Estimating large correlation matrices for international migration

DOI10.1214/18-AOAS1175zbMATH Open1405.62235arXiv1605.08759OpenAlexW2963299194WikidataQ92063665 ScholiaQ92063665MaRDI QIDQ1624816FDOQ1624816

Authors: Jonathan J. Azose, Adrian E. Raftery 

Publication date: 16 November 2018

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Abstract: The United Nations is the major organization producing and regularly updating probabilistic population projections for all countries. International migration is a critical component of such projections, and between-country correlations are important for forecasts of regional aggregates. However, there are 200 countries and only 12 data points, each one corresponding to a five-year time period. Thus a $200imes200$ correlation matrix must be estimated on the basis of 12 data points. Using Pearson correlations produces many spurious correlations. We propose a maximum a posteriori estimator for the correlation matrix with an interpretable informative prior distribution. The prior serves to regularize the correlation matrix, shrinking a priori untrustworthy elements towards zero. Our estimated correlation structure improves projections of net migration for regional aggregates, producing narrower projections of migration for Africa as a whole and wider projections for Europe. A simulation study confirms that our estimator outperforms both the Pearson correlation matrix and a simple shrinkage estimator when estimating a sparse correlation matrix.

Full work available at URL: https://arxiv.org/abs/1605.08759

Recommendations

• Estimation of emigration, return migration, and transit migration between all pairs of countries
• scientific article
• Application of latent class regression model for modeling factors associated with inter-province immigrations
• Modeling approaches to the indirect estimation of migration flows: From entropy to EM

zbMATH Keywords

migrationhigh-dimensioncorrelation estimationcorrelation matricesmaximum a posteriori estimationinternational migration

Mathematics Subject Classification ID

Measures of association (correlation, canonical correlation, etc.) (62H20) Applications of statistics to social sciences (62P25)

Cites Work

• Sparse estimation of a covariance matrix
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Strictly Proper Scoring Rules, Prediction, and Estimation
• Title not available (Why is that?)
• Large Covariance Estimation by Thresholding Principal Orthogonal Complements
• Covariance regularization by thresholding
• A well-conditioned estimator for large-dimensional covariance matrices
• Nonlinear shrinkage estimation of large-dimensional covariance matrices
• Sparse inverse covariance estimation with the graphical lasso
• Regularized estimation of large covariance matrices
• Integrated Modeling of European Migration
• Accurate Approximations for Posterior Moments and Marginal Densities
• Bayesian correlation estimation
• Sparse estimation of large covariance matrices via a nested Lasso penalty
• Regularization of Wavelet Approximations
• Title not available (Why is that?)
• Simple marginally noninformative prior distributions for covariance matrices
• Operator norm consistent estimation of large-dimensional sparse covariance matrices
• Covariance and precision matrix estimation for high-dimensional time series
• Estimation with quadratic loss.
• An overview of the estimation of large covariance and precision matrices
• Sparse precision matrix estimation via lasso penalized D-trace loss
• Covariance matrix selection and estimation via penalised normal likelihood
• Covariance estimation: the GLM and regularization perspectives
• Estimation of a covariance matrix with zeros
• Analysis of Longitudinal Data With Semiparametric Estimation of Covariance Function
• Bayesian inference for a covariance matrix
• Estimation of high-dimensional prior and posterior covariance matrices in Kalman filter vari\-ants
• Stable estimation of a covariance matrix guided by nuclear norm penalties
• Sparse estimation of high-dimensional correlation matrices

Cited In (2)

• California Exodus? A network model of population redistribution in the United States
• Partial correlation graphical LASSO

Uses Software

• glasso
• spcov

This page was built for publication: Estimating large correlation matrices for international migration

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1624816)