Disentangling mode-specific selection and measurement bias in social surveys

Schouten, Barry; Brakel, Jaap Van; Buelens, Bart; Laan, Jan van der; Klausch, Thomas

doi:10.1016/j.ssresearch.2013.07.005

Cited by 53 publications

(42 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These choices were left up to the country teams and thus reflect country differences in best practices as well as in terms of budgetary opportunities and constraints. There is a growing body of literature (e.g., Klausch, Hox and Schouten 2013;Schouten et al 2013) showing that the choice of survey mode influences the answering patterns of respondents, and if countries use different modes then observed country differences in answers could reflect mode differences rather than genuine country differences.…”

Section: Fieldworkmentioning

confidence: 99%

Generations and Gender Programme Wave 1 data collection

Fokkema

Kveder²,

Hiekel

et al. 2016

DemRes

View full text Add to dashboard Cite

BACKGROUNDThe Generations and Gender Survey (GGS) was developed to stimulate the study of a broad range of topics of relevance to population scientists. So far, at least one wave of the GGS has been conducted in 19 countries. If scholars want to use the GGS for comparative purposes, it is essential that there be cross-national equivalence in terms of survey implementation and representativeness. OBJECTIVESThe two main goals are (1) to describe the main features of the implementation of the GGS in participating countries, and (2) to describe and evaluate the quality of the data collection of the GGS in terms of its cross-sectional representativeness. METHODSWe use weighted and unweighted GGS data for 18 countries and compare this to country-specific information. RESULTSThe quality of sampling and fieldwork procedures of the GGS is generally good. On average, response rates in the GGS are comparable to those in other cross-national surveys. After weighting, the data are generally representative in terms of age, gender, region, and household size, but less so for marital status and educational attainment. Implications for future waves of the GGS are discussed.

show abstract

Section: Fieldworkmentioning

confidence: 99%

Generations and Gender Programme Wave 1 data collection

Fokkema

Kveder²,

Hiekel

et al. 2016

DemRes

View full text Add to dashboard Cite

show abstract

“…In the simple comparative design (Figure 1a), additional auxiliary information is needed to estimate this mean (Vannieuwenhuyze et al 2010(Vannieuwenhuyze et al , 2013. In the case study, we, therefore, applied a reinterview design called within-subject design (Figure 1b; Klausch et al 2014;Schouten et al 2013; cf. reinterview response rates in Table 1).…”

Section: Estimation Of Single-and Mixed-mode Effects Against the Smbmentioning

confidence: 99%

“…In this article, we answer these RQs for the case of the Dutch Crime Victimization Survey (CVS), a national survey conducted by Statistics Netherlands, based on a large-scale experiment with three mixed-mode designs: web, mail, and telephone followed up by F2F, reanalyzing data collected by Schouten et al (2013). We estimate TB of the modes before and after the mixed-mode follow-up (RQ1) and decompose it into SB and MB components (RQ2).…”

Section: Introductionmentioning

confidence: 99%

Evaluating Bias of Sequential Mixed-mode Designs Against Benchmark Surveys

Klausch

Schouten

Hox

2015

Sociological Methods & Research

Self Cite

View full text Add to dashboard Cite

This study evaluated three types of bias-total, measurement, and selection bias (SB)-in three sequential mixed-mode designs of the Dutch Crime Victimization Survey: telephone, mail, and web, where nonrespondents were followed up face-to-face (F2F). In the absence of true scores, all biases were estimated as mode effects against two different types of benchmarks. In the single-mode benchmark (SMB), effects were evaluated against a F2F reference survey. In an alternative analysis, a ''hybrid-mode benchmark'' (HMB) was used, where effects were evaluated against a mix of the measurements of a web survey and the SB of a F2F survey. A special reinterview design made available additional auxiliary data exploited in estimation for a range of survey variables. Depending on the SMB and HMB perspectives, a telephone, mail, or web design with a F2F follow-up (SMB) or a design involving only mail and/or web but not a F2F followup (HMB) is recommended based on the empirical findings.

show abstract

“…Although theoretically it makes sense to distinguish between measurement and selection effects in mode differences, these are harder to distinguish empirically. A small number of articles have tried to do this so far (Lugtig et al 2011;Schouten et al 2013;Vannieuwenhuyze and Loosveldt 2012;Vannieuwenhuyze, Loosveldt, and Molenberghs 2010). Usually, they do so either through a very complex survey design (e.g., Schouten et al 2013) or by using a number of assumptions (e.g., Lugtig et al 2011;Vannieuwenhuyze and Loosveldt 2012).…”

Section: Analytical Approachmentioning

confidence: 99%

The Impact of Mixing Modes on Reliability in Longitudinal Studies

Cernat

2014

Sociological Methods & Research

View full text Add to dashboard Cite

Mixed-mode designs are increasingly important in surveys, and large longitudinal studies are progressively moving to or considering such a design. In this context, our knowledge regarding the impact of mixing modes on data quality indicators in longitudinal studies is sparse. This study tries to ameliorate this situation by taking advantage of a quasi-experimental design in a longitudinal survey. Using models that estimate reliability for repeated measures, quasi-simplex models, 33 variables are analyzed by comparing a single-mode CAPI design to a sequential CATI-CAPI design. Results show no differences in reliabilities and stabilities across mixed modes either in the wave when the switch was made or in the subsequent waves. Implications and limitations are discussed.

show abstract

Disentangling mode-specific selection and measurement bias in social surveys

Cited by 53 publications

References 7 publications

Generations and Gender Programme Wave 1 data collection

Generations and Gender Programme Wave 1 data collection

Evaluating Bias of Sequential Mixed-mode Designs Against Benchmark Surveys

The Impact of Mixing Modes on Reliability in Longitudinal Studies

Contact Info

Product

Resources

About