Skip to main content
PMC home page
Environmental Health Perspectives logoLink to Environmental Health Perspectives
. 1993 Dec;101(Suppl 4):23–38. doi: 10.1289/ehp.93101s423

Principles of study design in environmental epidemiology.

H Morgenstern 1, D Thomas 1
PMCID: PMC1519688  PMID: 8206038

Abstract

This paper discusses the principles of study design and related methodologic issues in environmental epidemiology. Emphasis is given to studies aimed at evaluating causal hypotheses regarding exposures to suspected health hazards. Following background sections on the quantitative objectives and methods of population-based research, we present the major types of observational designs used in environmental epidemiology: first, the three basic designs involving the individual as the unit of analysis (i.e., cohort, cross-sectional, and case-control studies) and a brief discussion of genetic studies for assessing gene-environment interactions; second, various ecologic designs involving the group or region as the unit of analysis. Ecologic designs are given special emphasis in this paper because of our lack of resources or inability to accurately measure environmental exposures in large numbers of individuals. The paper concludes with a section highlighting current design issues in environmental epidemiology and several recommendations for future work.

Full text

PDF
23

Selected References

These references are in PubMed. This may not be the complete list of references from this article.

  1. AST D. B., SCHLESINGER E. R. The conclusion of a ten-year study of water fluoridation. Am J Public Health Nations Health. 1956 Mar;46(3):265–271. doi: 10.2105/ajph.46.3.265. [DOI] [PMC free article] [PubMed] [Google Scholar]
  2. Armenian H. K., Lilienfeld A. M. Incubation period of disease. Epidemiol Rev. 1983;5:1–15. doi: 10.1093/oxfordjournals.epirev.a036254. [DOI] [PubMed] [Google Scholar]
  3. Beral V., Chilvers C., Fraser P. On the estimation of relative risk from vital statistical data. J Epidemiol Community Health. 1979 Jun;33(2):159–162. doi: 10.1136/jech.33.2.159. [DOI] [PMC free article] [PubMed] [Google Scholar]
  4. Bland K. I., Garrison R. N., Knutson C. O. Colorectal carcinoma: overview of management techniques. Postgrad Med. 1979 Sep;66(3):106-9, 112-5. doi: 10.1080/00325481.1979.11715249. [DOI] [PubMed] [Google Scholar]
  5. Brenner H., Greenland S., Savitz D. A. The effects of nondifferential confounder misclassification in ecologic studies. Epidemiology. 1992 Sep;3(5):456–459. doi: 10.1097/00001648-199209000-00013. [DOI] [PubMed] [Google Scholar]
  6. Brenner H., Savitz D. A., Jöckel K. H., Greenland S. Effects of nondifferential exposure misclassification in ecologic studies. Am J Epidemiol. 1992 Jan 1;135(1):85–95. doi: 10.1093/oxfordjournals.aje.a116205. [DOI] [PubMed] [Google Scholar]
  7. Breslow N. E., Zhao L. P. Logistic regression for stratified case-control studies. Biometrics. 1988 Sep;44(3):891–899. [PubMed] [Google Scholar]
  8. Buck C., Donner A. The design of controlled experiments in the evaluation of non-therapeutic interventions. J Chronic Dis. 1982;35(7):531–538. doi: 10.1016/0021-9681(82)90072-8. [DOI] [PubMed] [Google Scholar]
  9. Cain K. C., Breslow N. E. Logistic regression analysis and efficient design for two-stage studies. Am J Epidemiol. 1988 Dec;128(6):1198–1206. doi: 10.1093/oxfordjournals.aje.a115074. [DOI] [PubMed] [Google Scholar]
  10. Caporaso N., Hayes R. B., Dosemeci M., Hoover R., Ayesh R., Hetzel M., Idle J. Lung cancer risk, occupational exposure, and the debrisoquine metabolic phenotype. Cancer Res. 1989 Jul 1;49(13):3675–3679. [PubMed] [Google Scholar]
