Abstract
A hierarchical Bayesian factor model for multivariate spatially correlated data is proposed. Multiple cancer incidence data in Scotland are jointly analyzed, looking for common components, able to detect etiological factors of diseases hidden behind the data. The proposed method searches factor scores incorporating a dependence within observations due to a geographical structure. The great flexibility of the Bayesian approach allows the inclusion of prior opinions about adjacent regions having highly correlated observable and latent variables. The proposed model is an extension of a model proposed by Rowe (2003a) and starts from the introduction of separable covariance matrix for the observations. A Gibbs sampling algorithm is implemented to sample from the posterior distributions.
Similar content being viewed by others
References
Aguilar O, West M (2000) Bayesian dynamic factor models and portfolio allocation. J Bus Econ Stat 18: 338–357
Anselin L (2001) Rao’s score test in spatial econometrics. J Stat Plan Inference 97: 113–139
Anselin L (2007) Spatial econometrics in RSUE: retrospect and prospect. Reg Sci Urban Econ 37: 450–456
Arminger G, Muthén BO (1998) A Bayesian approach to nonlinear latent variable models using the Gibbs sampler and the metropolis-hastings algorithm. Psychometrika 63: 271–300
Besag J, York J, Mollie A (1991) Bayesian image restoration, with two applications in spatial statistics. Ann Inst Stat Math 43: 1–20
Best N, Richardson S, Thomson A (2005) A comparison of Bayesian spatial models for disease mapping. Stat Methods Med Res 14: 35–59
Breslow NE, Clayton DG (1993) Approximate inference in generalized linear mixed models. J Am Stat Assoc 88: 9–25
Brooks S, Gelman A (1998) Alternative methods for monitoring convergence of iterative simulations. J Comput Graph Stat 7: 434–455
Burkitt DP (1969) Related disease-related cause?. Lancet 2: 1229–1231
Burkitt DP (1970) Relationship as a clue to causation. Lancet 2: 1237–1240
Cancer in Scotland (October 2010) Information Services Division, NHS, National Services Scotland
Christensen WF, Amemiya Y (2003) Modeling and prediction for multivariate spatial factor analysis. J Stat Plan Inference 115: 543–564
Clayton D, Kaldor J (1987) Empirical bayes estimates of age- standardized relative risks for use in disease mapping. Biometrics 43: 671–681
Cressie N (1993a) Regional mapping of incidence rates using spatial Bayesian models. Med Care 31: 60–65
Cressie N (1993b) Statistics for spatial data. Wiley, New York
Cressie N, Wikle CK (2001) Statistics for spatio-temporal data. Wiley, New York
Cressie N, Calder K, Clark J, VerHoef J, Wikle CK (2009) Accounting for uncertainty in ecological analysis: the strengths and limitations of hierarchical statistical modeling. Ecol Appl 19: 553–557
Diggle PG, Moyeed RA, Tawn JA (1992) Model-based geo-statistics. Appl Stat 47: 299–350
Downing A, Forman D, Gilthorpe MS, Edwards KL, Manda SO (2008) Joint disease mapping using six cancers in the Yorkshire region of England. Int J Health Geogr 28: 7–41
Fathalla MF (1971) Incessant ovulation-a factor in ovarian neoplasia?. Lancet 2(7716): 163
Fritschi L, Glassm DC, Tabrizi JS, Leavy JE, Ambrosini GL (2007) Occupational risk factors for prostate cancer and benign prostatic hyperplasia: a case-control study in Western Australia. Occup Environ Med 64(1): 60–65
Gilks WR, Best NG, Tan KKC (1995) Adaptive Rejection Metropolis Sampling within Gibbs Sampling. Appl Stat 44: 455–472
Grönberg H (2003) Prostate cancer epidemiology. Lancet 361: 859–864
Haining R, Grith D, Bennett R (1989) Maximum likelihood estimation with missing spatial data and with an application to remotely sensed data. Commun Stat Theory Methods 1875–1894
Hayashi K, Sen PK (2001) Bias-corrected estimator of factor loadings in Bayesian factor analysis. Educ Psychol Meas 62(6): 944–959
Hogan JW, Tchernis R (2004) Bayesian factor analysis for spatially correlated data, with application to summarizing area-level material deprivation from census data. J Am Stat Assoc 99(466): 314–324
