Home > Research > Publications & Outputs > Adjustment for survey non-representativeness us...

Research

Associated organisational unit

Links

Text available via DOI:

Keywords

View graph of relations

Adjustment for survey non-representativeness using record-linkage: refined estimates of alcohol consumption by deprivation in Scotland

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Adjustment for survey non-representativeness using record-linkage: refined estimates of alcohol consumption by deprivation in Scotland. / Gorman, Emma; Leyland, Alastair H.; McCartney, Gerry et al.
In: Addiction, Vol. 112, No. 7, 07.2017, p. 1270-1280.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Gorman, E, Leyland, AH, McCartney, G, Katikireddi, SV, Rutherford, L, Graham, L, Robinson, M & Gray, L 2017, 'Adjustment for survey non-representativeness using record-linkage: refined estimates of alcohol consumption by deprivation in Scotland', Addiction, vol. 112, no. 7, pp. 1270-1280. https://doi.org/10.1111/add.13797

APA

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

Vancouver

Gorman E, Leyland AH, McCartney G, Katikireddi SV, Rutherford L, Graham L et al. Adjustment for survey non-representativeness using record-linkage: refined estimates of alcohol consumption by deprivation in Scotland. Addiction. 2017 Jul;112(7):1270-1280. Epub 2017 Apr 25. doi: 10.1111/add.13797

Author

Gorman, Emma ; Leyland, Alastair H. ; McCartney, Gerry et al. / Adjustment for survey non-representativeness using record-linkage: refined estimates of alcohol consumption by deprivation in Scotland. In: Addiction. 2017 ; Vol. 112, No. 7. pp. 1270-1280.

Bibtex

@article{953f260ba3654e5d9b51272d5bb3e5cf,
title = "Adjustment for survey non-representativeness using record-linkage:: refined estimates of alcohol consumption by deprivation in Scotland",
abstract = "Background and aims: Analytical approaches to addressing survey non-participation bias typically use only demographic information to improve estimates. We applied a novel methodology which uses health information from data linkage to adjust for non-representativeness. We illustrate the method by presenting adjusted alcohol consumption estimates for Scotland.Design: Data on consenting respondents to the Scottish Health Surveys (SHeSs) 1995-2010 were linked confidentially to routinely collected hospital admission and mortality records. Synthetic observations representing non-respondents were created using general population data. Multiple imputation was performed to compute adjusted alcohol estimates given a range of assumptions about the missing data. Adjusted estimates of mean weekly consumption were additionally calibrated to per-capita alcohol sales data.Setting: Scotland.Participants: 13 936 male and 18 021 female respondents to the SHeSs 1995-2010, aged 20-64years.Measurements: Weekly alcohol consumption, non-, binge- and problem-drinking.Findings: Initial adjustment for non-response resulted in estimates of mean weekly consumption that were elevated by up to 17.8% [26.5units (18.6-34.4)] compared with corrections based solely on socio-demographic data [22.5 (17.7-27.3)]; other drinking behaviour estimates were little changed. Under more extreme assumptions the overall difference was up to 53%, and calibrating to sales estimates resulted in up to 88% difference. Increases were especially pronounced among males in deprived areas.Conclusions: The use of routinely collected health data to reduce bias arising from survey non-response resulted in higher alcohol consumption estimates among working-age males in Scotland, with less impact for females. This new method of bias reduction can be generalized to other surveys to improve estimates of alternative harmful behaviours.",
keywords = "Alcohol consumption, alcohol-related harm, bias, epidemiology, health surveys, non-participation, record-linkage, Scotland, POPULATION-BASED HEALTH, NONRESPONSE BIAS, FOLLOW-UP, CAGE QUESTIONNAIRE, SALES DATA, MORTALITY, POLICY, PARTICIPANTS, COHORT, UNIT",
author = "Emma Gorman and Leyland, {Alastair H.} and Gerry McCartney and Katikireddi, {Srinivasa Vittal} and Lisa Rutherford and Lesley Graham and Mark Robinson and Linsay Gray",
year = "2017",
month = jul,
doi = "10.1111/add.13797",
language = "English",
volume = "112",
pages = "1270--1280",
journal = "Addiction",
issn = "0965-2140",
publisher = "Wiley",
number = "7",

}

RIS

TY - JOUR

T1 - Adjustment for survey non-representativeness using record-linkage:

T2 - refined estimates of alcohol consumption by deprivation in Scotland

AU - Gorman, Emma

AU - Leyland, Alastair H.

