Abstract
This chapter extends to spatial statistics the main theme from Chap. 7: that positive exposure-response coefficients in regression models are not valid substitutes for quantitative risk assessment, because statistical coefficients do not usually reveal causal relationships. Many recent health risk assessments have noted that adverse health outcomes are significantly statistically associated with proximity to suspected sources of health hazard, such as manufacturing plants or point sources of air pollution. Using geographic proximity to sources as surrogates for exposure to (possibly unknown) releases, spatial ecological studies have identified potential adverse health effects based on significant regression coefficients between risk rates and distances from sources in multivariate statistical risk models. Although this procedure has been fruitful in identifying exposure-response associations, the resulting regression coefficients typically lack valid causal interpretations. Spurious spatial regression and other threats to valid causal inference discussed in this chapter undermine practical efforts to causally link health effects to geographic sources, even when there are clear statistical associations between them. This chapter demonstrates the methodological problems by examining statistical associations and regression coefficients between spatially distributed exposure and response variables in a realistic spatial data set. We find that distance from “nonsense” sources (such as arbitrary points or lines) are highly statistically significant predictors of cause-specific risks, such as traffic fatalities and incidence of Kaposi’s Sarcoma. However, the signs of such associations typically depend on the distance scale chosen. This is consistent with theoretical analyses showing that random spatial trends (which tend to fluctuate in sign), rather than true causal relations, can create statistically significant regression coefficients: spatial location itself becomes a confounder for spatially distributed exposure and response variables. Hence, extreme caution, and careful application of spatial statistical methods are warranted before interpreting proximity-based exposure-response relations as evidence of a possible or probable causal relation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Angrist JD, Pischke J-S. Mostly harmless econometrics: an empiricist’s companion. Princeton, NJ: Princeton University Press; 2009.
Berman DW, Cox T, Popken D. A cautionary tale: the characteristics of two-dimensional distributions and their effects on epidemiological studies employing an ecological design. Crit Rev Toxicol. 2013;43(Suppl 1):1–25.
Campbell DT, Stanley JC. Experimental and quasi-experimental designs for research. Chicago: Rand McNally; 1966.
Carbone M, Yang H. Molecular pathways: targeting mechanisms of asbestos and erionite carcinogenesis in mesothelioma. Clin Cancer Res. 2012;18(3):598–604.
CCR (2012) Cancer incidence/mortality rates in California. http://www.cancer-rates.info/ca. Accessed 5 Jan 2012
Cox LA Jr. Regulatory false positives: true, false, or uncertain? Risk Anal. 2007;27(5):1083–6.
CSDC (2012) Selected census 1990 and 2000 population and housing estimates for tract 2000. California Dept. of Finance, Demographic Research Unit, California State Data Center. http://www.dof.ca.gov/research/demographic/state_census_data_center/products-services/. Accessed 5 Jan 2012
Dash D, Druzdzel MJ. A note on the correctness of the causal ordering algorithm. Artif Intell. 2008;172:1800–8.
Druzdzel MJ, Simon HA. Causality in Bayesian belief networks. In: Proceedings of the ninth annual conference on uncertainty in artificial intelligence (UAI-93). San Francisco: Morgan Kaufmann Publishers, Inc.; 1993. p. 3–11.
Eichler M, Didelez V. On Granger causality and the effect of interventions in time series. Lifetime Data Anal. 2010;16(1):3–32.
Freedman DA. Graphical models for causation, and the identification problem. Eval Rev. 2004;28(4):267–93.
Friedman N, Goldszmidt M. Learning Bayesian networks with local structure. In: Jordan MI, editor. Learning in graphical models. Cambridge: MIT Press; 1998. p. 421–59.
García-Pérez J, López-Cima MF, Boldo E, Fernández-Navarro P, Aragonés N, Pollán M, Pérez-Gómez B, López-Abente G. Leukemia-related mortality in towns lying in the vicinity of metal production andprocessing installations. Environ Int. 2010;36(7):746–53.
Gardner D. The science of fear: how the culture of fear manipulates your brain. New York: Penguin Group; 2009.
Gilmour S, Degenhardt L, Hall W, Day C. Using intervention time series analyses to assess the effects of imperfectly identifiable natural events: a general method and example. BMC Med Res Methodol. 2006;6:16.
Goria S, Daniau C, de Crouy-Chanel P, Empereur-Bissonnet P, Fabre P, Colonna M, Duboudin C, Viel JF, Richardson S. Risk of cancer in the vicinity of municipal solid waste incinerators: importance of using a flexible modelling strategy. Int J Health Geogr. 2009;8:31.
Hack CE, Haber LT, Maier A, Shulte P, Fowler B, Lotz WG, Savage RE Jr. A Bayesian network model for biomarker-based dose response. Risk Anal. 2010;30(7):1037–51.
