Correcting for non-participation bias in health surveys using record-linkage, synthetic observations and pattern mixture modelling

Gray, L., Gorman, E., White, I. R., Katikireddi, S. V., McCartney, G., Rutherford, L. and Leyland, A. H. 2020. Correcting for non-participation bias in health surveys using record-linkage, synthetic observations and pattern mixture modelling. Statistical Methods in Medical Research. 29 (4), pp. 1212-1226. https://doi.org/10.1177/0962280219854482

TitleCorrecting for non-participation bias in health surveys using record-linkage, synthetic observations and pattern mixture modelling
TypeJournal article
AuthorsGray, L., Gorman, E., White, I. R., Katikireddi, S. V., McCartney, G., Rutherford, L. and Leyland, A. H.
Abstract

Surveys are key means of obtaining policy-relevant information not available from routine sources. Bias arising from non-participation is typically handled by applying weights derived from limited socio-demographic characteristics. This approach neither captures nor adjusts for differences in health and related behaviours between participants and non-participants within categories. We addressed non-participation bias in alcohol consumption estimates using novel methodology applied to 2003 Scottish Health Survey responses record-linked to prospective administrative data. Differences were identified in socio-demographic characteristics, alcohol-related harm (hospitalisation or mortality) and all-cause mortality between survey participants and, from unlinked administrative sources, the contemporaneous general population of Scotland. These were used to infer the number of non-participants within each subgroup defined by socio-demographics and health outcomes. Synthetic observations for non-participants were then generated, missing only alcohol consumption. Weekly alcohol consumption values among synthetic non-participants were multiply imputed under missing at random and missing not at random assumptions. Relative to estimates adjusted using previously derived weights, the obtained mean weekly alcohol intake estimates were up to 59% higher among men and 16% higher among women, depending on the assumptions imposed. This work demonstrates the universal value of multiple imputation-based methodological advancement incorporating administrative health data over routine weighting procedures.

JournalStatistical Methods in Medical Research
Journal citation29 (4), pp. 1212-1226
Year2020
PublisherSage
Digital Object Identifier (DOI)https://doi.org/10.1177/0962280219854482
Web address (URL)https://journals.sagepub.com/doi/10.1177/0962280219854482
Publication dates
Published online11 Jun 2019
Published in print01 Apr 2020
FunderMRC (Medical Research Council)
LicenseCC BY 4.0

Related outputs

Causal Inference
Kameshwara, K. and Gorman, E. 2025. Forthcoming. Causal Inference . in: Thomas, M., Jules, T., Shields, R. and Schweisfurth, M. (ed.) The Bloomsbury Handbook of Method in Comparative and International Education Bloomsbury.

Ethnic differences in intergenerational housing mobility in England and Wales
Buscha, F., Gorman, E., Sturgis, P. and Zhang, M. 2023. Ethnic differences in intergenerational housing mobility in England and Wales. Journal of Social Policy. Advanced online publication. https://doi.org/10.1017/S0047279423000570

Education pathways to the labour market for 16-year-olds who struggle to achieve maths and English in General Certificate of Secondary Education
Gorman, E., Thomson, D., Urwin, P. and Zhang, M. 2023. Education pathways to the labour market for 16-year-olds who struggle to achieve maths and English in General Certificate of Secondary Education. ADRUK 2023 Conference. Swansea University. https://doi.org/10.23889/ijpds.v8i2.2306.

A national multiple baseline cohort study of mental health conditions in early adolescence and subsequent educational outcomes in New Zealand
Gorman, E., Bowden, N., Kokaua, J., McNeill, B. and Schluter, P.J. 2023. A national multiple baseline cohort study of mental health conditions in early adolescence and subsequent educational outcomes in New Zealand. Scientific Reports. 13 11025. https://doi.org/10.1038/s41598-023-38131-8

Does schooling have lasting effects on cognitive function? Evidence from compulsory schooling laws
Gorman, E. 2023. Does schooling have lasting effects on cognitive function? Evidence from compulsory schooling laws. Demography. 60 (4), pp. 1139-1161. https://doi.org/10.1215/00703370-10875853

Selective schooling and social mobility in England
Buscha, F., Gorman, E. and Sturgis, P. 2023. Selective schooling and social mobility in England. Labour Economics. 81 102336. https://doi.org/10.1016/j.labeco.2023.102336

Selective Schooling and Returns to Education
Gorman, E. 2022. Selective Schooling and Returns to Education. in: Zimmermann, K.F. (ed.) Handbook of Labor, Human Resources and Population Economics Springer.