AU - McCartney, Gerry

AU - Katikireddi, Srinivasa Vittal

AU - Rutherford, Lisa

AU - Graham, Lesley

AU - Robinson, Mark

AU - Gray, Linsay

PY - 2017/7

Y1 - 2017/7

N2 - Background and aims: Analytical approaches to addressing survey non-participation bias typically use only demographic information to improve estimates. We applied a novel methodology which uses health information from data linkage to adjust for non-representativeness. We illustrate the method by presenting adjusted alcohol consumption estimates for Scotland.Design: Data on consenting respondents to the Scottish Health Surveys (SHeSs) 1995-2010 were linked confidentially to routinely collected hospital admission and mortality records. Synthetic observations representing non-respondents were created using general population data. Multiple imputation was performed to compute adjusted alcohol estimates given a range of assumptions about the missing data. Adjusted estimates of mean weekly consumption were additionally calibrated to per-capita alcohol sales data.Setting: Scotland.Participants: 13 936 male and 18 021 female respondents to the SHeSs 1995-2010, aged 20-64years.Measurements: Weekly alcohol consumption, non-, binge- and problem-drinking.Findings: Initial adjustment for non-response resulted in estimates of mean weekly consumption that were elevated by up to 17.8% [26.5units (18.6-34.4)] compared with corrections based solely on socio-demographic data [22.5 (17.7-27.3)]; other drinking behaviour estimates were little changed. Under more extreme assumptions the overall difference was up to 53%, and calibrating to sales estimates resulted in up to 88% difference. Increases were especially pronounced among males in deprived areas.Conclusions: The use of routinely collected health data to reduce bias arising from survey non-response resulted in higher alcohol consumption estimates among working-age males in Scotland, with less impact for females. This new method of bias reduction can be generalized to other surveys to improve estimates of alternative harmful behaviours.

AB - Background and aims: Analytical approaches to addressing survey non-participation bias typically use only demographic information to improve estimates. We applied a novel methodology which uses health information from data linkage to adjust for non-representativeness. We illustrate the method by presenting adjusted alcohol consumption estimates for Scotland.Design: Data on consenting respondents to the Scottish Health Surveys (SHeSs) 1995-2010 were linked confidentially to routinely collected hospital admission and mortality records. Synthetic observations representing non-respondents were created using general population data. Multiple imputation was performed to compute adjusted alcohol estimates given a range of assumptions about the missing data. Adjusted estimates of mean weekly consumption were additionally calibrated to per-capita alcohol sales data.Setting: Scotland.Participants: 13 936 male and 18 021 female respondents to the SHeSs 1995-2010, aged 20-64years.Measurements: Weekly alcohol consumption, non-, binge- and problem-drinking.Findings: Initial adjustment for non-response resulted in estimates of mean weekly consumption that were elevated by up to 17.8% [26.5units (18.6-34.4)] compared with corrections based solely on socio-demographic data [22.5 (17.7-27.3)]; other drinking behaviour estimates were little changed. Under more extreme assumptions the overall difference was up to 53%, and calibrating to sales estimates resulted in up to 88% difference. Increases were especially pronounced among males in deprived areas.Conclusions: The use of routinely collected health data to reduce bias arising from survey non-response resulted in higher alcohol consumption estimates among working-age males in Scotland, with less impact for females. This new method of bias reduction can be generalized to other surveys to improve estimates of alternative harmful behaviours.

KW - Alcohol consumption

KW - alcohol-related harm

KW - bias

KW - epidemiology

KW - health surveys

KW - non-participation

KW - record-linkage

KW - Scotland

KW - POPULATION-BASED HEALTH

KW - NONRESPONSE BIAS

KW - FOLLOW-UP

KW - CAGE QUESTIONNAIRE

KW - SALES DATA

KW - MORTALITY

KW - POLICY

KW - PARTICIPANTS

KW - COHORT

KW - UNIT

U2 - 10.1111/add.13797

DO - 10.1111/add.13797

M3 - Journal article

VL - 112

SP - 1270

EP - 1280

JO - Addiction

JF - Addiction

SN - 0965-2140

IS - 7

ER -