A detailed database of sub-annual Spanish demographic statistics: 2005-2021.

The big data revolution has made it possible to collect, transmit and exploit huge amounts of data. The potential this offer for data analysis, however, clashes with the limitations imposed by laws on protection of personal data. This paper details a new database (DEMOSPA0521) made after processing and summarising more than 868 million demographic records from Spain, corresponding to a period of seventeen years (2005-2021). DEMOSPA0521 is composed of fifteen files: a group of (monthly and daily moving averages) datasets derived from population stocks and a collection of (daily, monthly and quarterly) datasets obtained from population, death, migration and birth statistics. The intra-annual distributions were calculated by exploiting both the temporal dimensions of age and calendar. DEMOSPA0521 also includes eleven R-Code files that enables the summary datasets to be derived from the raw microdata. DEMOSPA0521 can be used to confirm established results and employed to answer new research questions.

Dataset of an actual life-risk insurance portfolio.

The foundation of the insurance business is built on data, the latter being one of the most valuable assets of any insurer. In fact, the risk structure to which an insurance company is exposed can actually be deduced by reviewing its customer database. It is not surprising, therefore, that access to real insurance datasets is very limited. This paper introduces and describes a dataset corresponding to a cross-section extraction of a real life-risk insurance portfolio. The dataset contains information on 76,102 policies and a total of 15 variables, including the capital at risk, the genders and dates of birth of the insured, and the effective and renewal dates of their policies. This dataset can be used both in teaching and in research. Combined with external life tables, the data available in the dataset can be used to build and compare pricing systems, to evaluate marketing strategies, in portfolio analysis, for calculations required by Solvency II regulations or for market benchmarking analysis. For example, the data from this dataset have been used in Pavía and Lledó [1] to compare the classic pricing methodology based on annual life tables with a new pricing methodology based on life tables with less than annual periodicity Pavía and Lledó [2], specifically quarterly, and in Lledó et al. to demonstrate the impact that using a new methodology to manage catastrophic risks in life insurance would have in terms of solvency capital requirements.

Dataset of the COVID-19 post-lockdown survey conducted by GIPEyOP in Spain.

2020 was a year marked by COVID-19, an infectious disease caused by the SARS-CoV-2 virus. Since the official beginning of the pandemic (March 2020), the authorities in Spain have been imposing significant restrictions (mainly on mobility) to stop the spread of the disease. In October 2020, the research group GIPEyOP (Elections and Public Opinion Research Group from the University of Valencia) conducted a survey to analyse whether the Spanish population has maintained or modified their habits and customs once the strict measures imposed in Spain during the onset of the pandemic were relaxed. This article describes the dataset collected, which is provided as an attachment. The dataset is made up of 196 variables, following elimination of those variables that could potentially identify the respondents to ensure their anonymity. Over 22 days, from September 23 to October 14, 2020, GIPEyOP collected 1755 valid responses. Respondents were contacted by chain or snowball sampling via email and social media and answered a self-administered web questionnaire consisting of 40 questions. amongst other uses, the resulting dataset can be (re)used to analyse whether the period of home confinement that Spaniards experienced between March and June 2020 has caused them to change their habits and customs, such as how often they do sport or go to bars or restaurants. The data also permit the study of whether there have been changes in the distribution of household chores by comparing three clearly differentiated moments (before confinement, during confinement and after confinement), what type of work (telework or face-to-face) the respondents would prefer or to know how the management of the crisis by govern authorities impacted on their votes preferences.

Dataset of the COVID-19 lockdown survey conducted by GIPEyOP in Spain.

This article introduces a dataset that captures relevant information about the living conditions, feelings, and habits of residents in Spain during ninety nine days of home confinement. This and other measures, imposed by the Government of Spain to mitigate the impact of the pandemic on the population, have brought with them important economic, labor, and social changes, which have been accompanied by various modifications (some only temporary) in Spaniards habits and behaviours. Data collection was carried out through the implementation of a questionnaire with 33 questions, which was sent by email to the collaborators of GIPEyOP (Elections and Public Opinion Research Group from the University of Valencia). These collaborators, in turn, forwarded the questionnaire to their acquaintances using email and social networks, mainly WhatsApp, Facebook, and Twitter. This non-probabilistic methodology has generated a total of 8387 valid responses. The resulting dataset may be (re)used by sociologists, political scientists, economists, or psychologists, among others, to identify how household chores were distributed among family members during the lockdown, what impact the confinement had on the labor performance of workers, the extent of teleworking and on some (physical and psychological) health issues linked to the confinement, including relationships with the place of residence during confinement. The data also provides information on how social networks spread geographically or what Spaniards thought of the management of the crisis by local, national, and international authorities.

