While a large number of studies have described animal social networks, we have a poor understanding of how these networks vary with ecological and social conditions. For example, reproductive periods are an important ...While a large number of studies have described animal social networks, we have a poor understanding of how these networks vary with ecological and social conditions. For example, reproductive periods are an important life-history stage that may involve changes in dominance relationships among individuals, yet no study to date has compared social networks of do- minance interactions （i.e. dominance networks） across reproductive contexts. We first analyzed a long-term dataset on captive so- cial groups of the cooperatively breeding cichlid Neolamprologuspulcher, and found that eviction events were significantly more common around reproduction than expected by chance. Next, we compared the structure of dominance networks during early pa- rental care and non-reproductive periods, using one of the first applications of exponential random graph models in behavioral biology. Contrary to our predictions, we found that dominance networks showed few changes between early parental care and non-reproductive periods. We found no evidence that dominance interactions became more skewed towards larger individuals, became more frequent between similar-sized individuals, or became more biased towards a particular sex during parental care. However, we did find that there were relatively more dominance interactions between opposite-sex dyads in the early parental care period, which may be a by-product of increased sexual interactions during this time. This is the first study in behavioral ecology to compare social networks using exponential random graph modeling, and demonstrates a powerful analytical framework for future studies in the field [Current Zoology 61 （1）： 45-54, 2015].展开更多
文摘While a large number of studies have described animal social networks, we have a poor understanding of how these networks vary with ecological and social conditions. For example, reproductive periods are an important life-history stage that may involve changes in dominance relationships among individuals, yet no study to date has compared social networks of do- minance interactions （i.e. dominance networks） across reproductive contexts. We first analyzed a long-term dataset on captive so- cial groups of the cooperatively breeding cichlid Neolamprologuspulcher, and found that eviction events were significantly more common around reproduction than expected by chance. Next, we compared the structure of dominance networks during early pa- rental care and non-reproductive periods, using one of the first applications of exponential random graph models in behavioral biology. Contrary to our predictions, we found that dominance networks showed few changes between early parental care and non-reproductive periods. We found no evidence that dominance interactions became more skewed towards larger individuals, became more frequent between similar-sized individuals, or became more biased towards a particular sex during parental care. However, we did find that there were relatively more dominance interactions between opposite-sex dyads in the early parental care period, which may be a by-product of increased sexual interactions during this time. This is the first study in behavioral ecology to compare social networks using exponential random graph modeling, and demonstrates a powerful analytical framework for future studies in the field [Current Zoology 61 （1）： 45-54, 2015].
