This study proposes the use of regression discontinuity design (RD) in electoral systems and cross-national public opinion research. As an illustrative example, we use data from the Comparative Study of Electoral Systems project in an attempt to identify a causal effect of representation on respondents' attitudes toward the state of the economic and political system in their country. RD exploits a strict cutoff value of a variable- in this case the threshold for representation that is common in many parliamentary democracies-and employs it as a treatment assignment mechanism. Under certain assumptions, if a discontinuity in the estimation is observed at the cutoff value, then this discontinuity can be used to estimate a local average treatment effect. Though in the analysis of two dependent variables (satisfaction with democracy and subject assessment of economic performance) a discontinuity is observed, in neither case can this discontinuity be attributed causal significance due to the fact that the key identifying assumption for RD-that of conditional continuity- appears to have failed based on on an analysis of potential covariates. Despite this failure to identify the causal effect, we propose additional techniques that hold promise for identification of such effects in similar situations. [ABSTRACT FROM AUTHOR]