In this study, we investigated whether the parsing was performed in an incremental manner or a delyaed manner. To address this issue, we examined two types of sentences which are identical except their main-clause predicates. The Full Attachment Model (an incremental model) and the Head Driven Model (a delay model) predict that reanalysis will occur in one of two different types of sentences respectively. Event-Related brain Potentials (ERPs) were recorded while subjects read these sentences. The results revealed that the ERPs elicited in one type of sentence were significantly more positive-going than those in the other. This ERP effect was comparable to the P600 which was assumed to be the electrophysiological marker of reanalysis. The result was compatible with the prediciton of the Full Attachment Model, but contradicts the prediction of the Head Driven Model. We, therefore, concluded that the parser pursued syntactic analyses not in a delayed manner but rather in an incremental manner.