The application of Local Indicators for Categorical Data (LICD) to explore spatial dependence in archaeological spaces

Abstract Global and local analyses of spatial autocorrelation are commonplace in spatial archaeology. However, they are exclusively focused on continuous numerical parameters, even though logical (presence/absence) and categorical parameters are equally frequent in archaeological research. Global tests of spatial dependence for categorical data are routinely used in other fields, and local versions of these tests (known as LICD) have recently been developed. This paper provides a detailed description of such methods, and presents the first adaptation and application of LICD to archaeological data. Different LICD versions have been tested on two case-studies: (a) an archaeological grid, with object presence or absence recorded for each cell; (b) Historic Landscape Characterisation, with the origin of character types (mediaeval, post-mediaeval or modern) recorded for each region. These examples seek to showcase and promote the use of LICD in landscape and intra-site archaeology.