, and Tail Value at Risk (TVaR). In addition, the geometric distribution is obtained as a limiting case of the proposed model when . We study parameter estimation using a zero-proportion and mean estimator, maximum-likelihood estimation, and an ECME algorithm. The practical performance of the proposed model is illustrated through a Monte Carlo study that explicitly accounts for boundary solutions, and through three automobile insurance datasets, where it is compared with the Poisson and negative binomial distributions using asymptotic and parametric bootstrap goodness-of-fit tests. The proposed model performs as well as the negative binomial distribution in two classical datasets, whereas for a portfolio of 100,000 policies it attains the smallest AIC but, like the negative binomial model, it is rejected by the goodness-of-fit tests. - Open Access
Weighted Beta Regression for Modeling Bounded Data
A two-parameter weighted beta distribution is introduced for modeling bounded data, which has many similarities to the beta distribution. We propose a class of regression models where the response is weighted beta distributed and the two shape parameters that index the weighted beta distribution are related to covariates and regression parameters. The proposed regression model is a natural strong competitor of the beta regression model. We study the mathematical and statistical properties of the distribution, and we provide a useful interpretation of the parameters. The maximum likelihood method is used for estimating the model parameters. We conduct simulation studies to investigate the performance of the maximum likelihood estimators and the asymptotic confidence intervals of the parameters. We present an application of the proposed regression model to real bounded data.
Open AccessWeighted Beta Regression for Modeling Bounded Data
A two-parameter weighted beta distribution is introduced for modeling bounded data, which has many similarities to the beta distribution. We propose a class of regression models where the response is weighted beta distributed and the two shape parameters that index the weighted beta distribution are related to covariates and regression parameters. The proposed regression model is a natural strong competitor of the beta regression model. We study the mathematical and statistical properties of the distribution, and we provide a useful interpretation of the parameters. The maximum likelihood method is used for estimating the model parameters. We conduct simulation studies to investigate the performance of the maximum likelihood estimators and the asymptotic confidence intervals of the parameters. We present an application of the proposed regression model to real bounded data.
- Open Access
The Wrapped Q-Lindley Distribution: A New Circular Model with Statistical Properties, Classical and Bayesian Inference, and Applications to Directional Data
Circular data arise naturally in a wide range of scientific fields, including biology, geology, meteorology, and environmental sciences, where conventional linear statistical methods are inappropriate unless the circular structure of the observations is taken into account. Motivated by the need for parsimonious, analytically tractable models for unimodal directional data, we introduce a new one-parameter circular model, the Wrapped Q-Lindley (WQL) distribution. The proposed model is obtained by wrapping the Q-Lindley distribution and has a specific unimodal asymmetric shape. Closed-form or analytically tractable expressions are derived for several important distributional properties, including the characteristic function, trigonometric moments, circular descriptive measures, and Rényi entropy. We investigate parameter estimation using ten classical estimation methods, along with Bayesian inference, under four symmetric and asymmetric loss functions. A Monte Carlo simulation study evaluates and compares the finite-sample performance of the competing estimators. The practical usefulness of the proposed model is illustrated through two real directional datasets involving sun compass orientation measurements of starhead topminnows and wind direction observations. Comparisons with several established circular models indicate that the WQL distribution provides competitive fitting performance for the considered datasets. We discuss its parsimonious structure and analytical tractability, along with the implications of its structural discontinuity at the wrap point, in the context of directional data analysis.
Open AccessThe Wrapped Q-Lindley Distribution: A New Circular Model with Statistical Properties, Classical and Bayesian Inference, and Applications to Directional Data
Circular data arise naturally in a wide range of scientific fields, including biology, geology, meteorology, and environmental sciences, where conventional linear statistical methods are inappropriate unless the circular structure of the observations is taken into account. Motivated by the need for parsimonious, analytically tractable models for unimodal directional data, we introduce a new one-parameter circular model, the Wrapped Q-Lindley (WQL) distribution. The proposed model is obtained by wrapping the Q-Lindley distribution and has a specific unimodal asymmetric shape. Closed-form or analytically tractable expressions are derived for several important distributional properties, including the characteristic function, trigonometric moments, circular descriptive measures, and Rényi entropy. We investigate parameter estimation using ten classical estimation methods, along with Bayesian inference, under four symmetric and asymmetric loss functions. A Monte Carlo simulation study evaluates and compares the finite-sample performance of the competing estimators. The practical usefulness of the proposed model is illustrated through two real directional datasets involving sun compass orientation measurements of starhead topminnows and wind direction observations. Comparisons with several established circular models indicate that the WQL distribution provides competitive fitting performance for the considered datasets. We discuss its parsimonious structure and analytical tractability, along with the implications of its structural discontinuity at the wrap point, in the context of directional data analysis.
- Open Access
Scale Mixture of Akash Distribution with Applications to Income Data
In this paper, the scale mixture of Akash (SMAK) distribution is introduced. This new distribution results from a scale mixture of the Akash distribution and the exponential distribution. The SMAK distribution is an alternative to two-parameter distributions with a heavy right tail. We study its representation, some basic properties, and maximum likelihood inference. We carry out three applications with real data, in which the SMAK distribution exhibits better performance than other distributions.
