Search

Objective: To test whether reported associations between race/ethnicity and breast cancer estrogen receptor (ER) status are inflated due to missing ER data, lack of socioeconomic data, and use of the odds ratio (OR) rather than the prevalence ratio (PR).Methods: We geocoded and added census tract socioeconomic data to all cases of primary invasive breast cancer (n = 42,420) among women diagnosed between 1998 and 2002 in two California cancer registries (San Francisco Bay Area; Los Angeles County) and analyzed the data using log binomial regression.Results: Adjusting for socioeconomic position and tumor characteristics, in models using the imputed data, reduced the PR for the black versus white excess risk of being ER--from 1.76 (95% CI: 1.66, 1.86; adjusted for age and catchment area) to 1.47 (95% CI: 1.38, 1.56). The latter parameter estimate was 16% greater (i.e., 1.56) in models excluding women with missing ER data, and was 43% greater when estimated using the OR (i.e., 1.82).Conclusion(s): Studies on race/ethnicity and ER status that fail to account for missing data and socioeconomic data and report the OR are likely to yield inflated estimates of racial/ethnic disparities in ER status. [ABSTRACT FROM AUTHOR]

Influence analysis and leverage analysis are important and well-established adjuncts to ordinary least squares (OLS) regression, but analogous regression diagnostics are not generally available for multivariate regression problems. This article describes measures of influence and leverage for a generalized least squares (GLS) estimator of the regression coefficients in a class of multivariate linear models for repeated measurements. When the covariance matrix of the observation vectors is known, the GLS estimator can be expressed as an OLS estimator calculated from transformed variables. In this situation, the multivariate regression diagnostics are directly related to the univariate measures. When the covariance matrix is unknown, however, multistage estimation procedures are required. We describe measures of influence and leverage for a three-step estimator that uses the residuals from an initial OLS regression to estimate the covariance matrix of the response vectors. These diagnostics account for the influence of individual data values on the estimated covariance matrix. The article reports on two different measures of influence and the relation between them: (a) derivative influence, the differential change in an estimated parameter or predicted value resulting from a slight perturbation in the weight assigned to a given observation or vector of observations, and (b) deletion influence, the change in a parameter estimate resulting from the deletion of the vector of observations. Both of these measures can be represented as the sum of components that correspond to the stages of the GLS estimation. Examination of the relative asymptotic sizes of these components and of the differences between derivative and deletion influence leads to modified versions of these... [ABSTRACT FROM AUTHOR]

Two methods, one based upon grouping, are proposed for fitting o regression line to bivariate data when the means of the observations have known order along the line. The two procedures are compared with respect to their limiting distributions and asymptotic efficiency. Criteria are given for choosing one of these procedures to fit the line. [ABSTRACT FROM AUTHOR]