instrument) in multiple periods based on inverse probability weighting. Treatment selection and attrition may depend on both … endogeneity and missing outcomes. We use instrumental variables, pre-treatment characteristics, and short-term (or intermediate … we find that controlling for attrition considerably affects the effect estimates. …

endogeneity and attrition/non-response bias, using two instrumental variables. Making use of a discrete instrument for the … treatment and a continuous instrument for non-response/attrition, we identify the average treatment effect on compliers as well … as the total population and suggest non- and semiparametric estimators. We apply the latter to a randomized experiment at …

the sharp identified set for the local average treatment effect under the exclusion restriction of an instrument and the … deterministic monotonicity of the true treatment in the instrument. Even allowing for general measurement error (e.g., the …

bounds on the average treatment effect when an imperfect instrument is available. As in Nevo and Rosen (2012), we assume that … the correlation between the imperfect instrument and the unobserved latent variables has the same sign as the correlation … the imperfect instrument is less endogenous than the treatment variable can help tighten the bounds. We also use the …

causal model. This ‘no randomisation bias’ assumption is generally untestable but if violated would undermine the causal …