The use of survival models involving a random effect or ``frailty" term are becoming more common. Usually the random effects are assumed to represent different clusters, and clusters are assumed to be independent. In this paper, we consider random effects corresponding to clusters that are spatially arranged, such as clinical sites or geographical regions. That is, we might suspect that random effects corresponding to strata in closer proximity to each other might also be similar in magnitude.
Such spatial arrangement of the strata can be modeled in several ways, but we group these ways into two general settings: (geostatistical approaches), where we use the exact geographic locations (e.g., latitude and longitude) of the strata, and (lattice approaches), where we use only the positions of the strata relative to each other (e.g., which counties neighbor which others). We compare our approaches in the context of a dataset on infant mortality in Minnesota counties between 1992 and 1996. Our main substantive goal here is to explain the pattern of infant mortality using important covariates (sex, race, birth weight, age of mother, etc.) while accounting for possible (spatially correlated) differences in hazard among the counties. We use the GIS ArcViewTM to map resulting fitted hazard rates, to help search for possible lingering spatial correlation. The DIC criterion (Spiegelhalter et al., 1998) is used to choose among various competing models. We compare use of our time-to-event outcome survival model with the simpler dichotomous outcome logistic model. Finally, we summarize our findings and suggest directions for future research.
See www.biostat.umn.edu/~bradLearning Objectives: At the conclusion of this presentation, the participant will be able to: 1. Describe the use of random effects to model spatial correlation structures, distinguishing between geostatistical and lattice approaches. 2. Discuss issues involving model choice, and criteria for distinguishing among models, for spatially correlated data. 3. Indicate how maps depicting fitted values from spatial models can help explore residual patterns of correlation for which the model has failed to account.
Keywords: Access to Health Care, Biostatistics
Presenting author's disclosure statement:
Organization/institution whose products or services will be discussed: None
I do not have any significant financial interest/arrangement or affiliation with any organization/institution whose products or services are being discussed in this session.