Multiple-bias modelling for analysis of observational data

Journal of the Royal Statistical Society. Series A: Statistics in Society

Volumn 168, Issue 2, 2005, Pages 267-306

  Greenland, Sander ^a   Copas, John ^b   Jones, David R ^c   Spiegelhalter, David ^d   Rice, Kenneth ^d   Armstrong, Ben ^e   Senn, Stephen ^f   Carpenter, James ^e   Kenward, Mike ^e   De Stavola, Bianca ^e   Nitsch, Dorothea ^e   Nitsch, D ^e   Muirhead, Colin R ^g   Hodges, Jim ^h   Longford, N T ⁱ   Gelman, Andrew ^j   Draper, David ^k   Gustafson, Paul ^l   McCandless, Lawrence ^l   Rubin, Donald B ^m  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b UNIVERSITY OF WARWICK   (United Kingdom)

^c UNIVERSITY OF LEICESTER   (United Kingdom)

^d MRC BIOSTATISTICS UNIT   (United Kingdom)

^e LONDON SCHOOL OF HYGIENE AND TROPICAL MEDICINE   (United Kingdom)

^f UNIVERSITY OF GLASGOW   (United Kingdom)

^g PUBLIC HEALTH ENGLAND   (United Kingdom)

^h UNIVERSITY OF MINNESOTA   (United States)

ⁱ SNTL   (United Kingdom)

^j Och Spine at New York Presbyterian Hospitals   (United States)

^k UNIVERSITY OF CALIFORNIA   (United States)

^l UNIVERSITY OF BRITISH COLUMBIA   (Canada)

^m HARVARD UNIVERSITY   (United States)

more..

Author keywords

Bayesian statistics; Confidence profile method; Confounding; Epidemiologic methods; Leukaemia; Magnetic fields; Meta analysis; Meta statistics; Monte Carlo methods; Observational data; Odds ratio; Relative risk; Risk analysis; Risk assessment; Sensitivity analysis

Indexed keywords

EID: 20144383829     PISSN: 09641998     EISSN: None     Source Type: Journal    
DOI: 10.1111/j.1467-985X.2004.00349.x     Document Type: Article

References (131)

