Abstract
In this paper, we propose a novel spatial importance parameter hierarchical logistic regression modeling approach that includes measurement error from misalignment. We apply this model to study the relationship between the estimated concentration of soil metals at the residence of mothers and the development of intellectual disability (ID) in their children. The data consist of monthly computerized claims data about the prenatal experience of pregnant women living in nine areas within South Carolina and insured by Medicaid during January 1, 1996 and December 31, 2001 and the outcome of ID in their children during early childhood. We excluded mother-child pairs if the mother moved to an unknown location during pregnancy. We identified an association of the ID outcome with arsenic (As) and mercury (Hg) concentration in soil during pregnancy, controlling for infant sex, maternal race, mother’s age, and gestational weeks at delivery. There is some indication that Hg has a slightly higher importance in the third and fourth months of pregnancy, while As has a more uniform effect over all the months with a suggestion of a slight increase in risk in later months.
Similar content being viewed by others
References
Aelion CM, Davis HT, McDermott S, Lawson AB (2008) Metal concentrations in rural topsoil in South Carolina: potential for human health impact. Sci Total Environ 402:149–156
Aelion CM, Davis HT, Liu Y, Lawson AB, McDermott S (2009a) Validation of Bayesian kriging of arsenic, chromium, lead, and mercury surface soil concentrations based on internode sampling. Environ Sci Technol 43:4432–4438
Aelion CM, Davis HT, McDermott S, Lawson AB (2009b) Soil metal concentrations and toxicity: associations with distances to industrial facilities and implications for human health. Sci Total Environ 407:2216–2223
Alberta Biomonitoring Program (2008) Chemicals in serum of pregnant women in Alberta. Alberta Health and Wellness. http://www.health.alberta.ca/documents/Chemical-Biomonitoring-2008.pdf. Accessed 07 March 2014
Audus KL (1999) Controlling drug delivery across the placenta. Eur J Pharm Sci 8:161–165
Banerjee S, Carlin BP, Gelfand AE (2003) Hierarchical modeling and analysis for spatial data. Chapman & Hall/CRC Monographs on Statistics & Applied Probability
Cai B, Lawson AB, McDermott S, Aelion CM (2011) Variable selection for spatial latent predictors under Bayesian spatial model. Stat Model 11:535–555
Cai B, Lawson AB, McDermott S, Aelion CM (2012) Bayesian spatial change-point model for intellectual disability analysis. Stat Methods Med Res (In press)
Carroll R, Ruppert D, Stefanski LA, Crainiceanu C (2006) Measurement error in nonlinear models: a modern perspective, 2nd edn. Chapman and Hall, New York
Centers for Disease Control and Prevention (1999) Toxicology profile for mercury. http://www.atsdr.cdc.gov/toxprofiles/tp46.pdf. Accessed 07 March 2014
Centers for Disease Control and Prevention (2004) Toxicology profile for copper. http://www.atsdr.cdc.gov/ToxProfiles/tp132.pdf. Accessed 07 March 2014
Centers for Disease Control and Prevention (2005) Toxicology profile for nickel. http://www.atsdr.cdc.gov/ToxProfiles/tp15.pdf. Accessed 07 March 2014
Centers for Disease Control and Prevention (2007a) Toxicology profile for arsenic. http://www.atsdr.cdc.gov/toxprofiles/tp2.pdf. Accessed 07 March 2014
Centers for Disease Control and Prevention (2007b) Toxicology profile for barium. http://www.atsdr.cdc.gov/ToxProfiles/tp24.pdf. Accessed 07 March 2014
Centers for Disease Control and Prevention (2012) Toxicology profile for chromium. http://www.atsdr.cdc.gov/toxprofiles/tp7.pdf. Accessed 07 March 2014
