We use cookies to ensure that we give you the best experience on our website. You can change your cookie settings at any time. Otherwise, we'll assume you're OK to continue.

Durham University

Research & business

View Profile

Publication details

Wilson, Paul & Einbeck, Jochen (2015), A simple and intuitive test for number-inflation or number-deflation, in Wagner, Helga & Friedl, Herwig eds, 2: 30th International Workshop on Statistical Modelling. Linz, Austria, Statistical Modelling Society, Linz, 299-302.

Author(s) from Durham


We present a test of zero-modification which checks if the number
of zeros is consistent with the hypothesized count distribution. This test is easily
extended to test for inflation or deflation of any non-negative values, and,
by performing multiple tests of inflation/deflation of the counts present in observed
data relative to any given model, it is possible to assess the suitability
of that model. Such multiple testing may be represented diagrammatically. The
test for number-inflation/deflation is informally called the “Christmas Eve Test”
as the original idea occurred to the main author on December 24th, 2014, and
the diagrammatic method the “Durham Diagram” as it was developed during
preparation for a talk at Durham University.


Conference Dates: 6-10 July 2015