Spanish electoral archive. SEA database.

This paper introduces the SEA database (acronym for Spanish Electoral Archive). SEA brings together the most complete public repository available to date on Spanish election outcomes. SEA holds all the results recorded from the electoral processes of General (1979-2019), Regional (1989-2021), Local (1979-2019) and European Parliamentary (1987-2019) elections held in Spain since the restoration of democracy in the late 70 s, in addition to other data sets with electoral content. The data are offered for free and is presented in a homogeneous and friendly format. Most of the databases are available for download with data from various electoral levels, including from the ballot box level. This paper details how the information is organized, what the main variables are on offer for each election, which processes were applied to the data for their homogenization, and discusses future areas of work. This data has many applications, for example, as inputs in election prediction models and in ecological inference algorithms, to study determinants of turnout or voting, or for defining marketing strategies.

Elasticity as a measure for online determination of remission points in ongoing epidemics.

The correct identification of change-points during ongoing outbreak investigations of infectious diseases is a matter of paramount importance in epidemiology, with major implications for the management of health care resources, public health and, as the COVID-19 pandemic has shown, social live. Onsets, peaks, and inflexion points are some of them. An onset is the moment when the epidemic starts. A "peak" indicates a moment at which the incorporated values, both before and after, are lower: a maximum. The inflexion points identify moments in which the rate of growth of the incorporation of new cases changes intensity. In this study, after interpreting the concept of elasticity of a random variable in an innovative way, we propose using it as a new simpler tool for anticipating epidemic remission change-points. In particular, we propose that the "remission point of change" will occur just at the instant when the speed in the accumulation of new cases is lower than the average speed of accumulation of cases up to that moment. This gives stability and robustness to the estimation in the event of possible remission variations. This descriptive measure, which is very easy to calculate and interpret, is revealed as informative and adequate, has the advantage of being distribution-free and can be estimated in real time, while the data is being collected. We use the 2014-2016 Western Africa Ebola virus epidemic to demonstrate this new approach. A couple of examples analyzing COVID-19 data are also included.

El punto de remisión de una epidemia localizado por su elasticidad: aplicación a la primera ola del COVID-19 en Chile / The remission point of an epidemic identified by elasticity. application to the first wave of covid-19 in Chile

INTRODUCCIÓN. La detección de cambios en las características de un proceso aleatorio, conocido como el problema del cambio, se ha convertido en un área de investigación estadística en rápido desarrollo. La correcta y rápida detección de los cambios es relevante en muchas situaciones reales, en particular, en Epidemiología. MATERIALES Y MÉTODOS. Como nueva métrica para determinar el momento efectivo de remisión de una epidemia (momento del cambio), se utiliza el concepto de elasticidad de una distribución de probabilidad, y se aplica a la reciente pandemia COVID-19 en Chile. RESULTADOS. La aplicación evidencia que existe una demora entre el día "pico" o día con el mayor número de casos, con el de "remisión" identificado por la elasticidad. En ese lapso temporal, entre pico y remisión, no deben suavizarse las medidas de control de la epidemia. Se obtiene una diferencia de 20 días entre los puntos de remisión de las series de contagios y muertes. Esta cifra puede interpretarse como una estimación de la supervivencia para los fallecidos durante la primera ola de COVID-19 una vez detectada en ellos la enfermedad. La comparación de los resultados de la aplicación con la de otros países sudamericanos muestra en ellos idéntico resultado que el observado en Chile, si bien con tiempos de demora entre pico y punto de remisión sensiblemente mayores. DISCUSIÓN. La medida usada en este trabajo es fácil de comunicar, no exige la formulación previa de hipótesis sobre el comportamiento de los datos y puede ser aplicada en tiempo real, tal y como se van conociendo los datos. Estas características de fácil aplicabilidad e interpretación, generando resultados razonables, la hacen atractiva e interesante para el estudio del cambio en series epidemiológicas.

INTRODUCTION. Detecting changes in the evolution of a random process, known as the problem of change, has become a quickly developing area of statistical research. The correct and rapid detection of changes is relevant in many real-life situations, particularly in epidemiology.MATERIALS AND METHODS. As a new metric to time-locate the moment of remission of an epidemic (moment of change), the concept of the elasticity of a probability distribution is applied to the recent COVID-19 pandemic in Chile.RESULTS. The application shows that there is a delay between the "peak" day, or day with the highest number of cases, and the "remission" day as identified by elasticity. In this period, between peak and remission, the epidemic control measures should not be relaxed. A difference of 20 days is obtained between the remission points of the series of infections and deaths. This figure can be interpreted as an estimate of survival time for those diagnosed with the disease who subsequently died during the first wave of COVID-19. Comparing the results of the application with that of other South American countries, we observe the same result as that attained for Chile, although with significantly longer delay times between the peak and the point of remission.DISCUSSION. The measure used in this study is easy to communicate, does not require the prior formulation of hypotheses about the behaviour of the data and can be applied in real time, as and when the data is known. These characteristics of easy applicability and interpretation, generating reasonable results, make the application convenient for the study of change in epidemiological series

Lent impact on the seasonality of conceptions during the twentieth century in Spain.