1. Angrist, J., Imbens, G. and Rubin, D. B. (1996) Identification of causal effects using instrumental variables (with discussion). J. Am. Statist. Ass., 91, 444-472.
2. Bishop, Y. M. M., Fienberg, S. E. and Holland, P. W. (1975) Discrete Multivariate Analysis: Theory and Practice. Cambridge: Massachusetts Institute of Technology Press.
3. Bracken, M. B., Belanger, K., Hellebrand, K., Adesso, K., Patel, S., Trich, E. and Leaderer, B. (1998) Correlates of residential wiring configurations. Am. J. Epidem., 148, 467-474.
4. Brain, J. D., Kavet, R., McCormick, D. L., Poole, C., Silverman, L. B., Smith, T. J., Valberg, P. A., Van Etten, R. A. and Weaver, J. C. (2003) Childhood leukemia: electric and magnetic fields as possible risk factors. Environ. Hlth Perspect., 111, 962-970.
5. Breslow, N. E. (1981) Odds ratio estimators when the data are sparse. Biometrika, 68, 73-84.
6. Coghill, R. W., Steward, J. and Philips, A. (1996) Extra low frequency electric and magnetic fields in the bedplace of children diagnosed with leukemia: a case-control study. Eur. J. Cancer Prevn, 5, 153-158.
7. Copas, J. B. (1999) What works?: selectivity models and meta-analysis. J. R. Statist. Soc. A, 162, 95-109.
8. Copas, J. B. and Li, H. G. (1997) Inference for non-random samples (with discussion). J. R. Statist. Soc. B, 59, 55-95.
9. Cornfield, J., Haenszel, W., Hammond, W. C., Lilienfeld, A. M., Shimkin, M. B. and Wynder, E. L. (1959) Smoking and lung cancer: recent evidence and a discussion of some questions. J. Natn. Cancer Inst., 22, 173-203.
10. Crouch, A. C., Lester, R. R., Lash, T. L., Armstrong, S. R. and Green, L. C. (1997) Health risk assessment prepared per the risk assessment reforms under consideration in the U.S. Congress. Hum. Ecol. Risk Assessmnt, 3, 713-785.
11. Dockerty, J. D., Elwood, J. M., Skegg, D. C. G. and Herbison, G. P. (1998) Electromagnetic field exposures and childhood cancers in New Zealand. Cancer Causes Contr., 9, 299-309; erratum 10 (1999), 641.
12. Draper, D., Saltelli, A., Tarantola, S. and Prado, P. (2000) Scenario and parametric sensitivity and uncertainty analyses in nuclear waste disposal risk assessment: the case of GESAMAC. In Mathematical and Statistical Methods for Sensitivity Analysis (eds A. Saltelli, K. Chan and M. Scott), ch. 13, pp. 275-292. New York: Wiley.
13. Eddy, D. M., Hasselblad, V. and Schachter, R. (1992) Meta-analysis by the Confidence Profile Method. New York: Academic Press.
14. Efron, B. and Tibshirani, R. (1993) An Introduction to the Bootstrap. New York: Chapman and Hall.
15. Electric Power Research Institute (2003) Selection bias in epidemiologic studies of EMF and childhood leukemia. EPRI Report 1008149. World Health Organization, Geneva.
16. Feychting, M. and Ahlbom, A. (1993) Magnetic fields and cancer in children residing near Swedish high-voltage power lines. Am. J. Epidem., 138, 467-481.
17. Flegal, K. M., Keyl, P. M. and Nieto, F. J. (1991) Differential misclassification arising from nondifferential errors in exposure measurement. Am. J. Epidem., 134, 1233-1244.
18. Frangakis, C. and Rubin, D. B. (2002) Principal stratification in causal inference. Biometrics, 58, 21-29.
19. Gelman, A., Carlin, J. B., Stern, H. S. and Rubin, D. B. (2003). Bayesian Data Analysis, 2nd edn. New York: Chapman and Hall-CRC.
20. Good, I. J. (1983) Good Thinking. Minneapolis: University of Minnesota Press.
21. Graham, P. (2000) Bayesian inference for a generalized population attributable fraction. Statist. Med., 19, 937-956.
22. Green, L. M., Miller, A. B., Villeneuve, P. J., Agnew, D. A., Greenberg, M. L., Li, J. and Donnelly, K. E. (1999) A case-control study of childhood leukemia in southern Ontario, Canada, and exposure to magnetic fields in residences. Int. J. Cancer, 82, 161-170.
23. Greenland, S. (1996) Basic methods for sensitivity analysis of bias. Int. J. Epidem., 25, 1107-1116.
24. Greenland, S. (1998) The sensitivity of a sensitivity analysis. Proc. Biometr. Sect. Am. Statist. Ass., 19-21.
25. Greenland, S. (2001a) Sensitivity analysis, Monte-Carlo risk analysis, and Bayesian uncertainty assessment. Risk Anal., 21, 579-583.
