The articles in the Festschrift nicely mirror Adrian’s own contributions, both in subject area and also in his belief that methods based on established statistical principles are generally to be preferred over more ad hoc approaches. The first four papers are concerned with stochastic geometry and stereology. They include a beautiful (and beautifully illustrated) review of some recent work in stereology (Jensen 2021); two papers on specific applications which speak to the maxim that ‘there is nothing so practical as a good theory’ (Stoyan, Beneš & Seitl 2021; Christoffersen, Møller & Christensen 2021); and some novel methodology for detecting outliers in random sets (Cascos, Li & Molchanov 2021).
The next set of articles are concerned with spatial statistics. In keeping with Adrian’s own approach, the contributions address significant practical issues for the analysis of point pattern data. These include the use of conditional intensity (Diggle 2021); a new method for estimating the inhomogeneous K-function and the pair correlation function (Shaw, Møller & Waagepetersen 2021); a pair of papers about information criteria for point process models, and in particular how to measure the effective sample size when computing the Bayesian information criterion (Choiruddin, Coeurjolly & Waagepetersen 2021; Renner, Warton & Hui 2021); and work on spatially adaptive kernel estimation of the intensity function (van Lieshout 2021).
The special issue concludes with delightful articles that promote the following ideas: the central role of statistical principles in data analysis, and the importance of clear thinking in the face of deceptively complex probability problems. Cressie (2021) offers some advice to data scientists seeking statistical principles, while Gill (2021) wrestles with the classic ‘Two Envelope Problem’ in a characteristically entertaining manner.More Details