6533b85afe1ef96bd12b89c1

RESEARCH PRODUCT

Selecciin De Sub-Muestras De Gran Tamaao De La Mcvl Representativas De Las Prestaciones Del Sistema PPblico De Pensiones (Selection of High Size Sub-Samples from the Continuous Sample of Working Lives (CSWL) Representative of the Benefits Provided by the Spanish Public Pension System)

Marta Regúlez-castilloCarlos Vidal-meliáJuan Manuel Pérez-salamero González

subject

education.field_of_studyWorking lifemedia_common.quotation_subjectPublic pensionPopulationArteducationHumanitiesCartographymedia_common

description

Spanish Abstract: La Muestra Continua de Vidas Laborales (MCVL) es un conjunto de microdatos individuales anonimizados extraidos de los registros de la Seguridad Social de Espana. Es una fuente muy valiosa de informacion utilizada en numerosos estudios sobre Economia laboral y sobre el sistema publico de pensiones espanol. Este articulo presenta dos importantes aportaciones. Por un lado se analiza la representatividad de la MCVL respecto de la poblacion de pensionistas para el periodo 2005-2013. Se concluye que no es representativa en determinados tipos de prestaciones y esto ocurre en casi la totalidad de los anos considerados. Una de las razones es que la MCVL se obtiene mediante un muestreo aleatorio simple (MAS), por lo que el ajuste a la poblacion por edad, genero y tipo de pension es peor que el que se hubiera obtenido mediante un muestreo aleatorio estratificado (MAE) con afijacion proporcional. Una solucion seria obtener una sub-muestra por MAE de la MCVL. En este trabajo se ilustra que de esta forma se renuncia a un gran numero de registros de pensiones, lo que disminuye la diversidad de vidas laborales y de historiales de prestaciones. En consecuencia, una segunda aportacion es la de aplicar una metodologia basada en la optimizacion para elegir submuestras de gran tamano extraidas de la MCVL que mejoren la representatividad respecto a la poblacion de pensionistas. La mejora en la representatividad de la submuestra obtenida se constata comparando la estimacion del gasto total en pensiones proporcionada por la MCVL y la de dichas submuestras.English Abstract: Continuous Sample of Working Lives (CSWL) is a set of anonymized micro data with information about individuals taken from Spanish Social Security records. It provides very valuable information used in many studies on Labor Economics and in the analysis of the Spanish public pension system. This article presents two major contributions. The first one is the analysis of the MCVL representativeness of the population of pensioners for the period 2005-2013. It is concluded that the CSWL does not follow the same distribution as the population with respect to some types of benefits and this happens in most of the waves. One of the reasons is that it is obtained by a Simple Random Sampling, so that adjustment to the population by age, gender and type of pension is worse than what might have been achieved using Stratified Random Sampling (MAE) with proportional allocation. As a possible solution, researchers could obtain a sub-sample by MAE from CSWL, in this article we illustrate that this implies giving up a large number of pension records, which reduces the diversity of working life and typology of pensioners. Hence, a second contribution of this paper is the application of a novel methodology based on optimization for choosing large sub-samples drawn from CSWL that are more representative of the population of pensioners. The gains from using this sample design procedure is found by comparing the estimate of total pension expenditure provided by the CSWL and such sub-samples.

https://doi.org/10.2139/ssrn.2611022