26. Greenland, S. (2001b) Putting background information about relative risks into conjugate priors. Biometrics, 57, 663-670.
27. Greenland, S. (2003a) The impact of prior distributions for uncontrolled confounding and response bias: a case study of the relation of wire codes and magnetic fields to childhood leukemia. J. Am. Statist. Ass., 98, 47-54.
28. Greenland, S. (2003b) Generalized conjugate priors for Bayesian analysis of risk and survival regressions. Biometrics, 59, 92-99.
29. Greenland, S. (2004a) Interval estimation by simulation as an alternative to and extension of confidence intervals. Int. J. Epidem., 33, 1389-1397.
30. Greenland, S. (2004b) Smoothing epidemiologic data. In Encyclopedia of Biostatistics, 2nd edn (eds P. Armitage and T. Colton). New York: Wiley.
31. Greenland, S., Pearl, J. and Robins, J. M. (1999) Causal diagrams for epidemiologic research. Epidemiology, 10, 37-48.
32. Greenland, S. and Robins, J. M. (1985) Confounding and misclassification. Am. J. Epidem., 122, 495-506.
33. Greenland, S., Schwartzbaum, J. A. and Finkle, W. D. (2000) Problems from small samples and sparse data in conditional logistic regression analysis. Am. J. Epidem., 151, 531-539.
34. Greenland, S., Sheppard, A. R., Kaune, W. T., Poole, C. and Kelsh, M. A. (2000) A pooled analysis of magnetic fields, wire codes, and childhood leukemia. Epidemiology, 11, 624-634.
35. Gustafson, P. (2003) Measurement Error and Misclassification in Statistics and Epidemiology. New York: Chapman and Hall.
36. Hatch, E. E., Kleinerman, R. A., Linet, M. S., Tarone, R. E., Kaune, W. T., Auvinen, A., Baris, D., Robison, L. L. and Wacholder, S. (2000) Do confounding or selection factors of residential wire codes and magnetic fields distort findings of electromagnetic fields studies? Epidemiology, 11, 189-198.
37. Jurek, A. M., Maldonado, G., Greenland, S. and Church, T. R. (2004) Exposure-measurement error is frequently ignored when interpreting epidemiologic study results (abstract). Am. J. Epidem., 159, S72.
38. Kabuto, M. (2003) A study on environmental EMF and children's health: final report of a grant-in-aid for scientific research project, 1999-2001 (in Japanese). Report. Japanese Ministry of Education, Culture, Sports, Science and Technology, Tokyo.
39. Kavet, R. and Zaffanella, L. E. (2002) Contact voltage measured in residences: implications for the association between magnetic fields and childhood leukemia. Bioelectromagnetics, 23, 464-474.
40. Langholz, B. (2001) Factors that explain the power line configuration wiring code-childhood leukemia association: what would they look like (with discussion)? Bioelectromagn. Suppl., 5, S19-S31.
41. Lash, T. L. and Fink, A. K. (2003) Semi-automated sensitivity analysis to assess systematic errors in observational epidemiologic data. Epidemiology, 14, 451-458.
42. Lash, T. L. and Silliman, R. A. (2000) A sensitivity analysis to separate bias due to confounding from bias due to predicting misclassification by a variable that does both. Epidemiology, 11, 544-549.
43. Learner, E. E. (1974) False models and post-data model construction. J. Am. Statist. Ass., 69, 122-131.
44. Learner, E. E. (1978) Specification Searches. New York: Wiley.
45. Linet, M. S., Hatch, E. E., Kleinermann, R. A., Robison, L. C., Kaune, W. T., Friedman, D. R., Severson, R. K., Hainer, C. M., Hartsoak, C. T., Niwa, S., Wacholder, S. and Tarone, R. E. (1997) Residential exposure to magnetic fields and acute lymphoblastic leukemia in children. New Engl. J. Med., 337, 1-7.
46. Little, R. J. A. and Rubin, D. A. (2002) Statistical Analysis with Missing Data, 2nd edn. New York: Wiley.
47. London, S. J., Thomas, D. C., Bowman, J. D., Sobel, E., Cheng, T.-C. and Peters, J. M. (1991) Exposure to residential electric and magnetic fields and risk of childhood leukemia. Am. J. Epidem., 134, 923-937.
48. Maclure, M. and Greenland, S. (1992) Tests for trend and dose-response: misinterpretations and alternatives. Am. J. Epidem., 135, 96-104.
49. Maclure, M. and Schneeweiss, S. (2001) Causation of bias: the episcope. Epidemiology, 12, 114-122.