In European past populations, religious canons shaped the seasonal distribution of marriages and births by means of banning weddings and sexual intercourse during important holidays within the religious calendar. In contemporary secularized societies, this seasonal modeling has disappeared. A few pieces of evidence have been gathered to explain how they have disappeared. This paper analyzes the impact of Lent on the seasonality of conceptions during the last century in Spain. Data births of the entire Spanish population born in Spain and alive on the first of January 2003 (more than 39 million) containing the date, size of the municipality (six groups) are used. To analyze this seasonality, we have used time-series techniques. We have built an ad hoc temporal regressor starting from the number of days of Lent that corresponds to each month. We have also used regression models with autoregressive and moving average errors (regARIMA models) to estimate, by maximum likelihood, the set of model parameters. The paper gathers new evidences about the importance of religion on the preproduction of Spanish population until very recently. They show that during the twentieth century, in Spain, there were a significant decrease in conceptions during Lent and a significant rebound after this period. We note that this previous effect disappeared in 1975-1980, when both democracy and the contraception revolution began in Spain. After this period, the seasonality of birth in general disappears.

Data from the GIPEyOP online election poll for the 2015 Spanish General election.

The general elections of 2015 in Spain took place in the middle of the Great Recession after several years of austerity economic policies. This election caused a political earthquake that shook the Spanish party system. During the campaign of that election, GIPEyOP (Elections and Public Opinion Research Group from University of Valencia) conducted a survey to collect relevant data about the electorate beliefs, intentions and motivations. This article describes the data set attained, which comprises 71 variables after removing, to ensure full anonymity, those variables that would potentially allow respondents to be identified. Respondents answered a self-administered online questionnaire and were recruited using chain sampling. A total of 14,261 valid observations were collected between 27th November and 18th December 2015. GIPEyOP employed the data collected up to 14th December to deliver a prediction of the election outcomes during that election campaign. Among other issues, this data set may be reused to assess theories of expectations' formation, to spot how social networks spread geographically and to measure gender, age and education technological gap of the Spanish population.

Assessing uncertainty of voter transitions estimated from aggregated data. Application to the 2017 French presidential election.

Inferring electoral individual behaviour from aggregated data is a very active research area, with ramifications in sociology and political science. A new approach based on linear programming is proposed to estimate voter transitions among parties (or candidates) between two elections. Compared to other linear and quadratic programming models previously published, our approach presents two important innovations. Firstly, it explicitly deals with new entries and exits in the election census without assuming unrealistic hypotheses, enabling a reasonable estimation of vote behaviour of young electors voting for the first time. Secondly, by exploiting the information contained in the model residuals, we develop a procedure to assess the uncertainty in the estimates. This significantly distinguishes our model from other published mathematical programming methods. The method is illustrated estimating the vote transfer matrix between the first and second rounds of the 2017 French presidential election and measuring its level of uncertainty. Likewise, compared to the most current alternatives based on ecological regression, our approach is considerably simpler and faster, and has provided reasonable results in all the actual elections to which it has been applied. Interested scholars can easily use our procedure with the aid of the R-function provided in the Supplemental Material.

Combining Benford's Law and machine learning to detect money laundering. An actual Spanish court case.

OBJECTIVES: This paper is based on the analysis of the database of operations from a macro-case on money laundering orchestrated between a core company and a group of its suppliers, 26 of which had already been identified by the police as fraudulent companies. In the face of a well-founded suspicion that more companies have perpetrated criminal acts and in order to make better use of what are very limited police resources, we aim to construct a tool to detect money laundering criminals. METHODS: We combine Benford's Law and machine learning algorithms (logistic regression, decision trees, neural networks, and random forests) to find patterns of money laundering criminals in the context of a real Spanish court case. RESULTS: After mapping each supplier's set of accounting data into a 21-dimensional space using Benford's Law and applying machine learning algorithms, additional companies that could merit further scrutiny are flagged up. CONCLUSIONS: A new tool to detect money laundering criminals is proposed in this paper. The tool is tested in the context of a real case.