ABSTRACT
Hierarchical or multilevel designsHierarchical design are common, collecting observations repeatedly from the same individual or grouping individuals into blocks or subunits, e.g., different assays, animal cages, or laboratories. Any factor that restricts a random sampling design needs to be included in the dose-response model; therefore, for a hierarchical design, the correlation between observations from the same experimental unit needs to be taken into account. The effect of drought stress on Brassica oleraceaBrassica oleracea was investigated by selecting drought-stess-resistant lines out of a population of different double-haploid genotypes. For simple hierarchical dose-response experiments, the package medrc provides a user-friendly interface similar to the function drm(), using the package nlme in the background. Streibig et al. investigated the inhibition of photosynthesis in response to two synthetic photosystem II inhibitors, the herbicides diuron and bentazon.
