MAPLES: A general method for the estimation of age profiles from standard demographic surveys (with an application to fertility)

In this paper we present MAPLES (Method for Age Profiles Longitudinal EStimation), a general method for the estimation of age profiles that uses standard micro-level demographic survey data. The aim is to estimate smoothed age profiles and relative risks for time-fixed and time-varying covariates. MAPLES is implemented through a data processing routine and a series of regressions using GAM (Generalized Additive Models). Although the approach has been developed to be applied for living arrangements and fertility, MAPLES may be used for any kind of life event. In fact, it can be applied to every setting in which micro-level data on transitions are available from a large-scale representative survey (e.g., Demographic and Health Surveys; Fertility and Family Surveys; Generations and Gender Surveys). MAPLES is a R software package containing a set of commands that can be easily applied and that may constitute a useful tool box for demographers and social scientists. The package is available in the CRAN library http://cran.r-project.org/web/packages/MAPLES. 1 Università di Milano. Department of Economics, Business and Statistics, Carlo F. Dondena Centre for Research on Social Dynamics. E-mail: [email protected]. 2 Università Bocconi, Carlo F. Dondena Centre for Research on Social Dynamics, Department of Decision Sciences and IGIER. E-mail: [email protected]. Impicciatore & Billari: MAPLES http://www.demographic-research.org 720