Premium
Explaining cross‐country differences in survey contact rates: application of decomposition methods
Author(s) -
Blom Annelies G.
Publication year - 2012
Publication title -
journal of the royal statistical society: series a (statistics in society)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.103
H-Index - 84
eISSN - 1467-985X
pISSN - 0964-1998
DOI - 10.1111/j.1467-985x.2011.01006.x
Subject(s) - cross country , survey data collection , propensity score matching , population , association (psychology) , demography , psychology , demographic economics , statistics , mathematics , economics , sociology , psychotherapist
Summary. Survey contact rates differ across countries. However, to date the reasons for these cross‐country differences have not been identified. Differences can be due to differences in survey characteristics, differences in population characteristics and differences in processes, i.e. in the association between the first and second reasons and contact propensity. The paper investigates correlates of contact by decomposing cross‐country differences in predicted mean contact propensities into these three components. The findings explain which fieldwork strategies and population characteristics are related to cross‐country differences in contact rates. The analyses distinguish factors explaining within‐country contact propensity from factors explaining cross‐country differences. We demonstrate the suitability of decomposition methods for analysing group differences in survey outcomes.