Centers for Disease Control and Prevention, Intellectual Disability Fact Sheet (2014) http://www.cdc.gov/ncbddd/actearly/pdf/parents_pdfs/IntellectualDisability.pdf. Accessed 07 March 2014
Collipp PJ, Chen SY, Maitinsky S (1983) Manganese in infant formulas and learning disability. Ann Nutr Metab 27:488–494
Cook AJ, Gold DR, Li Y (2009) Spatial cluster detection for repeatedly measured outcomes while accounting for residential history. Biom J Biom Z 51:801–818
Davis HT, Aelion CM, McDermott S, Lawson AB (2009) Identifying natural and anthropogenic sources of metals in urban and rural soils using GIS-based data, PCA, and spatial interpolation. Environ Pollut 157:2378–2385
Diggle PJ, Ribeiro PJ Jr (2007) Model-based geostatistics. Springer, New York
Gelman A (2006) Prior distributions for variance parameters in hierarchical models. Bayesian Anal 1:515–534
Goldman LR, Koduru S (2000) Chemicals in the environment and developmental toxicity to children: a public health and policy perspective. Environ Health Perspect 108(Suppl 3):443–448
Groom KM, Poppe KK, North RA, McCowan LM (2007) Small-for-gestational-age infants classified by customized or population birthweight centiles: impact of gestational age at delivery. Am J Obstet Gynecol. 197(3):239.e1–5
Gryparis A, Paciorek CJ, Zeka A, Schwartz J, Coull BA (2009) Measurement error caused by spatial misalignment in environmental epidemiology. Biostatistics 10:258–274
Hoffman K, Webster TF, Weinberg JM, Aschengrau A, Janulewicz PA, White RF, Vieira VM (2010) Spatial analysis of learning and developmental disorders in upper Cape Cod, Massachusetts using generalized additive models. Int J Health Geogr 9:7
Kim JI, Lawson AB, McDermott S, Aelion CM (2009) Variable selection for spatial random field predictors under a Bayesian mixed hierarchical spatial model. Spat Spatio-Temporal Epidemiol 1:95–102
Kim JI, Lawson AB, McDermott S, Aelion CM (2010) Bayesian spatial modeling of disease risk in relation to multivariate environmental risk fields. Stat Med 29:142–157
Lawson AB (2006) Disease cluster detection: a critique and a Bayesian proposal. Stat Med 25:897–916
Lawson AB (2013) Bayesian disease mapping: hierarchical modeling in spatial epidemiology. Chapman and Hall/CRC
Li X, Lee S, Wong S, Shi W, Thornton I (2004) The study of metal contamination in urban soils of Hong Kong using a GIS-based approach. Environ Pollut 129:113–124
Liu Y, McDermott S, Lawson A, Aelion CM (2010) The relationship between mental retardation and developmental delays in children and the levels of arsenic, mercury and lead in soil samples taken near their mother’s residence during pregnancy. Int J Hyg Environ Health 213:116–123
Manjourides J, Pagano M (2011) Improving the power of chronic disease surveillance by incorporating residential history. Stat Med 30:2222–2233
McDermott S, Durkin MS, Schupf N, Stein ZA (2007) Epidemiology and etiology of mental retardation. In: Jacobson JW, Mulick JA, Rojahn J (eds) Handbook of intellectual and developmental disabilities. Springer, New York
McDermott S, Wu J, Cai B, Lawson A, Aelion CM (2011) Probability of intellectual disability is associated with soil concentrations of arsenic and lead. Chemosphere 84:31–38
McDermott S, Bao W, Aelion CM, Cai B, Lawson A (2012) When are fetuses and young children most susceptible to soil metal concentrations of arsenic, lead and mercury? Spat Spatio-Temporal Epidemiol 3:265–272
National Dissemination Center for Children with Disabilities (2014) http://nichcy.org. Accessed 07 March 2014
Paciorek CJ (2012) Combining spatial information sources while accounting for systematic errors in proxies. J R Stat Soc (Ser C) 61:429–451
