This paper presented the results from our analysis of three items in the National Character Survey. Since we were in possession of time-series data covering a twenty-five year period, we sought both to highlight the changes in attitudes which have taken place in post-war Japan, and to offer some insight into the processes producing these shifts. 1) Major shifts in attitudes have taken place among Japanese adults. Our analysis suggests that these shifts are not due solely to the process of population replacement. Even past their formative years, individuals change their views, and often quite rapidly. 2) Shifts in attitudes in different areas are not always synchronous. Not surprisingly, the impact of social, economic, and political developments is not uniform across different attitudinal areas. 3) There are important attitudinal cleavages among Japanese. The most notable among these cleavages is one based on sex.
A new algorithm of multidimensional scaling is proposed. It performs metric or nonmetric analyses of two- or three-way data. It is a simple, convergent algorithm analogous to ALSCAL, but it approximately optimizes the least-squares fit of distances (not squared). This paper mainly considers the nonmetric two-way case.
This paper is concerned with the first part of a series of experiments involving the image formation process of simple meaningless line figures. Iijima (1973) proposed a “mathematical figure theory” in his pattern recognition theory. In this theory he emphasizes a definition of the relationship between original figure and figure image formed on the retina before feature extraction processing. This paper reports an attempt to find clues of basic rules of ordinary human perceptional behavior. Such practical study of pattern recognition psychology of form perception are scarce. The main purpose of Experiment 1 to identify the general characteristics which affect the image formation process when a person views unknown figures. Factor analysis has been performed on the scale value of “conspicuous” figure which were selected intuitively out of the presented stimulus figures. Some characteristics of figures were extracted as image formation factors. Experiment 2 was conducted to verify the results of Experiment 1 from another point of view. The data for “impressive” figures was collected by stimulus reduction using a tachistoscope. In Experiment 3, the results of above two experiments were validated more directly in observation of eye movement responces for stimulus figures. From these results, it is indicated that the practical methods used here may be an effective approach to investigate the basic elements of human pattern recognition.
A method of simultaneous scaling of categories is proposed in order to disclose the structural interdependency of a set of discrete variables, in which categories within one discrete variable are regarded as a set of dummy variables. From this viewpoint, we propose a tentative method of simultaneous scaling by the use of generalized canonical correlation analysis for several sets of variables proposed by Horst (1961). An application of the generalized canonical correlation analysis to discrete variables is demonstrated by making use of the following three different criteria; i.e., (a) Dual scaling, (b) the sum of the correlation coefficients and (c) the sum of the squared correlation coefficients.
A “formal coalition” in a voting body is defined as a subgroup of members in which their vote is completely dependent, voting as a bloc. The formation of such a formal coalition sometimes yields the unexpected effects on the power of members in the voting body. They are the non-increase of power of coalitional members and the increase of power of non-coalitional members. This paper shows that the unexpected effects above will occur with respect to the Banzhaf power index and explores that the formal coalition of what members will yield what effects on the Banzhaf power of members. Throughout the paper, it is assumed that there is only one two-member formal coalition in the voting body and that there are no other formal coalitions in it. Using the well-known concepts of veto and dummy, we then obtained the necessary and sufficient condition that the unexpected effects on coalitional member's power will occur. In addition, introducing the three new concepts about non-coalitional members, we obtained several sufficient conditions that the unexpected effects on non-coalitional member's power will occur. Finally, by use of the obtained results we analysed the effects of all possible two-party formal coalitions on the power distribution in the House of Representatives of Japan.
The present paper is a review of recent theoretical and methodological developments in multidimensional scaling and its related methods in Japan. The term multidimensional scaling (MDS) is used in two senses. One is a narrow sense, and the other is a wider sense. The former is a technical term which is divided into metric MDS and non-metric MDS. The latter has many variations in multidimensional data analysis. In this review, MDS in a narrow sense and its closely related methods, which are a part of MDS in a wider sense, are taken into consideration. And Japanese works are introduced.