The Use of Weights to Account for Non-response and Drop-out

Overview

Journal Soc Psychiatry Psychiatr Epidemiol

Specialties Psychiatry
Public Health
Social Sciences

Date 2005 Apr 19

PMID 15834780

Citations 58

Authors

Michael Hofler

Hildegard Pfister

Roselind Lieb

Hans-Ulrich Wittchen

Affiliations

Soon will be listed here.

Abstract

Background: Empirical studies in psychiatric research and other fields often show substantially high refusal and drop-out rates. Non-participation and drop-out may introduce a bias whose magnitude depends on how strongly its determinants are related to the respective parameter of interest.

Methods: When most information is missing, the standard approach is to estimate each respondent's probability of participating and assign each respondent a weight that is inversely proportional to this probability. This paper contains a review of the major ideas and principles regarding the computation of statistical weights and the analysis of weighted data.

Results: A short software review for weighted data is provided and the use of statistical weights is illustrated through data from the EDSP (Early Developmental Stages of Psychopathology) Study. The results show that disregarding different sampling and response probabilities can have a major impact on estimated odds ratios.

Conclusions: The benefit of using statistical weights in reducing sampling bias should be balanced against increased variances in the weighted parameter estimates.

Citing Articles

Exploring the causal paths and longitudinal impact of telework on health: the TeleHealth survey-data linkage study protocol.

Bracho Montes de Oca E, Int Panis L, Verbrugghe M, De Waegeneer E, Cagnie B, de Geus B BMJ Open. 2025; 15(2):e096105.

PMID: 39900421 PMC: 11795372. DOI: 10.1136/bmjopen-2024-096105.

Socioeconomic Inequity in Access to Medical and Long-Term Care Among Older People.

Okamoto S, Yamada A, Kobayashi E, Liang J Int J Equity Health. 2025; 24(1):28.

PMID: 39849500 PMC: 11756124. DOI: 10.1186/s12939-024-02345-7.

Progression of nutritional impact symptoms in cancer patients undergoing radiotherapy.

de Oliveira Hinokuma A, de Andrade P, Hofelmann D Support Care Cancer. 2025; 33(2):108.

PMID: 39820523 DOI: 10.1007/s00520-025-09172-8.

Improving our understanding of the social determinants of mental health: a data linkage study of mental health records and the 2011 UK census.

Cybulski L, Chilman N, Jewell A, Dewey M, Hildersley R, Morgan C BMJ Open. 2024; 14(1):e073582.

PMID: 38286672 PMC: 10826590. DOI: 10.1136/bmjopen-2023-073582.

Arsenic Exposure and Epigenetic Aging: The Association with Cardiovascular Disease and All-Cause Mortality in the Strong Heart Study.

Jiang E, Domingo-Relloso A, Abuawad A, Haack K, Tellez-Plaza M, Fallin M Environ Health Perspect. 2023; 131(12):127016.

PMID: 38133959 PMC: 10743589. DOI: 10.1289/EHP11981.

References

Troxel A, Lipsitz S, Brennan T . Weighted estimating equations with nonignorably missing response data. Biometrics. 1997; 53(3):857-69. View

Lieb R, Isensee B, von Sydow K, Wittchen H . The Early Developmental Stages of Psychopathology Study (EDSP): a methodological update. Eur Addict Res. 2000; 6(4):170-82. DOI: 10.1159/000052043. View

Wittchen H, Perkonigg A, Lachner G, Nelson C . Early developmental stages of psychopathology study (EDSP): objectives and design. Eur Addict Res. 1998; 4(1-2):18-27. DOI: 10.1159/000018921. View

Wittchen H, Nelson C, Lachner G . Prevalence of mental disorders and psychosocial impairments in adolescents and young adults. Psychol Med. 1998; 28(1):109-26. DOI: 10.1017/s0033291797005928. View

Touloumi G, Pocock S, Babiker A, Darbyshire J . Impact of missing data due to selective dropouts in cohort studies and clinical trials. Epidemiology. 2002; 13(3):347-55. DOI: 10.1097/00001648-200205000-00017. View

Kessler R, Little R, Groves R . Advances in strategies for minimizing and adjusting for survey nonresponse. Epidemiol Rev. 1995; 17(1):192-204. DOI: 10.1093/oxfordjournals.epirev.a036176. View

Heyting A, Tolboom J, Essers J . Statistical handling of drop-outs in longitudinal clinical trials. Stat Med. 1992; 11(16):2043-61. DOI: 10.1002/sim.4780111603. View

Little R, Lewitzky S, Heeringa S, Lepkowski J, Kessler R . Assessment of weighting methodology for the National Comorbidity Survey. Am J Epidemiol. 1997; 146(5):439-49. DOI: 10.1093/oxfordjournals.aje.a009297. View

Rotnitzky A, Robins J . Analysis of semi-parametric regression models with non-ignorable non-response. Stat Med. 1997; 16(1-3):81-102. DOI: 10.1002/(sici)1097-0258(19970115)16:1<81::aid-sim473>3.0.co;2-0. View

10.

Greenland S . Response and follow-up bias in cohort studies. Am J Epidemiol. 1977; 106(3):184-7. DOI: 10.1093/oxfordjournals.aje.a112451. View

11.

Kessler R, McGonagle K, Zhao S, Nelson C, Hughes M, Eshleman S . Lifetime and 12-month prevalence of DSM-III-R psychiatric disorders in the United States. Results from the National Comorbidity Survey. Arch Gen Psychiatry. 1994; 51(1):8-19. DOI: 10.1001/archpsyc.1994.03950010008002. View

12.

Rubin D, Schenker N . Multiple imputation in health-care databases: an overview and some applications. Stat Med. 1991; 10(4):585-98. DOI: 10.1002/sim.4780100410. View

13.

Jacobi F, Wittchen H, Holting C, Sommer S, Lieb R, Hofler M . Estimating the prevalence of mental and somatic disorders in the community: aims and methods of the German National Health Interview and Examination Survey. Int J Methods Psychiatr Res. 2002; 11(1):1-18. PMC: 6878553. DOI: 10.1002/mpr.118. View

14.

Allehoff W, Esser G, Schmidt M, Hennicke K . [The significance of information and cooperation denial for the interpretation range of a multi-stage child psychiatric-epidemiologic study]. Soc Psychiatry. 1983; 18(1):29-36. DOI: 10.1007/BF00583385. View

15.

Carpenter J, Bithell J . Bootstrap confidence intervals: when, which, what? A practical guide for medical statisticians. Stat Med. 2000; 19(9):1141-64. DOI: 10.1002/(sici)1097-0258(20000515)19:9<1141::aid-sim479>3.0.co;2-f. View