The Annals of Applied Statistics

Analysis of Minnesota colon and rectum cancer point patterns with spatial and nonspatial covariate information

Shengde Liang, Bradley P. Carlin, and Alan E. Gelfand

Full-text: Open access


Colon and rectum cancer share many risk factors, and are often tabulated together as “colorectal cancer” in published summaries. However, recent work indicating that exercise, diet, and family history may have differential impacts on the two cancers encourages analyzing them separately, so that corresponding public health interventions can be more efficiently targeted. We analyze colon and rectum cancer data from the Minnesota Cancer Surveillance System from 1998–2002 over the 16-county Twin Cities (Minneapolis–St. Paul) metro and exurban area. The data consist of two marked point patterns, meaning that any statistical model must account for randomness in the observed locations, and expected positive association between the two cancer patterns. Our model extends marked spatial point pattern analysis in the context of a log Gaussian Cox process to accommodate spatially referenced covariates (local poverty rate and location within the metro area), individual-level risk factors (patient age and cancer stage), and related interactions. We obtain smoothed maps of marginal log-relative intensity surfaces for colon and rectum cancer, and uncover significant age and stage differences between the two groups. This encourages more aggressive colon cancer screening in the inner Twin Cities and their southern and western exurbs, where our model indicates higher colon cancer relative intensity.

Article information

Ann. Appl. Stat., Volume 3, Number 3 (2009), 943-962.

First available in Project Euclid: 5 October 2009

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Colon cancer log Gaussian Cox process (LGCP) rectum cancer spatial point process


Liang, Shengde; Carlin, Bradley P.; Gelfand, Alan E. Analysis of Minnesota colon and rectum cancer point patterns with spatial and nonspatial covariate information. Ann. Appl. Stat. 3 (2009), no. 3, 943--962. doi:10.1214/09-AOAS240.

