Bayesian models as a unified approach to estimate relative risk (or prevalence ratio) in binary and polytomous outcomes

Emerging Themes in Epidemiology

Suzi Alves Camey¹  Vanessa Bielefeldt Leotti Torman¹ 

[1] Post-Graduate Program in Epidemiology, Federal University of Rio Grande do Sul (UFRGS), Porto Alegre, RS, Brazil

关键词: Polytomous outcomes;    Dependent data;    Common outcomes;    Prevalence ratio;    Relative risk;    Bayesian models;   

Others  :  1214018
DOI  :  10.1186/s12982-015-0030-y

 received in 2015-01-07, accepted in 2015-06-15,  发布年份 2015

【 摘 要 】

Background

Disadvantages have already been pointed out on the use of odds ratio (OR) as a measure of association for designs such as cohort and cross sectional studies, for which relative risk (RR) or prevalence ratio (PR) are preferable. The model that directly estimates RR or PR and correctly specifies the distribution of the outcome as binomial is the log-binomial model, however, convergence problems occur very often. Robust Poisson regression also estimates these measures but it can produce probabilities greater than 1.

Results

In this paper, the use of Bayesian approach to solve the problem of convergence of the log-binomial model is illustrated. Furthermore, the method is extended to incorporate dependent data, as in cluster clinical trials and studies with multilevel design, and also to analyse polytomous outcomes. Comparisons between methods are made by analysing four data sets.

Conclusions

In all cases analysed, it was observed that Bayesian methods are capable of estimating the measures of interest, always within the correct parametric space of probabilities.

【 授权许可】

   
2015 Torman and Camey.

【 图 表 】

Fig. 1.

Fig. 2.