Helfenstein U. The use of transfer function models, intervention analysis and related time series methods in epidemiology. Int J Epidemiol. 1991;20(3):808–15.
Imberger G, Vejlby AD, Hansen SB, Møller AM, Wetterslev J. Statistical multiplicity in systematic reviews of anaesthesia interventions: a quantification and comparison between cochrane and non-cochrane reviews. PLoS ONE. 2011;6(12):e28422. https://doi.org/10.1371/journal.pone.0028422.
Ioannidis JPA. Why most published research findings are false. PLoS Med. 2005;2(8):e124. https://doi.org/10.1371/journal.pmed.0020124.
Krevor SC, Graves CR, Van Gosen BS, McCafferty AE (2009) Mapping the mineral resource base for mineral carbon-dioxide sequestration in the conterminous United States: U.S. Geological Survey Digital Data Series, p. 414. http://pubs.usgs.gov/ds/414/
Lauridsen J, Kosfeld R. Spurious spatial regression and heteroscedasticity. J Spat Sci. 2011;56(1):59–72.
Lehrer J (2012) Trials and errors: why science is failing us. Wired. http://www.wired.co.uk/magazine/archive/2012/02/features/trials-and-errors?page=all
Lipsitch M, Tchetgen Tchetgen E, Cohen T. Negative controls: a tool for detecting confounding and bias in observational studies. Epidemiology. 2010;21(3):383–8.
López-Abente G, Fernández-Navarro P, Boldo E, Ramis R, García-Pérez J. Industrial pollution and pleural cancer mortality in Spain. Sci Total Environ. 2012;424:57–62.
Loyo-Berríos NI, Irizarry R, Hennessey JG, Tao XG, Matanoski G. Air pollution sources and childhood asthma attacks in Catano, Puerto Rico. Am J Epidemiol. 2007;165(8):927–35.
Maclure M. Multivariate refutation of aetiological hypotheses in non-experimental epidemiology. Int J Epidemiol. 1990;19(4):782–7.
Monge-Corella S, García-Pérez J, Aragonés N, Pollán M, Pérez-Gómez B, López-Abente G. Lung cancer mortality in towns near paper, pulp and board industries in Spain: a point source pollution study. BMC Public Health. 2008;8:288.
Moore KL, Neugebauer R, van der Laan MJ, Tager IB. Causal inference in epidemiological studies with strong confounding. Stat Med. 2012;31(13):1380–404. https://doi.org/10.1002/sim.4469.
NHTSA (2012) Fatality analysis reporting system. http://www-fars.nhtsa.dot.gov/Main/index.aspx. Accessed 5 Jan 2012
Ottenbacher KJ. Quantitative evaluation of multiplicity in epidemiology and public health research. Am J Epidemiol. 1998;147:615–9.
Pan XL, Day HW, Wang W, Beckett LA, Schenker MB. Residential proximity to naturally occurring asbestos and mesothelioma risk in California. Am J Respir Crit Care Med. 2005;172(8):1019–25.
Pawlowicz R (2011) M_Map: a Mapping Package for MATLAB. http://www2.ocgy.ubc.ca/~rich/map.html. Retrieved 5 Jan 2012
Ramis R, Diggle P, Cambra K, López-Abente G. Prostate cancer and industrial pollution: risk around putative focus in a multi-source scenario. Environ Int. 2011;37(3):577–85.
Robins JM, Hernán MA, Brumback B. Marginal structural models and causal inference in epidemiology. Epidemiology. 2000;11(5):550–60.
Sarewitz D. Beware the creeping cracks of bias. Nature. 2012;485:149.
Statistica (2012) Statistica 10 documentation. http://documentation.statsoft.com/STATISTICAHelp.aspx?path=Graphs/Graph/ModifyingGraphs/Notes/DistanceWeightedLeastSquaresFitting
Stebbings JH Jr. Panel studies of acute health effects of air pollution. II. A methodologic study of linear regression analysis of asthma panel data. Environ Res. 1978;17(1):10–32.
USCB (2012) Census 2000 TIGER/line files. http://www.census.gov/geo/www/tiger/tiger2k/tgr2000.html. Accessed 5 Jan 2012
Whitworth KW, Marshall AK, Symanski E. Maternal residential proximity to unconventional gas development and perinatal outcomes among a diverse urban population in Texas. PLoS One. 2017;12(7):e0180966.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Cox Jr., L.A. (2021). Causal vs. Spurious Spatial Exposure-Response Associations in Health Risk Analysis. In: Quantitative Risk Analysis of Air Pollution Health Effects. International Series in Operations Research & Management Science, vol 299. Springer, Cham. https://doi.org/10.1007/978-3-030-57358-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-57358-4_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-57357-7
Online ISBN: 978-3-030-57358-4
eBook Packages: Business and ManagementBusiness and Management (R0)