A Hierarchical Bayesian Analysis of Circular Data with Autoregressive Errors: Modeling the Mechanical Properties of Cortical Bone
We study a hierarchical model for circular data with covariate information. The model for the data given the first stage parameters is based on a finite Fourier series expansion of the conditional mean level for each circular curve. The dependence of the response on the covariates is incorporated through a linear regression of the parameters on the covariates. The within curve dependence is accounted for by an autoregressive error structure. In the second and subsequent stages, a hierarchical Bayes structure is imposed on the parameters of the expansion.
We use the model to analyze a set of observational data consisting of CAT scans of cross-sections of human femurs at the lesser trochanter from a group of patients admitted to the Hospital for Special Surgery in New York City. Two responses are considered: the thickness of the cortical bone from a series of equi-angular rays through the centroid of the section, and the components of the area moment of inertia about the bone’s major principal axis. The latter provide a measure of the bone’s mechanical properties under loading. We relate these curves to each subject’s age, gender, and diagnosis. Marginal posterior distributions of the model parameters and predictive distributions of future observations are estimated using the Gibbs Sampler and displayed graphically. The sensitivity of the conclusions to the modeling assumptions is assessed. The necessity of interplay between the computationally rather simple classical methods and the computationally intensive Bayesian methods is stressed.
KeywordsCortical Bone Bone Strength Gibbs Sampler Juvenile Rheumatoid Arthritis Predictive Distribution
Unable to display preview. Download preview PDF.
- Gelman, A. and Rubin, D. (1991). A single series from the Gibbs sampler provides a false sense of security. Technical Report No. 305. Department of Statistics, University of California at Berkeley.Google Scholar
- Geyer, C. (1992). A practical guide to Markov chain Monte Carlo. Preprint. School of Statistics, University of Minnesota.Google Scholar
- Guttman I. and Pena D. (1988). Outliers and influence: evaluation by posteriors of parameters in the linear model. Bayesian Statistics 3, 631–640.Google Scholar
- Johnson W. and Geisser S. (1983). A predictive view of the detection and characterization of influential observations in regression analysis. J. Am. Statist. Assoc. 137–144.Google Scholar
- McCulloch, R. and Tsay, R. (1991). Bayesian analysis of autoregressive time series via the Gibbs sampler. Preprint, Graduate School of Business, University of Chicago.Google Scholar
- Pettit L. I. and Smith A. F. M. (1985). Outlier and influential observations in linear models. in Bayesian Statistics 2, 473–494.Google Scholar
- Peruggia, M., Santner, T., Ho, Y-Y. and McMillan, N. (1992). Hierarchical Bayes analysis of circular data with autoregressive errors: modeling the mechanical properties of cortical bone. Technical Report No. 493. Department of Statistics, The Ohio State University.Google Scholar
- Sutherland, D. H., Olshen, R. A., Biden, E. and Wyatt, M. (1988). The Development of Mature Walking. Mac Keith Press, London.Google Scholar
- Smith, A. F. M. (1991). Private Communication.Google Scholar