  11. Catalano R., Serxner S. Time series designs of potential interest to epidemiologists. Am J Epidemiol. 1987 Oct;126(4):724–731. doi: 10.1093/oxfordjournals.aje.a114712. [DOI] [PubMed] [Google Scholar]
  12. Claus E. B., Risch N. J., Thompson W. D. Age at onset as an indicator of familial risk of breast cancer. Am J Epidemiol. 1990 Jun;131(6):961–972. doi: 10.1093/oxfordjournals.aje.a115616. [DOI] [PubMed] [Google Scholar]
  13. Connor M. J., Gillings D. An empiric study of ecological inference. Am J Public Health. 1984 Jun;74(6):555–559. doi: 10.2105/ajph.74.6.555. [DOI] [PMC free article] [PubMed] [Google Scholar]
  14. Cornfield J. Randomization by group: a formal analysis. Am J Epidemiol. 1978 Aug;108(2):100–102. doi: 10.1093/oxfordjournals.aje.a112592. [DOI] [PubMed] [Google Scholar]
  15. Crawford M. D., Gardner M. J., Morris J. N. Changes in water hardness and local death-rates. Lancet. 1971 Aug 14;2(7720):327–329. doi: 10.1016/s0140-6736(71)90055-9. [DOI] [PubMed] [Google Scholar]
  16. Darby S. C., Doll R. Fallout, radiation doses near Dounreay, and childhood leukaemia. Br Med J (Clin Res Ed) 1987 Mar 7;294(6572):603–607. doi: 10.1136/bmj.294.6572.603. [DOI] [PMC free article] [PubMed] [Google Scholar]
  17. Donner A., Birkett N., Buck C. Randomization by cluster. Sample size requirements and analysis. Am J Epidemiol. 1981 Dec;114(6):906–914. doi: 10.1093/oxfordjournals.aje.a113261. [DOI] [PubMed] [Google Scholar]
  18. Dosemeci M., Wacholder S., Lubin J. H. Does nondifferential misclassification of exposure always bias a true effect toward the null value? Am J Epidemiol. 1990 Oct;132(4):746–748. doi: 10.1093/oxfordjournals.aje.a115716. [DOI] [PubMed] [Google Scholar]
  19. Feinstein A. R. Methodologic problems and standards in case-control research. J Chronic Dis. 1979;32(1-2):35–41. doi: 10.1016/0021-9681(79)90009-2. [DOI] [PubMed] [Google Scholar]
  20. Flanders W. D., Greenland S. Analytic methods for two-stage case-control studies and other stratified designs. Stat Med. 1991 May;10(5):739–747. doi: 10.1002/sim.4780100509. [DOI] [PubMed] [Google Scholar]
  21. Greenland S. Adjustment of risk ratios in case-base studies (hybrid epidemiologic designs). Stat Med. 1986 Nov-Dec;5(6):579–584. doi: 10.1002/sim.4780050605. [DOI] [PubMed] [Google Scholar]
  22. Greenland S. Divergent biases in ecologic and individual-level studies. Stat Med. 1992 Jun 30;11(9):1209–1223. doi: 10.1002/sim.4780110907. [DOI] [PubMed] [Google Scholar]
  23. Greenland S., Morgenstern H. Classification schemes for epidemiologic research designs. J Clin Epidemiol. 1988;41(8):715–716. doi: 10.1016/0895-4356(88)90155-2. [DOI] [PubMed] [Google Scholar]
  24. Greenland S., Morgenstern H. Ecological bias, confounding, and effect modification. Int J Epidemiol. 1989 Mar;18(1):269–274. doi: 10.1093/ije/18.1.269. [DOI] [PubMed] [Google Scholar]
  25. Greenland S., Morgenstern H. Matching and efficiency in cohort studies. Am J Epidemiol. 1990 Jan;131(1):151–159. doi: 10.1093/oxfordjournals.aje.a115469. [DOI] [PubMed] [Google Scholar]
  26. Greenland S., Morgenstern H. Neither within-region nor cross-regional independence of exposure and covariates prevents ecological bias. Int J Epidemiol. 1991 Sep;20(3):816–818. doi: 10.1093/ije/20.3.816. [DOI] [PubMed] [Google Scholar]
  27. Greenland S., Neutra R. An analysis of detection bias and proposed corrections in the study of estrogens and endometrial cancer. J Chronic Dis. 1981;34(9-10):433–438. doi: 10.1016/0021-9681(81)90002-3. [DOI] [PubMed] [Google Scholar]
  28. Greenland S. Randomization, statistics, and causal inference. Epidemiology. 1990 Nov;1(6):421–429. doi: 10.1097/00001648-199011000-00003. [DOI] [PubMed] [Google Scholar]
