"In 2001 the Minimum Income Guarantee for UK pensioners was reformed, changing the structure and level of benefits. We evaluate the behavioural response to this reform, using nonparametric analysis of data on some pensioners interviewed before and others after the reform, using matching on simulated pre- and post-reform entitlements and other characteristics. We consider the effect of measurement error in simulated entitlements and argue that nonparametric and conventional parametric approaches are complementary, since they bound the true reform effect in simple cases. The take-up response is found to be significant and positive, with evidence of larger impacts from the nonparametric analysis."

Support: Digital