We connect gender disparities in research output and collaboration patterns in economics. We first document large gender gaps in research output. These gaps persist across fifty years despite a significant increase in the fraction of women in economics during that time. We further show that output differences are closely related to differences in the coauthorship networks of men and women: women have fewer collaborators, collaborate more often with the same coauthors, and a higher fraction of their coauthors collaborate with each other. Taking into account coauthorship networks reduces the gender output gap by 18%.