A Method Making Fewer Assumptions Gave the Most Reliable Estimates of Exposure-outcome Associations in Stratified Case-cohort Studies

Overview

Journal J Clin Epidemiol

Publisher Elsevier

Specialty Public Health

Date 2015 Jun 9

PMID 26051242

Citations 4

Authors

Edmund Jones

Michael J Sweeting

Stephen J Sharp

Simon G Thompson

Affiliations

Soon will be listed here.

Abstract

Objective: A case-cohort study is an efficient epidemiological study design for estimating exposure-outcome associations. When sampling of the subcohort is stratified, several methods of analysis are possible, but it is unclear how they compare. Our objective was to compare five analysis methods using Cox regression for this type of data, ranging from a crude model that ignores the stratification to a flexible one that allows nonproportional hazards and varying covariate effects across the strata.

Study Design And Setting: We applied the five methods to estimate the association between physical activity and incident type 2 diabetes using data from a stratified case-cohort study and also used artificial data sets to exemplify circumstances in which they can give different results.

Results: In the diabetes study, all methods except the method that ignores the stratification gave similar results for the hazard ratio associated with physical activity. In the artificial data sets, the more flexible methods were shown to be necessary when certain assumptions of the simpler models failed. The most flexible method gave reliable results for all the artificial data sets.

Conclusion: The most flexible method is computationally straightforward, and appropriate whether or not key assumptions made by the simpler models are valid.

Citing Articles

Interaction between plasma phospholipid odd-chain fatty acids and GAD65 autoantibodies on the incidence of adult-onset diabetes: the EPIC-InterAct case-cohort study.

Lampousi A, Carlsson S, Lofvenborg J, Cabrera-Castro N, Chirlaque M, Fagherazzi G Diabetologia. 2023; 66(8):1460-1471.

PMID: 37301794 PMC: 10317878. DOI: 10.1007/s00125-023-05948-x.

Interaction Between GAD65 Antibodies and Dietary Fish Intake or Plasma Phospholipid n-3 Polyunsaturated Fatty Acids on Incident Adult-Onset Diabetes: The EPIC-InterAct Study.

Lofvenborg J, Carlsson S, Andersson T, Hampe C, Koulman A, Chirlaque Lopez M Diabetes Care. 2020; 44(2):416-424.

PMID: 33303636 PMC: 7818317. DOI: 10.2337/dc20-1463.

Individual participant data meta-analysis of intervention studies with time-to-event outcomes: A review of the methodology and an applied example.

de Jong V, Moons K, Riley R, Tudur Smith C, Marson A, Eijkemans M Res Synth Methods. 2019; 11(2):148-168.

PMID: 31759339 PMC: 7079159. DOI: 10.1002/jrsm.1384.

A two-step method for variable selection in the analysis of a case-cohort study.

Newcombe P, Connolly S, Seaman S, Richardson S, Sharp S Int J Epidemiol. 2017; 47(2):597-604.

PMID: 29136145 PMC: 5913627. DOI: 10.1093/ije/dyx224.

References

Kulathinal S, Karvanen J, Saarela O, Kuulasmaa K . Case-cohort design in practice - experiences from the MORGAM Project. Epidemiol Perspect Innov. 2007; 4:15. PMC: 2216006. DOI: 10.1186/1742-5573-4-15. View

Sanderson J, Thompson S, White I, Aspelund T, Pennells L . Derivation and assessment of risk prediction models using case-cohort data. BMC Med Res Methodol. 2013; 13:113. PMC: 3848813. DOI: 10.1186/1471-2288-13-113. View

Barlow W . Robust variance estimation for the case-cohort design. Biometrics. 1994; 50(4):1064-72. View

Burgess S, White I, Resche-Rigon M, Wood A . Combining multiple imputation and meta-analysis with individual participant data. Stat Med. 2013; 32(26):4499-514. PMC: 3963448. DOI: 10.1002/sim.5844. View