Open AccessScale Mixture of Akash Distribution with Applications to Income Data
In this paper, the scale mixture of Akash (SMAK) distribution is introduced. This new distribution results from a scale mixture of the Akash distribution and the exponential distribution. The SMAK distribution is an alternative to two-parameter distributions with a heavy right tail. We study its representation, some basic properties, and maximum likelihood inference. We carry out three applications with real data, in which the SMAK distribution exhibits better performance than other distributions.
- 28 July 2026
- Published by Springer Nature in Statistical Papers
- Vol. 67 (5) , 101
A new frailty model based on the jørgensen–seshadri–whitmore distribution
- 28 July 2026
- Published by Springer Nature in Statistical Papers
- Vol. 67 (5) , 101
A new frailty model based on the jørgensen–seshadri–whitmore distribution
- Open Access
- 4 July 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (13) , 2395
A Heavy-Tailed QLindley Distribution for Modelling Skewed Lifetime Data
Lifetime data arising in engineering reliability, survival analysis, actuarial science, and environmental studies often exhibit substantial right-skewness, extreme observations, and heterogeneous hazard-rate structures. Classical lifetime distributions may not adequately capture these characteristics, thereby affecting risk assessment, reliability evaluation, and predictive performance. In this paper, we introduce the Heavy-Tailed QLindley (HTQL) distribution, a new two-parameter heavy-tailed extension of the QLindley model obtained through the New Family of Heavy-Tailed (NFHT) transformation. The proposed distribution provides greater flexibility for modelling positively skewed and heavy-tailed data while preserving analytical tractability. The HTQL model accommodates increasing, decreasing, bathtub-shaped, unimodal, and nearly constant hazard rate functions, making it suitable for applications in reliability analysis, survival studies, actuarial science, and environmental modelling. Several mathematical and statistical properties of the HTQL distribution are derived, including explicit expressions for the quantile function, ordinary and incomplete moments, order statistics, and reliability measures. Important tail-based risk measures such as Value-at-Risk, Tail Value-at-Risk, Tail Variance, Tail Variance Premium, and Expected Shortfall are also obtained. Parameter estimation is investigated using maximum likelihood, ordinary least squares, Cramér–von Mises, and Bayesian approaches, together with bootstrap confidence intervals. A Monte Carlo simulation study is conducted to evaluate the finite-sample performance of the proposed estimators. The practical usefulness of the HTQL distribution is illustrated using three real-world datasets from pharmacokinetics, engineering reliability, and environmental studies. The empirical results show that the HTQL distribution provides highly competitive fits compared with several classical, Lindley-type, and heavy-tailed distributions. Overall, the proposed model constitutes a flexible and parsimonious alternative for modelling positive heavy-tailed data.
- 4 July 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (13) , 2395
Open AccessA Heavy-Tailed QLindley Distribution for Modelling Skewed Lifetime Data
Lifetime data arising in engineering reliability, survival analysis, actuarial science, and environmental studies often exhibit substantial right-skewness, extreme observations, and heterogeneous hazard-rate structures. Classical lifetime distributions may not adequately capture these characteristics, thereby affecting risk assessment, reliability evaluation, and predictive performance. In this paper, we introduce the Heavy-Tailed QLindley (HTQL) distribution, a new two-parameter heavy-tailed extension of the QLindley model obtained through the New Family of Heavy-Tailed (NFHT) transformation. The proposed distribution provides greater flexibility for modelling positively skewed and heavy-tailed data while preserving analytical tractability. The HTQL model accommodates increasing, decreasing, bathtub-shaped, unimodal, and nearly constant hazard rate functions, making it suitable for applications in reliability analysis, survival studies, actuarial science, and environmental modelling. Several mathematical and statistical properties of the HTQL distribution are derived, including explicit expressions for the quantile function, ordinary and incomplete moments, order statistics, and reliability measures. Important tail-based risk measures such as Value-at-Risk, Tail Value-at-Risk, Tail Variance, Tail Variance Premium, and Expected Shortfall are also obtained. Parameter estimation is investigated using maximum likelihood, ordinary least squares, Cramér–von Mises, and Bayesian approaches, together with bootstrap confidence intervals. A Monte Carlo simulation study is conducted to evaluate the finite-sample performance of the proposed estimators. The practical usefulness of the HTQL distribution is illustrated using three real-world datasets from pharmacokinetics, engineering reliability, and environmental studies. The empirical results show that the HTQL distribution provides highly competitive fits compared with several classical, Lindley-type, and heavy-tailed distributions. Overall, the proposed model constitutes a flexible and parsimonious alternative for modelling positive heavy-tailed data.
