Performance of variable and function selection methods for estimating the nonlinear health effects of correlated chemical mixtures: A simulation study

被引:10
作者
Lazarevic, Nina [1 ]
Knibbs, Luke D. [1 ]
Sly, Peter D. [2 ]
Barnett, Adrian G. [3 ]
机构
[1] Univ Queensland, Sch Publ Hlth, Fac Med, Herston, Qld 4006, Australia
[2] Univ Queensland, Childrens Hlth & Environm Program, Child Hlth Res Ctr, South Brisbane, Qld, Australia
[3] Queensland Univ Technol, Sch Publ Hlth & Social Work, Fac Hlth, Kelvin Grove, Qld, Australia
基金
英国医学研究理事会;
关键词
chemical mixtures; endocrine-disrupting chemicals; multipollutant; nonmonotonicity; variable selection; STRUCTURED ADDITIVE REGRESSION; EXPOSURE; MODELS; PRIORS; BART;
D O I
10.1002/sim.8701
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Statistical methods for identifying harmful chemicals in a correlated mixture often assume linearity in exposure-response relationships. Nonmonotonic relationships are increasingly recognized (eg, for endocrine-disrupting chemicals); however, the impact of nonmonotonicity on exposure selection has not been evaluated. In a simulation study, we assessed the performance of Bayesian kernel machine regression (BKMR), Bayesian additive regression trees (BART), Bayesian structured additive regression with spike-slab priors (BSTARSS), generalized additive models with double penalty (GAMDP) and thin plate shrinkage smoothers (GAMTS), multivariate adaptive regression splines (MARS), and lasso penalized regression. We simulated realistic exposure data based on pregnancy exposure to 17 phthalates and phenols in the US National Health and Nutrition Examination Survey using a multivariate copula. We simulated data sets of sizeN = 250 and compared methods across 32 scenarios, varying by model size and sparsity, signal-to-noise ratio, correlation structure, and exposure-response relationship shapes. We compared methods in terms of their sensitivity, specificity, and estimation accuracy. In most scenarios, BKMR, BSTARSS, GAMDP, and GAMTS achieved moderate to high sensitivity (0.52-0.98) and specificity (0.21-0.99). BART and MARS achieved high specificity (>= 0.90), but low sensitivity in low signal-to-noise ratio scenarios (0.20-0.51). Lasso was highly sensitive (0.71-0.99), except for quadratic relationships (<= 0.27). Penalized regression methods that assume linearity, such as lasso, may not be suitable for studies of environmental chemicals hypothesized to have nonmonotonic relationships with outcomes. Instead, BKMR, BSTARSS, GAMDP, and GAMTS are attractive methods for flexibly estimating the shapes of exposure-response relationships and selecting among correlated exposures.
引用
收藏
页码:3947 / 3967
页数:21
相关论文
共 58 条
[1]   A Systematic Comparison of Linear Regression-Based Statistical Methods to Assess Exposome-Health Associations [J].
Agier, Lydiane ;
Portengen, Lutzen ;
Chadeau-Hyam, Marc ;
Basagana, Xavier ;
Giorgis-Allemand, Lise ;
Siroux, Valerie ;
Robinson, Oliver ;
Vlaanderen, Jelle ;
Gonzalez, Juan R. ;
Nieuwenhuijsen, Mark J. ;
Vineis, Paolo ;
Vrijheid, Martine ;
Slama, Remy ;
Vermeulen, Roel .
ENVIRONMENTAL HEALTH PERSPECTIVES, 2016, 124 (12) :1848-1856
[2]  
[Anonymous], 2019, NAT HLTH NUTR EX SUR
[3]  
[Anonymous], 2006, R News
[4]   Optimal predictive model selection [J].
Barbieri, MM ;
Berger, JO .
ANNALS OF STATISTICS, 2004, 32 (03) :870-897
[5]   A systematic comparison of statistical methods to detect interactions in exposome-health associations [J].
Barrera-Gomez, Jose ;
Agier, Lydiane ;
Portengen, Lutzen ;
Chadeau-Hyam, Marc ;
Giorgis-Allemand, Lise ;
Siroux, Valerie ;
Robinson, Oliver ;
Vlaanderen, Jelle ;
Gonzalez, Juan R. ;
Nieuwenhuijsen, Mark ;
Vineis, Paolo ;
Vrijheid, Martine ;
Vermeulen, Roel ;
Slama, Remy ;
Basagana, Xavier .
ENVIRONMENTAL HEALTH, 2017, 16
[6]   Extending the Distributed Lag Model framework to handle chemical mixtures [J].
Bello, Ghalib A. ;
Arora, Manish ;
Austin, Christine ;
Horton, Megan K. ;
Wright, Robert O. ;
Gennings, Chris .
ENVIRONMENTAL RESEARCH, 2017, 156 :253-264
[7]   Estimating the Health Effects of Exposure to Multi-Pollutant Mixture [J].
Billionnet, Cecile ;
Sherrill, Duane ;
Annesi-Maesano, Isabella .
ANNALS OF EPIDEMIOLOGY, 2012, 22 (02) :126-141
[8]   Environmental Chemicals: Evaluating Low-Dose Effects [J].
Birnbaum, Linda S. .
ENVIRONMENTAL HEALTH PERSPECTIVES, 2012, 120 (04) :A143-A144
[9]   VARIABLE SELECTION FOR BART: AN APPLICATION TO GENE REGULATION [J].
Bleich, Justin ;
Kapelner, Adam ;
George, Edward I. ;
Jensen, Shane T. .
ANNALS OF APPLIED STATISTICS, 2014, 8 (03) :1750-1781
[10]   Statistical software for analyzing the health effects of multiple concurrent exposures via Bayesian kernel machine regression [J].
Bobb, Jennifer F. ;
Henn, Birgit Claus ;
Valeri, Linda ;
Coull, Brent A. .
ENVIRONMENTAL HEALTH, 2018, 17