The matching method for treatment evaluation does not balance selective unobserved differences between treated and non-treated. We derive a simple correction term if there is an instrument that shifts the treatment probability to zero in specific cases. Policies with eligibility restrictions,...

This paper examines changes in the distribution of wages using bounds to allow for the impact of non-random selection into work. We show that bounds constructed without any economic or statistical assumptions can be informative. However, since employment rates in the UK are often low they are...