Data, R Code, and Output Supporting: Using lorelograms to measure and model correlation in binary data: Applications to ecological studies

These files contain data, R code and associated output supporting results presented in “Iannarilli, F. , Arnold, T. W., Erb, J. and Fieberg, J. R. (2019). Using lorelograms to measure and model correlation in binary data: Applications to ecological studies. Methods Ecol Evol.”. In this paper, we introduce in the ecological literature the lorelogram, a statistical tool for quantifying correlation patterns in binary data, with novel applications to species distributional and camera-trap studies. We demonstrate the usefulness of the lorelogram via several motivating examples illustrating its use a) as a data-based method for objectively determining space- or time-to-independence between subsequent detections; and b) for describing correlation and behavioural patterns at different time scales, including short-time scales (e.g., minutes) common to camera trap data. This information can then be used to formulate an appropriate statistical modelling framework that allows researchers to explore effects of additional covariates (at different scales), while properly accounting for correlation.