In this talk, I have two aims: (1) to present my own work on survey errors and endogeneity, and (2) to situate it in an ongoing debate about the future of social science. Recent years have witnessed a "statistical crisis" spurred by concerns over limited research transparency and institutional practices favouring the proliferation of false positive results. While this development has been most pronounced in disciplines such as social psychology, as a buzzword "replicability" has filtered down to sociology as well. I argue that certain concerns underlying the current crisis may have less traction in sociology, while important challenges faced by our discipline remain unaddressed by the proposed remedies. Insofar as a statistical crisis in sociology is warranted, it should have a different flavour from that of neighbouring disciplines.
This event is part of the Sociology Seminar Series.