In this chapter, we propose a log-linear model for the biases observed when analyzing model communities data. Our model expands the recent work from McLaren, Willis and Callahan (MWC) [eLife, 8:e46923 ...

The logistic model and the log-linear model provide the same parametric description of disease risk: α 1t, β 1t, and γ 1t have exactly the same interpretations in both models. The log-linear ...