Pless IB (1994) The epidemiology of childhood disorders. Oxford University Press, New York
Spiegelhalter D, Best N, Carlin B, Van der Linde A (2002) Bayesian measures of model complexity and fit. J Roy Stat Soc Ser B 64:583–616
Szpiro AA, Paciorek CJ, Sheppard L (2011) Does more accurate exposure prediction necessarily improve health effect estimates? Epidemiology 22:680–685
Tong S (2000) Migration bias in ecologic studies. Eur J Epidemiol 16:365–369
Trasande L, Schechter CB, Haynes KA, Landrigan PJ (2006) Mental retardation and prenatal methylmercury toxicity. Am J Ind Med 49:153–158
U.S. Department of Health And Human Services (2012) Toxicological profile for chromium. http://www.atsdr.cdc.gov/toxprofiles/tp7.pdf. Accessed 27 March 2012
Vahter M (2009) Effects of arsenic on maternal and fetal health. Annu Rev Nutr 29:381–399
Van den Hooven EH, Pierik FH, Van Ratingen SW, Zandveld PY, Meijer EW, Hofman A, Miedema HM, Jaddoe VW, De Kluizenaar Y (2012) Air pollution exposure estimation using dispersion modelling and continuous monitoring data in a prospective birth cohort study in the Netherlands. Environ Health: Glob Access Sci Sources 11:9
Vieira V, Webster T, Aschengrau A, Ozonoff D (2002) A method for spatial analysis of risk in a population-based case–control study. Int J Hyg Environ Health 205:115–120
Vieira V, Webster T, Weinberg J, Aschengrau A, Ozonoff D (2005) Spatial analysis of lung, colorectal, and breast cancer on Cape Cod: an application of generalized additive models to case–control data. Environ Health: Glob Access Sci Sources 4:11
Vincenty T (1975) Direct and inverse solutions of geodesics on the ellipsoid with application of nested equations. Surv Rev XXII:88–93
Walsh LM, Sumner ME, Keeney DR (1977) Occurrence and distribution of arsenic in soils and plants. Environ Health Perspect 19:67–71
Wheeler DC, Waller LA, Cozen W, Ward MH (2012) Spatial-temporal analysis of non-Hodgkin lymphoma risk using multiple residential locations. Spat Spatio-Temporal Epidemiol 3:163–171
Zhen H, Lawson AB, McDermott S, Lamichhane AP, Aelion M (2008) A spatial analysis of mental retardation of unknown cause and maternal residence during pregnancy. Geospat Health 2:173–182
Acknowledgments
Source of financial support: funding for this research was provided by the National Institutes of Health, R01 Grant No. ES012895-04A2.
Author information
Authors and Affiliations
Corresponding author
Additional information
Responsible editor: Philippe Garrigues
Appendices
Appendix 1: Metropolis-Hastings algorithm
Recent development in computer facilities made Markov chain Monte Carlo (MCMC) (Trasande et al. 2006) simulation techniques one of the main computational tools in Bayesian statistical inference. For this study, we implemented the Metropolis version of the Metropolis-Hastings algorithm (U.S. Department of Health And Human Services 2012), which is one of the most popular MCMC methods. The algorithm consists of the following steps repeated T times, where T is the number of iterations of the chain. Our parameter θ consists of the true chemical values Z*(s j,i ), the regression coefficients and their standard deviations:
\( {\beta}_0,{\sigma}_{\beta_0},{\beta}_1,{\sigma}_{\beta_1},\left({w}_1,{w}_2,{w}_3,{w}_4,{w}_5,{w}_6,{w}_7,{w}_8,{w}_9\right),{\beta}_{21},{\sigma}_{\beta_{21}},\dots {\beta}_{2m},\dots {\sigma}_{\beta_{2m}} \), m being the number of individual level covariates.
In order to enhance computational efficiency block updates have been used for updating the true chemical values. Symmetric proposal distributions have been used for all the parameters.
