Cross-cultural survey data for Japan and France were analyzed in various aspects by a quantification method of response pattern, equivalent to Benzécri's analyse des correspondances. New findings regarding consistencies and differences in ways of thinking between the two peoples emerged. Methodological suggestions are given throughout the data analysis.
A stability of clusters can be defined by the tolerance for a small disturbance in the data. An estimating expression of the stability is shown in reference to the case of single-linkage algorithm. As one of the applications of this stability, the method of deciding on the number of single-linkage clusters is proposed. Some numerical examples are shown in order to compare the method with other conventional methods.
In order to discuss selected issues on the methodology of social utility assessment, this paper shows an illustrative procedure in which consumer preferences for several performances and costs of residential air-coolers are analyzed. The focuses are related to the selection of a fundamental set of relevant attributes, the composition of questionaires for field data gathering from consumers, and the estimation of multiattribute utility functions on the social values. In the estimation process of social utility functions, a kind of random utility model of group preferential choice is employed. This model can be viewed as an additive utility version of Thurstone's model associated with the irrelevancy of common aspects among choice alternatives as in Tversky's Elimination by Aspects model. The assessed results seem to be moderately valid in reference to diffusion tendency of air-coolers in the real market.
Survey findings from personal interviews with respondents in three countries (Japan, West Germany, and the United States) are used to determine differences in attitudes toward the role of women in these respective countries. Findings are first classified for each country by sex and age groups on the basic topics of “men and women”, “marriage”, and “the family”. Overall differences between countries are then analyzed by an application of Quantification Theory (III). It is found that attitudes toward the social role of women range more widely between different countries than between sex or age groups within any given country.
Examined were Japanese & US Rs' attitudes toward “way of life” related to work. Two sets of data were utilized: (1) Cross-societal comparative data obtained through 1978 surveys carried out in the US & Japan, gathered from a national sample of adults in each society, chosen on the basis of a multistage probability sampling. (2) Time-series data collected at 5-year intervals since 1953 by the Institute of Statistical Mathematics. These data consisted of national samples of adults 20+ years of age. In order to delineate the character of interdependence undergirding the systems of beliefs in these two societies, factor analytic technique was applied to the data. Systems of attitudes in the US & Japan reveal similarities over a wide spectrum of issues & concerns. Results suggest an essential similarity in outlooks toward different lifestyles. At the same time, however, the results reveal fundamental differences. Results obtained for the US display a dominant system containing “core” outlooks. In comparison, the pattern for Japan evidences two competing systems of outlooks: “old” & “new”. These differences derive from each society's sociocultural history, as well as its ecological setting. (Abstract in French appended.)