  29. Greenland S. Response and follow-up bias in cohort studies. Am J Epidemiol. 1977 Sep;106(3):184–187. doi: 10.1093/oxfordjournals.aje.a112451. [DOI] [PubMed] [Google Scholar]
  30. Greenland S., Schlesselman J. J., Criqui M. H. The fallacy of employing standardized regression coefficients and correlations as measures of effect. Am J Epidemiol. 1986 Feb;123(2):203–208. doi: 10.1093/oxfordjournals.aje.a114229. [DOI] [PubMed] [Google Scholar]
  31. Greenland S. Statistical uncertainty due to misclassification: implications for validation substudies. J Clin Epidemiol. 1988;41(12):1167–1174. doi: 10.1016/0895-4356(88)90020-0. [DOI] [PubMed] [Google Scholar]
  32. Greenland S. The effect of misclassification in the presence of covariates. Am J Epidemiol. 1980 Oct;112(4):564–569. doi: 10.1093/oxfordjournals.aje.a113025. [DOI] [PubMed] [Google Scholar]
  33. Greenland S., Thomas D. C., Morgenstern H. The rare-disease assumption revisited. A critique of "estimators of relative risk for case-control studies". Am J Epidemiol. 1986 Dec;124(6):869–883. doi: 10.1093/oxfordjournals.aje.a114476. [DOI] [PubMed] [Google Scholar]
  34. Greenland S., Thomas D. C. On the need for the rare disease assumption in case-control studies. Am J Epidemiol. 1982 Sep;116(3):547–553. doi: 10.1093/oxfordjournals.aje.a113439. [DOI] [PubMed] [Google Scholar]
  35. Gruchow H. W., Rimm A. A., Hoffmann R. G. Alcohol consumption and ischemic heart disease mortality: are time-series correlations meaningful? Am J Epidemiol. 1983 Nov;118(5):641–650. doi: 10.1093/oxfordjournals.aje.a113675. [DOI] [PubMed] [Google Scholar]
  36. Hatch M., Susser M. Background gamma radiation and childhood cancers within ten miles of a US nuclear plant. Int J Epidemiol. 1990 Sep;19(3):546–552. doi: 10.1093/ije/19.3.546. [DOI] [PubMed] [Google Scholar]
  37. Humphreys K., Carr-Hill R. Area variations in health outcomes: artefact or ecology. Int J Epidemiol. 1991 Mar;20(1):251–258. doi: 10.1093/ije/20.1.251. [DOI] [PubMed] [Google Scholar]
  38. Khoury M. J., Beaty T. H., Flanders W. D. Epidemiologic approaches to the use of DNA markers in the search for disease susceptibility genes. Epidemiol Rev. 1990;12:41–55. doi: 10.1093/oxfordjournals.epirev.a036061. [DOI] [PubMed] [Google Scholar]
  39. Lee J. A. Melanoma and exposure to sunlight. Epidemiol Rev. 1982;4:110–136. doi: 10.1093/oxfordjournals.epirev.a036243. [DOI] [PubMed] [Google Scholar]
  40. Lee J. A., Petersen G. R., Stevens R. G., Vesanen K. The influence of age, year of birth, and date on mortality from malignant melanoma in the populations of England and Wales, Canada, and the white population of the United States. Am J Epidemiol. 1979 Dec;110(6):734–739. doi: 10.1093/oxfordjournals.aje.a112854. [DOI] [PubMed] [Google Scholar]
  41. Louis T. A., Lavori P. W., Bailar J. C., 3rd, Polansky M. Crossover and self-controlled designs in clinical research. N Engl J Med. 1984 Jan 5;310(1):24–31. doi: 10.1056/NEJM198401053100106. [DOI] [PubMed] [Google Scholar]
  42. Mack W., Langholz B., Thomas D. C. Survival models for familial aggregation of cancer. Environ Health Perspect. 1990 Jul;87:27–35. doi: 10.1289/ehp.908727. [DOI] [PMC free article] [PubMed] [Google Scholar]
  43. Mahoney M. C., LaBrie D. S., Nasca P. C., Wolfgang P. E., Burnett W. S. Population density and cancer mortality differentials in New York State, 1978-1982. Int J Epidemiol. 1990 Sep;19(3):483–490. doi: 10.1093/ije/19.3.483. [DOI] [PubMed] [Google Scholar]
  44. Mantel N. Synthetic retrospective studies and related topics. Biometrics. 1973 Sep;29(3):479–486. [PubMed] [Google Scholar]