Export citation


  • Banerjee, S., Carlin, B. P. and Gelfand, A. E. (2004). Hierarchical Modeling and Analysis for Spatial Data. Chapman and Hall/CRC Press, Boca Raton, FL.
  • Banerjee, S. and Gelfand, A. E. (2006). Bayesian wombling: Curvilinear gradient assessment under spatial process models. J. Amer. Statist. Assoc. 101 1487–1501.
  • Banerjee, S., Gelfand, A. E., Finley, A. O. and Sang, H. (2008). Gaussian predictive process models for large spatial datasets. J. Roy. Statist. Soc. Ser. B 70 825–848.
  • Beneš, V., Bodlák, K., Møller, J. and Waagepetersen, R. (2002). Bayesian analysis of log Gaussian Cox processes for disease mapping. Research Report R-02-2001, Dept. Mathematical Sciences, Aalborg Univ., Aalborg.
  • Diggle, P. J. (2003). Statistical Analysis of Spatial Point Patterns, 2nd ed. Arnold, London.
  • Diggle, P. J. and Rowlingson, B. S. (1994). A conditional approach to point process modelling of elevated risk. J. Roy. Statist. Soc. Ser. A 157 433–440.
  • Flood, A., Peters, U., Chatterjee, N., Lacey, Jr., J. V., Schairer, C. and Schatzkin, A. (2005). Calcium from diet and supplements is associated with reduced risk of colorectal cancer in a prospective cohort of women. Cancer Epidemiology, Biomarkers & Prevention 14 126–132.
  • Flood, A., Rastogi, T., Wirfält, E., Mitrou, P. N., Reedy, J., Subar, A. F., Kipnis, V., Mouw, T., Hollenbeck, A. R., Leitzmann, M. and Schatzkin, A. (2008). Dietary patterns as identified by factor analysis and colorectal cancer among middle-aged Americans. American Journal of Clinical Nutrition 88 176–184.
  • Folsom, A. R. and Hong, C.-P. (2005). Magnesium intake and reduced risk of colon cancer in a prospective study of women. American Journal of Epidemiology 163 232–235.
  • Fuchs, C., Giovannucci, E., Colditz, G., Hunter, D., Speizer, F. and Willett, W. (1994). A prospective study of family history and the risk of colorectal cancer. New England Journal of Medicine 331 1669–1674.
  • Gelfand, A. E., Schmidt, A. M., Banerjee, S. and Sirmans, C. F. (2004). Nonstationary multivariate process modelling through spatially varying coregionalization (with discussion). Test 13 263–312.
  • Glebov, O. K., Rodriguez, L. M., Nakahara, K., Jenkins, J., Cliatt, J., Humbyrd, C.-J., DeNobile, J., Soballe, P., Simon, R., Wright, G., Lynch, P., Patterson, S., Lynch, H., Gallinger, S., Buchbinder, A., Gordon, G., Hawk, E. and Kirsch, I. R. (2003). Distinguishing right from left colon by the pattern of gene expression. Cancer Epidemiology, Biomarkers & Prevention 12 755–762.
  • Guan, Y. (2006). A composite likelihood approach in fitting spatial point process models. J. Amer. Statist. Assoc. 101 1502–1512.
  • Guan, Y. and Loh, J. M. (2007). A thinned block bootstrap variance estimation procedure for inhomogeneous spatial point patterns. J. Amer. Statist. Assoc. 102 1377–1386.
  • Guan, Y., Waagepetersen, R. and Beale, C. (2008). Second-order analysis of inhomogeneous spatial point processes with proportional intensity functions. J. Amer. Statist. Assoc. 103 769–777.
  • Huang, C. S., O’Brien, M. J., Yang, S. and Farraye, F. (2004). Hyperplastic polyps, serrated adenomas, and the serrated polyp neoplasia pathway. American Journal of Gastroenterology 99 2242–2255.
  • Kulldorff, M. (2006). SaTScan user guide, Version 7.0. Available at
  • Liang, S., Banerjee, S. and Carlin, B. P. (2009). Bayesian wombling for spatial point processes. Biometrics. DOI: 10.1111/j.1541-0420.2009.01203.x
  • Liang, S., Carlin, B. P. and Gelfand, A. E. (2009). Supplement to “Analysis of Minnesota colon and rectum cancer point patterns with spatial and nonspatial covariate information.” DOI: 10.1214/09-AOAS240SUPP.
  • Møller, J. and Waagepetersen, R. P. (2003). An introduction to simulation-based inference for spatial point processes. In Spatial Statistics and Computational Methods (J. Møller, ed.). Lecture Notes in Statistics 173 143–198. Springer, New York.
  • Møller, J. and Waagepetersen, R. P. (2004). Statistical Inference and Simulation for Spatial Point Processes. Chapman and Hall/CRC Press, Boca Raton, FL.
  • O’Brien, M. J., Yang, S., Mack, C., Xu, H., Huang, C. S., Mulcahy, E., Amorosino, M. and Farraye, F. A. (2006). Comparison of microsatellite instability, CpG island methylation phenotype, BRAF and KRAS status in serrated polyps and traditional adenomas indicates separate pathways to distinct colorectal carcinoma end points. American Journal of Surgical Pathology 30 1491–1501.
  • Pedersen, A., Johansen, C. and Gr onbaek, M. (2003). Relations between amount and type of alcohol and colon and rectal cancer in a Danish population based cohort study. Gut 52 861–867.
  • Physical Activity Guidelines Advisory Committee (2008). Physical Activity Guidelines Advisory Committee Report, 2008. U.S. Dept. Health and Human Services, Washington, DC.
  • Waagepetersen, R. (2007). An estimating function approach to inference for inhomogeneous Neyman–Scott processes. Biometrics 63 252–258.
  • Waagepetersen, R. and Guan, Y. (2009). Two-step estimation for inhomogeneous spatial point processes. J. Roy. Statist. Soc. Ser. B 71 685–702.
  • Wakefield, J. and Salway, R. (2001). A statistical framework for ecological and aggregate studies. J. Roy. Statist. Soc. Ser. A 164 119–137.
  • Wei, E. K., Giovannucci, E., Wu, K., Rosner, B., Fuchs, C. S., Willett, W. C. and Colditz, G. A. (2003). Comparison of risk factors for colon and rectal cancer. International Journal of Cancer 108 433–442.
  • Wolpert, R. L. and Ickstadt, K. (1998). Poisson/gamma random field models for spatial statistics. Biometrika 85 251–269.

Supplemental materials