Kentaro Fukumoto

小学校6年生だったお姉ちゃんの君は、卒業直前に級友との思い出を深めるはずだった最後の1カ月が、いきなり消えてしまった。中学校に上がっても入学式はなく、新たな同級生にも会えなかった。妹の君も、家で勉強するための教材も大して配られなかったから暇…

application/pdf 研究報告

In this research, we propose a new biclustering method for extracting communities from binary matrices which represent a binary relation. A binary relation can be represented as a bipartite graph or a binary matrix. Many effective clustering methods for extracting communities from graphs and matrices have been proposed. In this paper, the objective data is a bid data which represent a participation record of companies in bids. A community in bid data means a set of companies which often participated in multiple bids. We aim at applying the community extraction to finding bid rigging groups. In order to achieve the goal, we propose a biclustering method based on the density of bipartite graphs and the characteristic extraction by the nonnegative matrix factorization.

application/pdf 研究報告

application/pdf 研究報告

Why so many legacy Diet members? This article estimates the effect of being legacy candidates on the "vote succession rate" (i.e. the ratio of citizens who vote for a candidate in an election to citizens who also will vote for the candidate's successor in the next election). This study proposes comparing legacy challenger with non-legacy challengers, not incumbents. This new statistical method estimates the effects of party and personal votes on the vote succession rate as well. We analyze the data of the Liberal Democratic Party candidates under the single member district system and find as follows: (i) the legacy challengers' advantage against non-legacy challengers is not less than the incumbents'; (ii) the effect of party votes is the same as that of legacy votes, but the effect of personal votes is not confirmed; and (iii) the legacy challengers' advantage emerges not because they are young or reelected many times.

This article defines the mechanical effect of electoral systems according to the literature on causal inference. An electoral system is decomposed into six parts: assembly size, district magnitude, malapportionment, geographical vote distribution, interaction between these, and electoral formula. The article proposes a new index of disproportionality, which is derived from the log likelihood ratio of the multinomial distribution. The mechanical effect of electoral systems on disproportionality is illustrated using simulation as well as election data from both Houses of Japanese Diet from 1890 to 2007.