Is less more? A commentary on the practice of ‘metric hacking’ in animal social network analysis

摘要: The use of social network analysis to quantify animal relationships has increased exponentially over the last two decades. A popular aspect is individually based metrics. Despite diversity metrics that exist and large number studies generate metrics, little guidance exists on type should be analysed in a single study. Here, we comment ‘hypothesize after results are known’ (HARKing) phenomenon context analysis, practice term ‘metric hacking’ define as statistical criteria select which rather than priori choice research hypothesis. We identify three situations where metric hacking can occur quantifying metrics: (1) covariance among explanatory variables same model; (2) response multiple models; (3) between model. outline several quantitative qualitative issues associated with hacking, provide alternative options appropriate avoid hacking. By increasing awareness hope encourage better for selection analysis.