  45. Marsh W., Center M. S. Dimethylsulfoxide, retinoic acid and 12-O-tetradecanoylphorbol-13-acetate induce a selective decrease in the phosphorylation of P150, a surface membrane phosphoprotein of HL60 cells resistant to adriamycin. Biochem Biophys Res Commun. 1986 Jul 16;138(1):9–16. doi: 10.1016/0006-291x(86)90239-1. [DOI] [PubMed] [Google Scholar]
  46. Marshall R. J. Validation study methods for estimating exposure proportions and odds ratios with misclassified data. J Clin Epidemiol. 1990;43(9):941–947. doi: 10.1016/0895-4356(90)90077-3. [DOI] [PubMed] [Google Scholar]
  47. Miettinen O. S. The "case-control" study: valid selection of subjects. J Chronic Dis. 1985;38(7):543–548. doi: 10.1016/0021-9681(85)90039-6. [DOI] [PubMed] [Google Scholar]
  48. Miettinen O. S., Wang J. D. An alternative to the proportionate mortality ratio. Am J Epidemiol. 1981 Jul;114(1):144–148. doi: 10.1093/oxfordjournals.aje.a113161. [DOI] [PubMed] [Google Scholar]
  49. Mollie A., Richardson S. Empirical Bayes estimates of cancer mortality rates using spatial models. Stat Med. 1991 Jan;10(1):95–112. doi: 10.1002/sim.4780100114. [DOI] [PubMed] [Google Scholar]
  50. Morgenstern H., Horwitz S. M., Berkman L. F. Connections between epidemiology and health services research: a review of psychosocial effects on childhood morbidity and pediatric medical care use. J Ambul Care Manage. 1986 Nov;9(4):33–45. doi: 10.1097/00004479-198611000-00006. [DOI] [PubMed] [Google Scholar]
  51. Morgenstern H., Kleinbaum D. G., Kupper L. L. Department of Epidemiology and Public Health, School of Medicine, Yale University, New Haven, CT. Int J Epidemiol. 1980 Mar;9(1):97–104. doi: 10.1093/ije/9.1.97. [DOI] [PubMed] [Google Scholar]
  52. Morgenstern H. Uses of ecologic analysis in epidemiologic research. Am J Public Health. 1982 Dec;72(12):1336–1344. doi: 10.2105/ajph.72.12.1336. [DOI] [PMC free article] [PubMed] [Google Scholar]
  53. Morgenstern H., Winn D. M. A method for determining the sampling ratio in epidemiologic studies. Stat Med. 1983 Jul-Sep;2(3):387–396. doi: 10.1002/sim.4780020311. [DOI] [PubMed] [Google Scholar]
  54. Newman S. C. Odds ratio estimation in a steady-state population. J Clin Epidemiol. 1988;41(1):59–65. doi: 10.1016/0895-4356(88)90009-1. [DOI] [PubMed] [Google Scholar]
  55. Ohno Y., Aoki K., Aoki N. A test of significance for geographic clusters of disease. Int J Epidemiol. 1979 Sep;8(3):273–280. doi: 10.1093/ije/8.3.273. [DOI] [PubMed] [Google Scholar]
  56. Polissar L. The effect of migration on comparison of disease rates in geographic studies in the United States. Am J Epidemiol. 1980 Feb;111(2):175–182. doi: 10.1093/oxfordjournals.aje.a112885. [DOI] [PubMed] [Google Scholar]
  57. Poole C. "Would" vs "should" in the definition of secondary study base. J Clin Epidemiol. 1990;43(9):1016–1020. doi: 10.1016/0895-4356(90)90091-3. [DOI] [PubMed] [Google Scholar]
  58. Richardson S., Hémon D. Ecological bias and confounding. Int J Epidemiol. 1990 Sep;19(3):764–767. doi: 10.1093/ije/19.3.764. [DOI] [PubMed] [Google Scholar]
  59. Richardson S., Stücker I., Hémon D. Comparison of relative risks obtained in ecological and individual studies: some methodological considerations. Int J Epidemiol. 1987 Mar;16(1):111–120. doi: 10.1093/ije/16.1.111. [DOI] [PubMed] [Google Scholar]
  60. Roberson P. K. Controlling for time-varying population distributions in disease clustering studies. Am J Epidemiol. 1990 Jul;132(1 Suppl):S131–S135. doi: 10.1093/oxfordjournals.aje.a115774. [DOI] [PubMed] [Google Scholar]
  61. Robins J. M., Blevins D. Analysis of proportionate mortality data using logistic regression models. Am J Epidemiol. 1987 Mar;125(3):524–535. doi: 10.1093/oxfordjournals.aje.a114559. [DOI] [PubMed] [Google Scholar]