- Open Access
- 1 April 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (7) , 1167
Preface to the Special Issue “Probability, Statistics & Symmetry”
This Special Issue of Mathematics is devoted to new survival analysis, regression, time series, and entropy analysis-based models and their applications
- 1 April 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (7) , 1167
Open AccessPreface to the Special Issue “Probability, Statistics & Symmetry”
This Special Issue of Mathematics is devoted to new survival analysis, regression, time series, and entropy analysis-based models and their applications
- 9 March 2026
- Published by The R Foundation
cdnbcr: Correlated Destructive Negative Binomial Cure Rate Model
Provides tools for modeling time-to-event data with a cure fraction under correlated destructive negative binomial cure rate models. The models assume multiple latent competing causes with possible dependence and allow for elimination (inactivation) of some initial causes. Estimation is performed via an Expectation-Maximization algorithm, and diagnostic tools based on Cox-Snell residuals are provided.
- 9 March 2026
- Published by The R Foundation
cdnbcr: Correlated Destructive Negative Binomial Cure Rate Model
Provides tools for modeling time-to-event data with a cure fraction under correlated destructive negative binomial cure rate models. The models assume multiple latent competing causes with possible dependence and allow for elimination (inactivation) of some initial causes. Estimation is performed via an Expectation-Maximization algorithm, and diagnostic tools based on Cox-Snell residuals are provided.
- Open Access
- 1 January 2026
- Published by American Institute of Mathematical Sciences (AIMS) in AIMS Mathematics
- Vol. 11 (8) , 24120-24136
On the composition of discrete distributions
In this paper, we introduced a parametric family of discrete probability distributions that had a simpler probabilistic construction than the classical Lagrangian family of distributions, obtained by composing some counting distributions with bounded support with the natural exponential family. This new family included, as a special case, the natural exponential family of distributions and consequently some of the well-known classical discrete distributions in the statistical literature, such as the Poisson, binomial, negative binomial, Hyper-Poisson, and others. A useful generalization of this family, encompassing quasi-binomial and generalized Poisson distributions, was studied. A few stochastic interpretations of these families were described. An extension of the proposed family that induced a dispersion parameter was also discussed. Finally, an extensive comparison with several standard count-data models illustrated the flexibility and competitiveness of the proposed family.
- 1 January 2026
- Published by American Institute of Mathematical Sciences (AIMS) in AIMS Mathematics
- Vol. 11 (8) , 24120-24136
Open AccessOn the composition of discrete distributions
In this paper, we introduced a parametric family of discrete probability distributions that had a simpler probabilistic construction than the classical Lagrangian family of distributions, obtained by composing some counting distributions with bounded support with the natural exponential family. This new family included, as a special case, the natural exponential family of distributions and consequently some of the well-known classical discrete distributions in the statistical literature, such as the Poisson, binomial, negative binomial, Hyper-Poisson, and others. A useful generalization of this family, encompassing quasi-binomial and generalized Poisson distributions, was studied. A few stochastic interpretations of these families were described. An extension of the proposed family that induced a dispersion parameter was also discussed. Finally, an extensive comparison with several standard count-data models illustrated the flexibility and competitiveness of the proposed family.
- Open Access
- 30 November 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (23) , 3838
Modeling PM2.5 Pollution Using a Truncated Positive Student’s-t Distribution: A Case Study in Chile
This study revisits a recently proposed member of the truncated positive family of distributions, referred to as the positively truncated Student’s-t distribution. The distribution retains the structure of the classical Student’s-t distribution while explicitly incorporating a kurtosis parameter, yielding a flexible three-parameter formulation that governs location, scale, and tail behavior. A closed-form quantile function is derived, allowing a novel reparameterization based on the pth quantile and thereby facilitating integration into quantile regression models. The analytical tractability of the quantile function also enables efficient random number generation via the inverse transform method, which supports a comprehensive simulation study demonstrating the strong performance of the proposed estimators, particularly for the degrees-of-freedom parameter. The entire methodology is implemented in the tpn package for the R software. Finally, two real-data applications involving PM2.5 measurements—one without covariates and another with covariates—highlight the model’s robustness and its ability to capture heavy-tailed behavior.
- 30 November 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (23) , 3838
Open AccessModeling PM2.5 Pollution Using a Truncated Positive Student’s-t Distribution: A Case Study in Chile
This study revisits a recently proposed member of the truncated positive family of distributions, referred to as the positively truncated Student’s-t distribution. The distribution retains the structure of the classical Student’s-t distribution while explicitly incorporating a kurtosis parameter, yielding a flexible three-parameter formulation that governs location, scale, and tail behavior. A closed-form quantile function is derived, allowing a novel reparameterization based on the pth quantile and thereby facilitating integration into quantile regression models. The analytical tractability of the quantile function also enables efficient random number generation via the inverse transform method, which supports a comprehensive simulation study demonstrating the strong performance of the proposed estimators, particularly for the degrees-of-freedom parameter. The entire methodology is implemented in the tpn package for the R software. Finally, two real-data applications involving PM2.5 measurements—one without covariates and another with covariates—highlight the model’s robustness and its ability to capture heavy-tailed behavior.