【 参考文献 】

• [1]Greenland S. Interpretation and choice of effect measures in epidemiologic analysis. Am J of Epidemiol. 1987; 125(5):761-768.
• [2]Thompson ML, Myers JE, Kriebel D. Prevalence odds ratio or prevalence ratio in the analysis of cross sectional data: what is to be done? Occup Environ Med. 1998; 55(4):272-277.
• [3]Lee J. Odds ratio or relative risk for cross-sectional data? Int J Epidemiol. 1994; 23(1):201-203.
• [4]Schmidt CO, Kohlmann T. When to use the odds ratio or the relative risk? Int J Public Health. 2008; 53(3):165-167.
• [5]Sinclair JC, Bracken MB. Clinically useful measures of effect in binary analyses of randomized trials. J Clin Epidemiol. 1994; 47(8):881-889.
• [6]Grimes DA, Schulz KF. Making sense of odds and odds ratios. Obstet Gynecol. 2008; 111(2 Pt 1):423-426.
• [7]Sackett DL, Deeks JJ, Altman DG. Down with odds ratios! Evid Based Med. 1996; 1(6):164-166.
• [8]Deeks J. When can odds ratios mislead? Odds ratios should be used only in case–control studies and logistic regression analyses. BMJ. 1998; 317(7166):1155-1156.
• [9]Zhang J, Yu KF. What’s the relative risk? A method of correcting the odds ratio in cohort studies of common outcomes. JAMA. 1998; 280(19):1690-1691.
• [10]McNutt L-A, Wu C, Xue X, Hafner JP. Estimating the relative risk in cohort studies and clinical trials of common outcomes. Am J Epidemiol. 2003; 157(10):940-943.
• [11]Zocchetti C, Consonni D, Bertazzi PA. Relationship between prevalence rate ratios and odds ratios in cross-sectional studies. Int J Epidemiol. 1997; 26(1):220-223.
• [12]Torman VBL, Camey SA. Bayesian Models for Estimating Relative Risks with Binary and Polytomous Outcomes (Portuguese) [dissertation]. Porto Alegre, RS: Universidade Federal do Rio Grande do Sul; 2013. http://hdl.handle.net/10183/80066. Accessed 07 Jan 2014.
• [13]Wacholder S. Binomial regression in GLIM: estimating risk ratios and risk differences. Am J Epidemiol. 1986; 123(1):174-184.
• [14]Zocchetti C, Consonni D, Bertazzi PA. Estimation of prevalence rate ratios from cross-sectional data. Int J Epidemiol. 1995; 24(5):1064-1067.
• [15]Zou G. A modified poisson regression approach to prospective studies with binary data. Am J Epidemiol. 2004; 159(7):702-706.
• [16]Barros AJD, Hirakata VN. Alternatives for logistic regression in cross-sectional studies: an empirical comparison of models that directly estimate the prevalence ratio. BMC Med Res Methodol. 2003; 3:21. BioMed Central Full Text
• [17]Carter RE, Lipsitz SR, Tilley BC. Quasi-likelihood estimation for relative risk regression models. Biostatistics. 2005; 6(1):39-44.
• [18]Williamson T, Eliasziw M, Fick G. Log-binomial models: exploring failed convergence. Emerg Themes Epidemiol. 2013; 10:14. BioMed Central Full Text
• [19]Blizzard L, Hosmer DW. Parameter estimation and goodness-of-fit in log binomial regression. Biom J. 2006; 48(1):5-22.
• [20]Yelland LN, Salter AB, Ryan P. Relative risk estimation in randomized controlled trials: a comparison of methods for independent observations. Int J Biostat. 2011; 7(1):1-31.
• [21]Chu H, Cole SR. Estimation of risk ratios in cohort studies with common outcomes: a Bayesian approach. Epidemiol. 2010; 21(6):855-862.
• [22]Zou GY, Donner A. Extension of the modified Poisson regression model to prospective studies with correlated binary data. Stat Methods Med Res. 2013; 22(6):661-670.
• [23]Yelland LN, Salter AB, Ryan P. Relative risk estimation in cluster randomized trials: a comparison of generalized estimating equation methods. Int J Biostat. 2011; 7(1):1-26.
• [24]Yelland LN, Salter AB, Ryan P, Laurence CO. Adjusted intraclass correlation coefficients for binary data: methods and estimates from a cluster-randomized trial in primary care. Clin Trials. 2011; 8(1):48-58.
• [25]Camey SA, Torman VBL, Hirakata VN, Cortes RX, Vigo A. Bias of multinomial logistic regression to estimate relative risk or prevalence ratio and alternatives. Cad Saude Publica. 2014; 30(1):21-29.
• [26]Blizzard L, Hosmer DW. The log multinomial regression model for nominal outcomes with more than two attributes. Biom J. 2007; 49(6):889-902.
• [27]Team RC. R: A Language and Environment for Statistical Computing. Vienna, Austria; 2013.
• [28]Zeileis A. Econometric computing with HC and HAC covariance matrix estimators. J Stat Softw. 2004; 11(10):1-17.
• [29]Lunn D, Spiegelhalter D, Thomas A, Best N. The BUGS project: Evolution, critique and future directions. Stat Med. 2009; 28(25):3049-67.
• [30]Thomas A, O’Hara B, Ligges U, Sturtz S. Making BUGS Open. R News. 2006; 6(1):12-17.
• [31]Carstensen B, Plummer M, Laara E, Hills M. Epi: A Package for Statistical Analysis in Epidemiology. 2013.
• [32]Kerry SM, Bland JM. Analysis of a trial randomised in clusters. BMJ. 1998; 316(7124):54.
• [33]Feng Z, Diehr P, Peterson A, McLerran D. Selected statistical issues in group randomized trials. Annu Rev Public Health. 2001; 22:167-187.
• [34]Giordani JMA, Hilgert JB, Hugo FN, Camey SA, Torman VBL, Passero LG, et al.. Contextual and individual determinants to satisfaction with the dental care of the Unified Health System (Portuguese) [abstract]. In: Brazilian Oral Research, 2013; 27:32. http://www.sbpqo.org.br/resumos/RevistaSupl2013.pdf Accessed 07 Jan 2015.
• [35]Snijders TAB, Bosker RJ. Multilevel Analysis: An Introduction to Basic and Advanced Multilevel Modeling. Sage Publications, London; 1999.
• [36]Hosmer DW, Lemeshow S. Applied Logistic Regression. 2nd ed. Wiley, New York; 2000.
• [37]Gelman A, Rubin DB. Inference from iterative simulation using multiple sequences. Stat Sci. 1992; 7(4):457-472.
• [38]Gelman A. Prior distributions for variance parameters in hierarchical models. Bayesian Anal. 2006; 1(3):515-534.
• [39]Rue H, Martino S, Chopin N. Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations. J R Stat Soc Ser B Stat Methodol. 2009; 71(2):319-392.
• [40]Martins TG, Simpson D, Lindgren F, Rue H. Bayesian computing with INLA: new features. Comput Stat Data Anal. 2013; 67:68-83.
• [41]Plummer M. JAGS: A program for analysis of Bayesian graphical models using Gibbs sampling. Proc 3rd Int Work Distrib Stat Comput. Vienna, Austria, March 20–22, 2003.
• [42]Stan: A C++ Library for Probability and Sampling, Version 2.5.0. 2014.