Summary: We are interested in studying the spatial dependency between the positions of on and off cholinergic amacrine cells because we hope this will tell us something about how the two cell types emerge during development. Our goal in is to demonstrate how recently developed Monte Carlo methods for conducting likelihood-based analysis of realistic point process models can lead to sharper inferences about the bivariate structure of the data. In particular, we will formulate and fit a bivariate pairwise interaction model for the amacrines data, and will argue that likelihood-based inference within this model is both statistically more efficient and scientifically more relevant than ad hoc testing of benchmark hypotheses such as independence.
For the entire collection see [Zbl 1084.62501].