Spatial and social mobility in England and Wales: A sub‐national analysis of differences and trends over time
Buscha, F., Gorman, Emma and Sturgis, Patrick 2021. Spatial and social mobility in England and Wales: A sub‐national analysis of differences and trends over time. The British Journal of Sociology. 72 (5), pp. 1378-1393. https://doi.org/10.1111/1468-4446.12885

Adolescent School Bullying Victimization and Later Life Outcomes
Gorman, E., Harmon, C., Mendolia, S., Staneva, A. and Walker, I. 2021. Adolescent School Bullying Victimization and Later Life Outcomes. Oxford Bulletin of Economics and Statistics. 83 (4), pp. 1048-1076. https://doi.org/10.1111/obes.12432

Heterogeneous effects of missing out on a place at a preferred secondary school in England
Gorman, Emma and Walker, Ian 2021. Heterogeneous effects of missing out on a place at a preferred secondary school in England. Economics of Education Review. 81 102082. https://doi.org/10.1016/j.econedurev.2021.102082

Assessing Factors that Affect the Labour Market Decisions of Young People aged 16 to 24: Research Informing LPC Review of Youth Rates
Bowyer, A., Cerqua, A., Di Pietro, G., Gorman, E. and Urwin, P. 2019. Assessing Factors that Affect the Labour Market Decisions of Young People aged 16 to 24: Research Informing LPC Review of Youth Rates. https://www.gov.uk/government/publications/research-on-minimum-wage-youth-rates Low Pay Commission.

Validation of non-participation bias methodology based on record-linked Finnish register-based health survey data: a protocol paper
McMinn, M. A., Martikainen, P., Gorman, E., Rissanen, H., Härkänen, T., Tolonen, H., Leyland, A. H. and Gray, L. 2019. Validation of non-participation bias methodology based on record-linked Finnish register-based health survey data: a protocol paper. BMJ Open. 9 (4), p. e026187 e026187. https://doi.org/10.1136/bmjopen-2018-026187

Adjustment for survey non‐representativeness using record‐linkage: refined estimates of alcohol consumption by deprivation in Scotland
Gorman, E., Leyland, A. H., McCartney, G., Katikireddi, S. V., Rutherford, L., Graham, L., Robinson, M. and Gray, L. 2017. Adjustment for survey non‐representativeness using record‐linkage: refined estimates of alcohol consumption by deprivation in Scotland. Addiction. 112 (7), pp. 1270-1280. https://doi.org/10.1111/add.13797

Assessing the Representativeness of Population-Sampled Health Surveys Through Linkage to Administrative Data on Alcohol-Related Outcomes
Gorman, E., Leyland, A. H., McCartney, G., White, I. R., Katikireddi, S. V., Rutherford, L., Graham, L. and Gray, L. 2014. Assessing the Representativeness of Population-Sampled Health Surveys Through Linkage to Administrative Data on Alcohol-Related Outcomes. American Journal of Epidemiology. 180 (9), pp. 941-948. https://doi.org/10.1093/aje/kwu207

Use of record-linkage to handle non-response and improve alcohol consumption estimates in health survey data: a study protocol
Gray, L., McCartney, G., White, I. R., Katikireddi, S. V., Rutherford, L., Gorman, E. and Leyland, A. H. 2013. Use of record-linkage to handle non-response and improve alcohol consumption estimates in health survey data: a study protocol . BMJ Open. 3 (3), p. BMJ Open 2013;3:e002647 e002647. https://doi.org/10.1136/bmjopen-2013-002647

Permalink - https://westminsterresearch.westminster.ac.uk/item/qv946/correcting-for-non-participation-bias-in-health-surveys-using-record-linkage-synthetic-observations-and-pattern-mixture-modelling


Share this

Usage statistics

109 total views
0 total downloads
These values cover views and downloads from WestminsterResearch and are for the period from September 2nd 2018, when this repository was created.