  62. Robins J. A graphical approach to the identification and estimation of causal parameters in mortality studies with sustained exposure periods. J Chronic Dis. 1987;40 (Suppl 2):139S–161S. doi: 10.1016/s0021-9681(87)80018-8. [DOI] [PubMed] [Google Scholar]
  63. Robins J. The control of confounding by intermediate variables. Stat Med. 1989 Jun;8(6):679–701. doi: 10.1002/sim.4780080608. [DOI] [PubMed] [Google Scholar]
  64. Rosenbaum P. R., Rubin D. B. Difficulties with regression analyses of age-adjusted rates. Biometrics. 1984 Jun;40(2):437–443. [PubMed] [Google Scholar]
  65. Savitz D. A., Barón A. E. Estimating and correcting for confounder misclassification. Am J Epidemiol. 1989 May;129(5):1062–1071. doi: 10.1093/oxfordjournals.aje.a115210. [DOI] [PubMed] [Google Scholar]
  66. Spiegelman D., Gray R. Cost-efficient study designs for binary response data with Gaussian covariate measurement error. Biometrics. 1991 Sep;47(3):851–869. [PubMed] [Google Scholar]
  67. Stavraky K. M. The role of ecologic analysis in studies of the etiology of disease: a discussion with reference to large bowel cancer. J Chronic Dis. 1976 Jul;29(7):435–444. doi: 10.1016/0021-9681(76)90084-9. [DOI] [PubMed] [Google Scholar]
  68. Susser E., Susser M. Familial aggregation studies. A note on their epidemiologic properties. Am J Epidemiol. 1989 Jan;129(1):23–30. doi: 10.1093/oxfordjournals.aje.a115119. [DOI] [PubMed] [Google Scholar]
  69. Susser M., Stein Z. Third variable analysis: application to causal sequences among nutrient intake, maternal weight, birthweight, placental weight, and gestation. Stat Med. 1982 Apr-Jun;1(2):105–120. doi: 10.1002/sim.4780010203. [DOI] [PubMed] [Google Scholar]
  70. Thomas D. C. Pitfalls in the analysis of exposure-time-response relationships. J Chronic Dis. 1987;40 (Suppl 2):71S–78S. doi: 10.1016/s0021-9681(87)80010-3. [DOI] [PubMed] [Google Scholar]
  71. Thompson W. D., Kelsey J. L., Walter S. D. Cost and efficiency in the choice of matched and unmatched case-control study designs. Am J Epidemiol. 1982 Nov;116(5):840–851. doi: 10.1093/oxfordjournals.aje.a113475. [DOI] [PubMed] [Google Scholar]
  72. Walker A. M. Anamorphic analysis: sampling and estimation for covariate effects when both exposure and disease are known. Biometrics. 1982 Dec;38(4):1025–1032. [PubMed] [Google Scholar]
  73. Wallenstein S., Gould M. S., Kleinman M. Use of the scan statistic to detect time-space clustering. Am J Epidemiol. 1989 Nov;130(5):1057–1064. doi: 10.1093/oxfordjournals.aje.a115406. [DOI] [PubMed] [Google Scholar]
  74. Walter S. D., Irwig L. M. Estimation of test error rates, disease prevalence and relative risk from misclassified data: a review. J Clin Epidemiol. 1988;41(9):923–937. doi: 10.1016/0895-4356(88)90110-2. [DOI] [PubMed] [Google Scholar]
  75. Wang J. D., Miettinen O. S. The mortality odds ratio (MOR) in occupational mortality studies--selection of reference occupation(s) and reference cause(s) of death. Ann Acad Med Singapore. 1984 Apr;13(2 Suppl):312–316. [PubMed] [Google Scholar]
  76. White J. E. A two stage design for the study of the relationship between a rare exposure and a rare disease. Am J Epidemiol. 1982 Jan;115(1):119–128. doi: 10.1093/oxfordjournals.aje.a113266. [DOI] [PubMed] [Google Scholar]
  77. Zelen M. A new design for randomized clinical trials. N Engl J Med. 1979 May 31;300(22):1242–1245. doi: 10.1056/NEJM197905313002203. [DOI] [PubMed] [Google Scholar]

Articles from Environmental Health Perspectives are provided here courtesy of National Institute of Environmental Health Sciences

RESOURCES