50. McBride, M. L., Gallagher, R. P., Theriault, H. G., Armstrong, B. G., Tamaro, S., Spinelli, J. J., Deadman, J. E., Fincham, S., Robson, D. and Choi, W. (1999) Power-frequency electric and magnetic fields and risk of childhood cancer. Am. J. Epidem., 149, 831-842.
51. Michaelis, J., Schüz, J., Meinert, R., Semann, E., Grigat, J. P., Kaatsch, P., Kaletsh, U., Miesner, A., Brinkmann, K., Kalkner, W. and Kärner, H. (1998) Combined risk estimates for two German population-based case-control studies on residential magnetic fields and childhood leukemia. Epidemiology, 9, 92-94.
52. Morgan, M. G. and Henrion, M. (1990) Uncertainty. New York: Cambridge University Press.
53. Mosteller, F. and Tukey, J. W. (1977) Data Analysis and Regression. New York: Addison-Wesley.
54. Olsen, J. H., Nielsen, A. and Schulgen, G. (1993) Residence near high voltage facilities and risk of cancer in children. Br. Med. J., 307, 891-895.
55. Pearl, J. (2000) Causality. New York: Cambridge University Press.
56. Phillips, C. V. (2001) The economics of "more research is needed". Int. J. Epidem., 30, 771-776.
57. Phillips, C. V. (2003) Quantifying and reporting uncertainty from systematic errors. Epidemiology, 14, 459-466.
58. Poole, C. and Greenland, S. (1997) How a court accepted a possible explanation. Am. Statistn, 51, 112-114.
59. Powell, M., Ebel, E. and Schlossel, W. (2001) Considering uncertainty in comparing the burden of illness due to foodborne microbial pathogens. Int. J. Food Microbiol, 69, 209-215.
60. Robins, J. M., Rotnitzky, A. and Scharfstein, D. O. (1999) Sensitivity analysis for selection bias and unmeasured confounding in missing data and causal inference models. In Statistical Models in Epidemiology (eds M. E. Halloran and D. A. Berry), pp. 1-92. New York: Springer.
61. Rosenbaum, P. (2002) Observational Studies, 2nd edn. New York: Springer.
62. Rothman, K. J. (1986) Modern Epidemiology. Boston: Little, Brown.
63. Rothman, K. J. and Greenland, S. (1998) Modern Epidemiology, 2nd edn. Philadelphia: Lippincott.
64. Rubin, D. B. (1983) A case study of the robustness of Bayesian methods of inference. In Scientific Inference, Data Analysis, and Robustness (eds G. E. P. Box, T. Leonard and C. F. Wu), pp. 213-244. New York: Academic Press.
65. Savitz, D. A., Wachtel, H., Barnes, F. A., John, E. M. and Tvrdik, J. G. (1988) Case-control study of childhood cancer and exposure to 60-Hz magnetic fields. Am. J. Epidem., 128, 21-38.
66. Schüz, J., Grigat, J. P., Brinkmann, K. and Michaelis, J. (2001) Residential magnetic fields as a risk factor for acute childhood leukemia: results from a German population-based case-control study. Int. J. Cancer, 91, 728-735.
67. Steenland, K. and Greenland, S. (2004) Monte-Carlo sensitivity analysis and Bayesian analysis of smoking as an unmeasured confounder in a study of silica and lung cancer. Am. J. Epidem., 160, 384-392.
68. Stigler, S. M. (1986) The History of Statistics. London: Belknap.
69. Tomenius, L. (1986) 50-Hz electromagnetic environment and the incidence of childhood tumors in Stockholm County. Bioelectromagnetics, 7, 191-207.
70. Tynes, T. and Haldorsen, T. (1997) Electromagnetic fields and cancer in children residing near Norwegian high-voltage power lines. Am. J. Epidem., 145, 219-226.
71. UK Childhood Cancer Study Investigators (1999) Exposure to power-frequency magnetic fields and the risk of childhood cancer. Lancet, 354, 1925-1931.
72. Verkasalo, P. K., Pukkala, E., Hongisto, M. Y., Valjus, J. E., Järvinen, P. J., Heikkilä, K. K. and Koskenvuo, M. (1993) Risk of cancer in Finnish children living close to power lines. Br. Med. J., 307, 895-899.
73. Vose, D. (2000) Risk Analysis. New York: Wiley.
74. Wacholder, S., Armstrong, B. and Hartge, P. (1993) Validation studies using an alloyed gold standard. Am. J. Epidem., 137, 1251-1258.
75. Yanagawa, T. (1984) Case-control studies: assessing the effect of a confounding factor. Biometrika, 71, 191-194.
76. Abayomi, K., Gelman, A. and Levy, M. (2004) Diagnostics for multivariate imputations. Technical Report. Department of Statistics, Columbia University, New York.
