Volume 32 - Article 33 | Pages 915–948 Author has provided data and code for replicating results

Smoothing internal migration age profiles for comparative research

By Aude Bernard, Martin Bell

Print this page  Facebook  Twitter

 

 
Date received:11 Jun 2013
Date published:12 May 2015
Word count:6169
Keywords:cross-national comparison, cubic spline, kernel regression, migration age profile, model migration schedule, smoothing
DOI:10.4054/DemRes.2015.32.33
Additional files:readme.32-33 (text file, 1 kB)
 demographic-research.32-33 (zip file, 229 kB)
 

Abstract

Background: Age patterns are a key dimension to compare migration between countries and over time. Comparative metrics can be reliably computed only if data capture the underlying age distribution of migration. Model schedules, the prevailing smoothing method, fit a composite exponential function, but are sensitive to function selection and initial parameter setting. Although non-parametric alternatives exist, their performance is yet to be established.

Objective: We compare cubic splines and kernel regressions against model schedules by assessing which method provides an accurate representation of the age profile and best performs on metrics for comparing aggregate age patterns.

Methods: We use full population microdata for Chile to perform 1,000 Monte-Carlo simulations for nine sample sizes and two spatial scales. We use residual and graphic analysis to assess model performance on the age and intensity at which migration peaks and the evolution of migration age patterns.

Results: Model schedules generate a better fit when (1) the expected distribution of the age profile is known a priori, (2) the pre-determined shape of the model schedule adequately describes the true age distribution, and (3) the component curves and initial parameter values can be correctly set. When any of these conditions is not met, kernel regressions and cubic splines offer more reliable alternatives.

Conclusions: Smoothing models should be selected according to research aims, age profile characteristics, and sample size. Kernel regressions and cubic splines enable a precise representation of aggregate migration age profiles for most sample sizes, without requiring parameter setting or imposing a pre-determined distribution, and therefore facilitate objective comparison.

Author's Affiliation

Aude Bernard - University of Queensland, Australia [Email]
Martin Bell - University of Queensland, Australia [Email]

Other articles by the same author/authors in Demographic Research

» Australia's uncertain demographic future
Volume 11 - Article 8

Most recent similar articles in Demographic Research

» How kinship systems and welfare regimes shape leaving home: A comparative study of the United States, Germany, Taiwan, and China
Volume 36 - Article 38    | Keywords: cross-national comparison

» Family migration in a cross-national perspective: The importance of institutional and cultural context
Volume 36 - Article 10    | Keywords: cross-national comparison

» Insight on 'typical' longevity: An analysis of the modal lifespan by leading causes of death in Canada
Volume 35 - Article 17    | Keywords: smoothing

» The Contextual Database of the Generations and Gender Programme: Concept, content, and research examples
Volume 35 - Article 9    | Keywords: cross-national comparison

» Cumulative risks of paternal and maternal incarceration in Denmark and the United States
Volume 32 - Article 57    | Keywords: cross-national comparison

Articles

»Volume 32

 

Citations

 

 

Similar Articles

 

 

Jump to Article

Volume Page
Volume Article ID