摘要: This paper has two aims: first to describe methods, issues, and outcomes involved in matching data from the Insurance Component of Medical Expenditure Panel Survey (MEPS-IC) other business microdata collected by US Census Bureau, second present some simple results that illustrate usefulness such combined data. We linking MEPS-IC with 1997 Economic Censuses (EC), but also discuss possible sources An issue any linkage is whether linked sample remains representative large enough be useful. The EC are attractive because, given survey’s broad coverage sample, most can matched it. use EC/MEPS-IC construct productivity measures useful auxiliary examining employers’ health insurance offering decisions.