This paper reports on the use of laboratory experiments to identify the effect of information on voting behavior and electoral outcomes in the direct legislation environment. I showed that when incompletely informed voters know that the setter has paid a certain amount to contest an election, they can use this information to increase the likelihood that they cast the same votes they would have cast had they possessed complete information. As a consequence of the way voter strategies were affected by information, the likelihood that the "incomplete information" electoral outcome was the same as the electoral outcome that would have been chosen by a completely informed electorate increases, as does the responsiveness of direct legislation outcomes to "complete information" voter preferences. While this research does not resolve long standing questions about the responsiveness of democratic institutions, it does add to what we understand about responsiveness by demonstrating conditions under which incompletely informed voters can generate the electoral outcomes that they would have if better informed. This research also informs the debate about the use of the referendum and initiative to determine policy. My answer to the question: "Is direct legislation is a useful mechanism for obtaining policy outcomes that correspond to the "will of the majority" or is it a way for small, wealthy interest groups to subvert the "popular will,"" is that direct legislation can be both. When voters are badly informed (or the electoral alternatives are reasonably complex), and there are no effective information cues available, small groups who have enough resources to obtain agenda control can use direct legislation to obtain preferred outcomes. When meaningful cues are available (or the effect of electoral alternatives are easy to understand), then direct legislation can be useful tool for the implementation of majority-preferred policies. © 1994 Kluwer Academic Publishers.