Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
We use longitudinal data from an Irish household survey to measure the union wage premium. A subsample in which the worker’s payslip was seen by the interviewer is unlikely to have measurement error for the union variable. The results support the finding that measurement error leads to a large downward bias in fixed-effects estimates of the union effect but indicate that ability bias has a small effect on the average union wage premium.