Instrumental variables

Experimental instrumental variables

This method is used to estimate the causal effect of variables on an intervention.

The instrumental variables method (IV) is described by Duncan Chapman on the Urban Institute’s website as “one of the more compelling quasi-experimental options of estimating impacts, largely because the assumptions needed to justify the IV option are often more plausible than those needed to justify other options, such as regression”

This method involves identifying instrumental variables; variables that impact outcomes by affecting a key independent variable. The method can also be used to control for measurement errors.



Chaplin, D. (2012). Instrumental variables options. Retrieved from (archived link)

'Instrumental variables' is referenced in: