A one-unit increase in <testosterone> concentration, here $1\,\mathrm{ng/dL}$, multiplies the expected offspring count by \b[$\boxed{e^{\beta_T}}$] under the <Poisson regression> with a <log link>. Thus the exact percentage change in the conditional mean is \b[$\boxed{100(e^{\beta_T}-1)\%}$]. The <regression coefficient> $\beta_T$ itself is the change in the logarithm of the expected count, not an additive change in offspring number.

Solution

Past exam of the systems biology course of the University of Cambridge / 2024 / Paper 3 / 1 / j / Solution

 Solution (source code)