Presentation of Volume 2, 1, 2020

José María Sarabia

DOI: https://doi.org/10.37830/SJS.2020.1.01   Nº SJS/002

• Full text

Financial and Actuarial Properties of the Beta-Pareto as a Long-Tail Distribution

Emilio Gómez-Déniz, Enrique Calderín-Ojeda

DOI: https://doi.org/10.37830/SJS.2020.1.02   Nº SJS/002

• Full text
• Abstract
  Undoubtedly, the single parameter Pareto distribution is one of the most attractive distribution in statistics; a power-law probability distribution that is found in a large number of real-world situations inside and outside the field of economics. Furthermore, it is usually used as a basis for excess of loss quotations as it gives a pretty good description of the random behaviour of large losses. In this paper, we provide properties of the Beta-Pareto distribution which can be useful in Economics,and in Financial and Actuarial fields, mainly related to the analysis of the tail of the distribution that makes it a candidate model for fitting actuarial data with extreme observations. As empirical applications two well-known data sources considered in general insurance are used to account for the suitability of the model.

The Gamma-Chen distribution: a new family of distributions with applications

Lucas David R. Reis, Gauss M. Cordeiro, Maria do Carmo S. Lima

DOI: https://doi.org/10.37830/SJS.2020.1.03   Nº SJS/002

• Full text
• Abstract

  The generalized gamma-generated family adds one shape parameter to a baseline distribution. We define the gamma-Chen and derive some of its mathematical properties. Its hazard rate may have increasing, decreasing, bathtub and unimodal shapes due to the extra parameter, which portrays a positive point of the proposed model. We perform Monte Carlo simulations to prove that the asymptotic properties of the maximum likelihood estimators hold. We show empirically that the new distribution is better than ten others known distributions using engineering-related data sets.

Towards a modular end-to-end statistical production process with mobile network data

David Salgado, Luis Sanguiao, Bogdan Oancea, Sandra Barragán, Marian Necula

DOI: https://doi.org/10.37830/SJS.2020.1.04   Nº SJS/002

• Full text
• Abstract

  Mobile network data has proved to be an outstanding data source for the production of statistics in general, and for Official Statistics, in particular. Similarly to another new digital data sources, this poses the remarkable challenge of refurbishing a new statistical production process. In the context of the European Statistical System (ESS), we substantiate the so-called ESS Reference Methodological Framework for Mobile Network Data with a first modular and evolvable proposed statistical process comprising (i) the geolocation of mobile devices, (ii) the deduplication of mobile devices, (iii) the statistical filtering to identify the target population, (iv) the aggregation into territorial units, and (v) the inference to the target population. The proposal is illustrated with synthetic data generated from a network event data simulator developed for these purposes.

Commonly used methods for measuring output quality of multisource statistics

Ton de Waal, Arnout van Delden, Sander Scholtus

DOI: https://doi.org/10.37830/SJS.2020.1.05   Nº SJS/002

• Full text
• Abstract

  Estimation of output quality based on sample surveys is well established. It accounts for the effects of sampling and non-response errors on the accuracy of an estimator. When administrative data are used or combinations of administrative data with survey data, more error types need to be taken into account. Moreover, estimators in multisource statistics can be based on different ways of combining data sources. That partly affects the methodology that is needed to estimate output quality. This paper presents results of the ESSnet project Quality of Multisource Statistics that studied methods to estimate output quality. We distinguish three main groups of methods: scoring methods, (re)sampling methods and methods based on parametric modeling. Each of those is Split into methods that can be used for both single and multisource statistics and methods that can be applied to multisource statistics only. We end the paper by discussing some of the main challenges for the near future. We argue that estimating output quality for multisource statistics is still more an art than a technique.