The need for tests dealing with different features of small area health data is less important with the increase in computation speed of computers and the access to MCMC methods. However there are many situations where exploratory testing could be useful and where MCMC methods are not readily useable or available.
In this paper, a number of simple tests are derived for the logistic model for case events. This model assumes that a control disease is available and that the events have a binary label relating to case or control state. The tests are derived from likelihood considerations and Monte Carlo critical regions are examined. A simulated evaluation of the tests is presented in terms of Monte Carlo power. A data example is considered.