77. Advisory Group on Non-ionising Radiation (2001) ELF electromagnetic fields and the risk of cancer. Document NRPB 12(1). National Radiological Protection Board, Chilton. (Available from http://www.nrpb.org/publications/ documents of nrpb/abstracts/absd12-1.htm.)
78. Berkson, J. (1946) Limitations of the application of fourfold tables to hospital data. Biometr. Bull., 2, 47-53.
79. Box, G. E. P. (1976) Science and statistics. J. Am. Statist Ass., 71, 791-799.
80. Box, G. E. P. and Tiao, G. C. (1973) Bayesian Inference in Statistical Analysis. Reading: Addison-Wesley.
81. Breiman, L. (2001) Statistical modeling: the two cultures (with discussion). Statist. Sci., 16, 199-231.
82. Claxton, K. (1999) Bayesian approaches to the value of information: implications for the regulation of new pharmaceuticals. Hlth Econ., 8, 269-274.
83. Cochran, W. G. (1953) Sampling Techniques, 1st edn. New York: Wiley.
84. Cole, S. R., Chu, H. and Greenland, S. (2005) A simulation study of multiple-imputation for measurement error correction. Am. J. Epidem., to be published.
85. Copas, J. and Eguchi, S. (2001) Local sensitivity approximations for selectivity bias. J. R. Statist. Soc. B, 63, 871-895.
86. Copas, J. B. and Jackson, D. (2004) A bound for publication bias based on the fraction of unpublished studies. Biometrics, 60, 146-153.
87. Crystal, D. and Crystal, B. (2002) Shakespeare's Words. London: Penguin.
88. Davey Smith, G. and Ebrahim, S. (2003) 'Mendelian randomization': can genetic epidemiology contribute to understanding environmental determinants of disease? Int. J. Epidem., 32, 1-22.
89. Dendukuri, N., Rahme, E., Belisle, P. and Joseph, L. (2004) Bayesian sample size determination for prevalence and diagnostic test studies in the absence of a gold standard test. Biometrics, 60, 388-397.
90. Draper, D. (1995) Inference and hierarchical modeling in the social sciences (with discussion). J. Educ. Behav. Statist., 20, 115-147, 233-239.
91. Eddy, D. M., Hasselblad, V. and Shachter, R. (1992) Meta-analysis by the Confidence Profile Method. Boston: Academic Press.
92. Flegal, K. M., Keyl, P. M. and Nieto, F. J. (1991) Differential misclassification arising from nondifferential errors in exposure measurement. Am. J. Epidem., 134, 1233-1244.
93. Fox, M. P., Lash, T. L. and Greenland, S. (2005) A SAS macro to automate probabilistic sensitivity analyses of misclassified binary variables.
94. Good, I. J. (1950) Probability and the Weighing of Evidence. London: Griffin.
95. Good, I. J. (1983) Good Thinking. Minneapolis: University of Minnesota Press.
96. Greenland, S. (2001) Sensitivity analysis, Monte-Carlo risk analysis, and Bayesian uncertainty assessment. Risk Anal., 21, 579-583.
97. Greenland, S., Pearl, J. and Robins, J. M. (1999) Causal diagrams for epidemiologic research. Epidemiology, 10, 37-48.
98. Gustafson, P. (2003) Measurement Error and Misclassification in Statistics and Epidemiology. New York: Chapman and Hall.
99. Gustafson, P. (2005) On model expansion, model contraction, identifiability, and prior information: two illustrative scenarios involving mismeasured data (with discussion). Statist. Sci., to be published.
100. Heckman, J. (1979) Sample selection bias as a specification error. Econometrica, 47, 153-161.
101. Heitjan, D. F. and Rubin, D. B. (1991) Ignorability and coarse data. Ann. Statist., 19, 2244-2253.
102. Holland, P. (1989) Discussion of "Fisher scoring algorithm for variance component analysis of data with multilevel structure," by Longford NT. In Multilevel Analysis of Educational Data (ed. R. D. Block), pp. 311-317. San Diego: Academic Press.
103. Lawlor, D. A., Davey Smith, G., Bruckdorfer, K. R., Kundu, D. and Ebrahim, S. (2004a) Those confounded vitamins: what can we learn from the differences between observational versus randomized trial evidence? Lancet, 363, 1724-1727.
104. Lawlor, D. A., Davey Smith, G. and Ebrahim, S. (2004b) The hormone replacement-coronary heart disease conundrum: is this the death of observational epidemiology? Int. J. Epidem., 33, 464-467.
