Every time I think I know what's going on, suddenly there's another layer of complications.
Part 1:
Noncollapsibility, confounding, and sparse-data bias. Part 1: The oddities of odds - Journal of Clinical Epidemiology (jclinepi.com)
Part 2:
Noncollapsibility, confounding, and sparse-data bias. Part 2: What should researchers make of persistent controversies about the odds ratio? - Journal of Clinical Epidemiology (jclinepi.com)
generalized linear model - Is there a mathematical definition of non-collapsibility? - Cross Validated (stackexchange.com)
Estimating and contextualizing the attenuation of odds ratios due to non collapsibility: Communications in Statistics - Theory and Methods: Vol 46, No 2 (tandfonline.com)