Danesh J, Saracci R, Berglund G, Feskens E, Overvad K, Panico S . EPIC-Heart: the cardiovascular component of a prospective study of nutritional, lifestyle and biological factors in 520,000 middle-aged participants from 10 European countries. Eur J Epidemiol. 2007; 22(2):129-41. DOI: 10.1007/s10654-006-9096-8. View

Sharp S, Poulaliou M, Thompson S, White I, Wood A . A review of published analyses of case-cohort studies and recommendations for future reporting. PLoS One. 2014; 9(6):e101176. PMC: 4074158. DOI: 10.1371/journal.pone.0101176. View

DerSimonian R, Laird N . Meta-analysis in clinical trials. Control Clin Trials. 1986; 7(3):177-88. DOI: 10.1016/0197-2456(86)90046-2. View

Thiebaut A, Benichou J . Choice of time-scale in Cox's model analysis of epidemiologic cohort data: a simulation study. Stat Med. 2004; 23(24):3803-20. DOI: 10.1002/sim.2098. View

Bingham S, Riboli E . Diet and cancer--the European Prospective Investigation into Cancer and Nutrition. Nat Rev Cancer. 2004; 4(3):206-15. DOI: 10.1038/nrc1298. View

10.

Thompson S, Kaptoge S, White I, Wood A, Perry P, Danesh J . Statistical methods for the time-to-event analysis of individual participant data from multiple epidemiological studies. Int J Epidemiol. 2010; 39(5):1345-59. PMC: 2972437. DOI: 10.1093/ije/dyq063. View

11.

Borgan O, Langholz B, Samuelsen S, Goldstein L, Pogoda J . Exposure stratified case-cohort designs. Lifetime Data Anal. 2000; 6(1):39-58. DOI: 10.1023/a:1009661900674. View

12.

Kim R . A new comparison of nested case-control and case-cohort designs and methods. Eur J Epidemiol. 2014; 30(3):197-207. PMC: 4374014. DOI: 10.1007/s10654-014-9974-4. View

13.

Bowden J, Tierney J, Simmonds M, Copas A, Higgins J . Individual patient data meta-analysis of time-to-event outcomes: one-stage versus two-stage approaches for estimating the hazard ratio under a random effects model. Res Synth Methods. 2015; 2(3):150-62. DOI: 10.1002/jrsm.45. View

14.

Cologne J, Preston D, Imai K, Misumi M, Yoshida K, Hayashi T . Conventional case-cohort design and analysis for studies of interaction. Int J Epidemiol. 2012; 41(4):1174-86. DOI: 10.1093/ije/dys102. View

15.

Xue X, Xie X, Gunter M, Rohan T, Wassertheil-Smoller S, Ho G . Testing the proportional hazards assumption in case-cohort analysis. BMC Med Res Methodol. 2013; 13:88. PMC: 3710085. DOI: 10.1186/1471-2288-13-88. View

16.

Ganna A, Reilly M, de Faire U, Pedersen N, Magnusson P, Ingelsson E . Risk prediction measures for case-cohort and nested case-control designs: an application to cardiovascular disease. Am J Epidemiol. 2012; 175(7):715-24. PMC: 3324433. DOI: 10.1093/aje/kwr374. View

17.

Onland-Moret N, van der A D, van der Schouw Y, Buschers W, Elias S, van Gils C . Analysis of case-cohort data: a comparison of different methods. J Clin Epidemiol. 2007; 60(4):350-5. DOI: 10.1016/j.jclinepi.2006.06.022. View

18.

Langenberg C, Sharp S, Forouhi N, Franks P, Schulze M, Kerrison N . Design and cohort description of the InterAct Project: an examination of the interaction of genetic and lifestyle factors on the incidence of type 2 diabetes in the EPIC Study. Diabetologia. 2011; 54(9):2272-82. PMC: 4222062. DOI: 10.1007/s00125-011-2182-9. View

19.

Ekelund U, Palla L, Brage S, Franks P, Peters T, Balkau B . Physical activity reduces the risk of incident type 2 diabetes in general and in abdominally lean and obese men and women: the EPIC-InterAct Study. Diabetologia. 2012; 55(7):1944-52. PMC: 3369127. DOI: 10.1007/s00125-012-2532-2. View