105. Leonhardt, D. (2001) Adding art to the rigor of statistical science. The New York Times, Apr. 28th. (Available from www.nytimes.com.)
106. Longford, N. T. (2001) Synthetic estimators with moderating influence: the carry-over in cross-over trials revisited. Statist. Med., 20, 3189-3203.
107. Manski, C. F. (1990) Nonparametric bounds on treatment effects. Am. Econ. Rev. Pap., 80, 319-323.
108. Matthews, R. A. J. (2001) Methods for assessing the credibility of clinical trial outcomes. Drug Inform. J., 35, 1469-1478.
109. McCandless, L. (2004) Assessing sensitivity to unmeasured confounding in observational studies - a Bayesian approach. MSc Thesis. Department of Statistics, University of British Columbia, Vancouver.
110. Molenberghs, G., Kenward, M. G. and Goetghebeur, E. (2001) Sensitivity analysis for incomplete contingency tables: the Slovenian plebiscite case. Appl. Statist., 50, 15-29.
111. Mosteller, F. and Wallace, D. (1954) Inference and Disputed Authorship: the Federalist. Reading: Addison-Wesley.
112. Pauline, C. D., Scares, P. and Neuhaus, J. (2003) Binomial regression with misclassification. Biometrics, 59, 670-675.
113. Petitti, D. B. (2004) Hormone replacement therapy and coronary heart disease: four lessons. Int. J. Epidem., 33, 461-463.
114. Peto, R., Doll, R., Buckley, J. D. and Sporn, M. B. (1981) Can dietary beta-carotene materially reduce human cancer rates? Nature, 290, 201-208.
115. Pocock, S. J. and Spiegelhalter, D. J. (1992) Domiciliary thrombolysis by general practitioners. Br. Med. J., 305, 1015.
116. Raab, G. M. and Donnelly, C. A. (1999) Information on sexual behaviour when some data are missing. Appl. Statist., 48, 117-133.
117. Rahme, E., Joseph, L. and Gyorkos, T. W. (2000) Bayesian sample size determination for estimating binomial parameters from data subject to misclassification. Appl. Statist., 49, 119-128.
118. Rice, K. M. (2003) Full-likelihood techniques for misclassification of exposure in matched case control studies. Statist. Med, 22, 3177-3194.
119. Rice, K. M. (2004) Equivalence between conditional and mixture approaches to the Rasch model and matched case-control studies, with applications. J. Am. Statist. Ass., 99, 510-522.
120. Robins, J. M. and Wang, N. S. (2000) Inference for imputation estimators. Biometrika, 87, 113-124.
121. Rothman, K. J. and Greenland, S. (1998) Modern Epidemiology, 2nd edn. Philadelphia: Lippincott.
122. Rubin, D. B. (1976) Inference and missing data. Biometrika, 63, 581-592.
123. Rubin, D. B. (1977) Formalizing subjective notions about the effect of nonrespondents in sample surveys. J. Am. Statist. Ass., 72, 538-543.
124. Rubin, D. B. (1978) Bayesian inference for causal effects: the role of randomization. Ann. Statist., 6, 34-58.
125. Senn, S. J. (2000) Consensus and controversy in pharmaceutical statistics (with discussion). Statistician, 49, 135-176.
126. Smith, A. F. M. and Gelfand, A. E. (1992) Bayesian statistics without tears: a sampling-resampling perspective. Am. Statistn, 46, 84-88.
127. Smith, T. C., Spiegelhalter, D. J. and Thomas, A. (1995) Bayesian approaches to random-effect meta-analysis: a comparative study. Statist. Med., 14, 2685-2699.
128. Spiegelhalter, D. J., Freedman, L. S. and Parmar, M. K. B. (1994) Bayesian approaches to randomized trials (with discussion). J. R. Statist. Soc. A, 157, 357-416.
129. Stampfer, M. J. and Colditz, G. A. (1991) Estrogen replacement therapy and coronary heart disease: a quantitative assessment of the epidemiologic evidence. Prev. Med., 20, 47-63.
130. Verzilli, C. and Carpenter, J. R. (2002) Estimating uncertainty in parameter estimates with incomplete data: an application to repeated ordinal measurements. Technical Report. Medical Statistics Unit, London School of Hygiene and Tropical Medicine, London. (Available from www.missingdata.org.uk.)
131. White, I., Carpenter, J., Evans, S. and Schroter, S. (2004) Eliciting and using expert opinions about non-response bias in randomised controlled trials. Submitted to Clin. Trials. (Available from www.missingdata.org.uk.)