Journel AG (1983) Geostatistics. Encyclopedia of statistical sciences 3: 424–431
Knorr-Held L, Best NG (2001) A shared component model for detecting joint and selective clustering of two diseases. J Roy Stat Soc Ser A 164: 73–85
Lawley DN (1940) The estimation of factor loadings by the method of maximum likelihood. Proc Roy Soc Edinb 60: 82–84
Lawson AB (2001) Statistical methods in spatial epidemiology. Wiley, New York
Le N, Sun W, Zidek J (1997) Bayesian multivariate spatial interpolater with data missing by design. J Roy Stat Soc Ser B 59: 501–510
Lee SE, Press SJ (1998) Robustness of Bayesian factor analys estimates. Commun Stat Theory Methods 27: 1871–1893
Leorato S, Mezzetti M (2011) Bayesian spatial panel data. Tecnical Report Università “Tor Vergata”, Rome
Lopes H, West M (2004) Bayesian model assessment in factor analysis. Stat Sinica 14: 41–67
Martin JL, McDonald RP (1975) Bayesian estimation in unrestricted factor analysis. A treatment for Heywood cases. Psychometrika 40: 505–517
Mezzetti M, Billari FC (2005) Bayesian correlated factor analysis of socio-demographic indicators. Stat Methods Appl 14: 223–241
Polasek W (1997) Factor analysis and outliers: a Bayesian approach. Discussion paper, University of Basel
Press SJ, Shigemasu K (1989) Bayesian inference in factor analysis In: Gleser L, Perlman M, Press SJ, Sampson A (eds) Contributions to probability and statistics: essays in honor of Ingram Olkin (Chap. 15). Springer, New York
Press SJ, Shigemasu K (1997) Bayesian inference in factor analysis-revised, with an appendix by Rowe, D.B. Technical report No. 243, Department of Statistics, University of California, Riverside
Rowe DB (2000) Factorization of separable and patterned covariance matrices for gibbs sampling. Monte Carlo Methods Appl 6(3): 205–210
Rowe DB (2002) Jointly distributed mean and mixing coefficients for Bayesian source separation using MCMC and ICM. Monte Carlo Methods Appl 8(4): 395–403
Rowe DB (2003a) Multivariate Bayesian statistics: models for source separation and signal unmixing. CRC Press, Boca Raton
Rowe DB (2003b) On using the sample mean in Bayesian factor analysis. J Interdiscip Math 6(3): 319–329
Rowe DB, Press SJ (1998) Gibbs sampling and hill climbing in Bayesian factor analysis. Technical Report No. 255, Department of Statistics, University of California, Riverside
Scheiner SM, Gurevitch J (2001) Design and analysis of ecological experiments. 2. Oxford University Press, Oxford
Spadea T, Zengarini N, Kunst A, Zanetti R, Rosso S, Costa G (2010) Cancer risk in relationship to different indicators of adult socioeconomic position in Turin, Italy. Cancer Causes Control 21(7):1117–1130
Srivastava MS, von Rosen T, von Rosen D (2008) Models with a Kronecker product covariance structure. Estim Test Math Methods Stat 17(4): 357–370
Tzala E, Best N (2008) Bayesian latent variable modelling of multivariate spatio-temporal variation in cancer mortality. Stat Methods Med Res 17: 97–118
Waller LA, Gotway CA (2004) Applied spatial statistics for public health data. Wiley-InterScience, New York
Waller LA, Carlin BP, Xia H, Gelfand AE (1997) Hierarchical spatio-temporal mapping of disease rates. J Am Stat Assoc 92: 607–617
Wang F, Wall MM (2003) Generalized common spatial factor model. Biostatistics 4: 569–582
Webster R, Oliver MA (2001) Geostatistics for environmental scientists. Wiley, New York
Wikle CK (2003) Hierarchical models in environmental science. Int Stat Rev 71: 181–199
Yanai H, Inaba Y, Takagi H, Toyokawa H, Yamamoto S (1978) An epidemiological study on mortality rates of various cancer sites during 1958–1971 by means of factor analysis. Behaviormetrica 5: 55–74
Yasui Y, Lele S (1997) A regression method for spatial disease rates: an estimating function approach. J Am Stat Assoc 92: 21–32
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mezzetti, M. Bayesian factor analysis for spatially correlated data: application to cancer incidence data in Scotland. Stat Methods Appl 21, 49–74 (2012). https://doi.org/10.1007/s10260-011-0177-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10260-011-0177-9