Abstract:
|
Co-exposure to multiple toxicants may generate non-negatively correlated exposure variables. To study the effects of these exposure variables on a continuous health outcome, we can use a linear model with a weighted sum of standardized exposure variables for the predictor, and its coefficient for the overall effect. The unknown weights typically range from zero to one, and the exposure variable with a larger weight contributes more to the effect on the outcome. Because the weight parameters present only when the parameter for the overall effect is non-zero, testing hypotheses on the overall effect can be challenging, especially when the number of exposure variables is above two. This paper presents a working model based approach to test specific hypotheses, including two tests for detecting the overall effect, and one test to detect unequal weights when the overall effect presents. We apply these approaches to investigate the effect of co-exposure to two neuro-toxicants, arsenic and manganese, on children's covariates-adjusted cognitive test scores.
|