-
Step 0
Assign starting values to θ 0.
For t = 1,…,T :
-
Step 1
Propose new values θ ′ from symmetric proposal distributions (h(θ ′ |θ)). In this case, we have used Gaussian proposals centered on the previous value for continuous parameters on (−∞, ∞)
-
Step 2
Calculate log (α) = min (0, R) then, as the symmetric proposals cancel in the ratio,
$$ R= \log \left\{\frac{L\left(\left.y\right|\theta^{\prime}\right)\prod {g}_i\left(\theta^{\prime}\right)}{L\left(\left.y\right|\theta \right)\prod {g}_i\left({\theta}_i\right)}\right\}, $$where L is the likelihood function and g is the prior distribution. The following prior distributions have been assigned:
$$ {\beta}_l\sim N\left(0,{\sigma}_{\beta_l}^2\right),l=0,1, $$$$ {\sigma}_{\beta_l}\sim U\left(0,2\right),l=0,1 $$w i ∼ Bernoulli (0.5), i = 1,…9
$$ \log \left({Z}^{*}\left({s}_{j,i}\right)\right)\sim N\left( \log \left({Z}^0\left({s}_{j,i}\right)\right),{\sigma}_{\log \left({Z}^0\left({s}_{j,i}\right)\right)}^2\right),j=1,\ldots 9,i=1,\dots n $$ -
Step 3
Update θ (t) = θ ′ with probability α
Appendix 2: simulation
To test the ability of the model to estimate importance parameters when correlated with the outcome, we used simulated data with different model assumptions. The simulation was performed with two scenarios, one in which month six values were simulated from a different distribution compared to the rest of the months, with a higher association with the outcome (Model 1). The second scenario was there was no variation in the months related to the chemical concentrations, and they were all generated from the same distributions (Model 2). Each dataset had 500 observations. We included only a limited number of scenarios due to difficulty in obtaining convergence for other variety of distribution assumptions and parameters. In Model 1, the outcome was generated from a Bernoulli (0.5) distribution. The chemical values for each month except month six were generated from a lognormal distribution with log mean −8 and log standard deviation 0.1 to which, if the outcome was 1 a random lognormal with mean −8 and log standard deviation 0.1 was added for each individual in each month except month 6. In order to induce a higher association with the outcome, a random lognormal with mean −4.2 and log standard deviation 0.1 was added for month six. In Model 2, the outcome was generated from a Bernoulli (0.5) distribution. The chemical values for each month were generated from a lognormal distribution with log mean −8 and log standard deviation 0.0001, to which a uniform U (0, 0.0001) random number was added to each month values for each subject. The kriged standard deviation was fixed at 0.001 for both models. We considered a low standard deviation in order to have less impact on the estimated values. Model 1 was run for 20,000 iterations, with the first 5,000 iterations discarded as burn-in. Model convergence was checked using the Geweke criteria. The highest importance parameter was obtained for the month 6 values (0.99), with lower importance parameters for the rest of the months. For model 1, the credible intervals for the importance parameters were (0, 1) except for month 6 which was (1, 1). These results suggest a good capability of the model to identify the months that are correlated with the outcome. The mean intercept and 95 % credible interval was estimated to be 0.047 (−0.11, 0.21), while the common mean slope and 95 % credible interval was 2.57 (2.54, 2.61). Model 2 was run for 20,000 iterations, 5,000 burn-in and a thinning of 3. Similar importance parameters have been estimated for each month (Table 5). For Model 2 the credible intervals for the importance parameters were (0, 1).
Rights and permissions
About this article
Cite this article
Onicescu, G., Lawson, A.B., McDermott, S. et al. Bayesian importance parameter modeling of misaligned predictors: soil metal measures related to residential history and intellectual disability in children. Environ Sci Pollut Res 21, 10775–10786 (2014). https://doi.org/10.1007/s11356-014-3072-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11356-014-3072-8