Suppose we take a sample of size n from a population and follow the ancestral lines backwards in time. Under standard assumptions, this process can be modeled by Kingman's coalescent, in which each pair of lineages merges at rate one. However, if some individuals have large numbers of offspring or if the population is affected by selection, then many ancestral lineages may merge at one time. In this talk, we will introduce the family of coalescent processes with multiple mergers and discuss some circumstances under which populations can be modeled by these coalescent processes. We will also describe how genetic data, such as the number of segregating sites and the site frequency spectrum, would be affected by multiple mergers of ancestral lines, and we will discuss the implications for statistical inference.