This study investigated how individuals interpret the overall meaning of two Japanese statements of verbal probability reporting the likelihood of an event's occurrence, and what kinds of factors affect these interpretations. Previous research has focused mainly on the interpretation of verbal probability expressed in a single statement regarding the occurrence of a single event. Although we are often given multiple statements about the likelihood of a single event's occurrence in our daily conversation, few studies have examined such instances of multiple information presentation. In this experiment, participants answered a series of choice questions presented in booklets. From their answers, certainty equivalents of single verbal probability statements and of two statements were calculated. The data show that interpretations of the overall meaning of the two probability statements were affected by the following factors: factors of the type of outcome (gain or loss), presentation order, and degree of inconsistency between the statements. Interpretations of the overall meanings were less than the simple average of two statements, and were not interpreted as larger (or smaller) than the likelihood of each statement.
We propose a propensity score weighted M-estimation method for marginal parametric models for groups in which all subjects are missing. It is shown that the propose estimator is consistent and its limiting distribution is normal. We also propose a hypothetsis testing method using the proposed estimator. Using the proposed method, we estimate the intervention effect of maternal smoking during pregnancy on the development of the child's cognitive functioning from data obtained from the US National Longitudinal Survey of Children and Youth.
The main objective of this special issue is to show some data analyses of the East Asia Value Survey conducted by the cross-national survey team centered in the Institute of Statistical Mathematics (ISM) during 2002-2004. This survey is closely linked with the longitudinal survey on the Japanese National Character in the past half-century and the cross-national comparative survey in the past three decades by ISM. Our past data analyses have shown that some stability and some changes of peoples' attitudes and social values. The data analyses on the present survey with those past surveys will be useful for the understandings of the countries and regions under development of international cooperation or unification as the “East Asia Community.” This is an introductory paper. I will explain about the survey on “Japanese National Character (JNC)” as well as its historical background in Section 1, and explain about the East Asia Value Survey in the relationships with the cross-national comparative survey as an extension of JNC survey in Section 2. Finally, in Section 3, I will briefly explain the significance of development of a Behaviormetric study on civilization as “Data Science”, which is based on the rigorous statistical theory of sampling methods. Also I will explain about our paradigm of survey study, what is called Cultural Manifold Analysis (CULMAN). Some detailed data analyses on several topics by the other members of the survey and myself will follow this introductory paper.
The objective of this paper is to discuss the sense of trust of the East Asian countries (Japan, China [Beijing, Shanghai, & Hong Kong], Taiwan, South Korea, & Singapore) as it is reflected in the response data of our East Asia Value Survey conducted during 2002-2005. I will present some data analyses on the variability of people's trust systems in order to explore what aspects of their sense of trust are stable over many decades and what aspects are variable under the longitudinal changes of economic and political conditions. Firstly, I will explain briefly the background of this study. Secondly, I will explain the history of our longitudinal and a series of cross-national surveys on national character. Thirdly, I will summarize some aspects of people's sense of trust in our longitudinal survey of Japanese national character as well as cross-national comparative surveys. I focus my analysis on the data of the East Asia Survey, but I integrate also data of other surveys such as our seven-nation survey conducted during 1987-1993, General Social Survey and World Value Survey. Finally, I will provide some comments for the future research.
Confucianism, as the typical Chinese thought, has influenced the people's attitude toward life, set the patterns of living and the standards of social values in China, Japan, Korea, and the other Oriental countries historically. Confucian ethical teachings include the traditional values such as benevolence & humaneness (Ren), righteousness (Yi), ritual & etiquette (Li), love within the family (Xiao), loyalty to the state (Zhong), honesty & trustworthiness (Xin) etc. This paper presents the results of comparative analysis of Chinese, Japanese, and Korean values based on the East Asian values survey conducted with the face-to-face interview in the mainland China, Hong Kong, Taiwan, Korea, and Japan from October 2002 to November 2003. Data analysis in this study was mainly focusing on some aspects of people's attitudes toward family, marriage, gender, traditional values using correspondence analysis. Except general pattern classification based on “Traditional-Modern” axis, the relationship between people's attitudes and their attribute variables such as gender and age have also been identified.
This study focuses on the similarities and differences of the work values among the peoples studies in our East Asia Value Survey conducted during 2002-2004. It shows useful aspects of cross-national comparison on the East Asia. Some researchers consider that the East Asia is under the influence of Confucianism, as the western countries under the influence of Christianity. It is said that scholars and civil servants are more respected than practical workers in Confucian ethics. Therefore, Maoism in China emphasized practical workers (farmers and labors) more respected. On the other hand, Confucian ethics of Japan was accepted among samurai (warrior)'s ethics at Edo era, may have been lost in the stream of democratization after Meiji era and in the reorganization after World War II. The questionnaire of our East Asia Value Survey included two open questions about the occupation: “What occupation do you respect most ?”; “What is the occupation you yourself would like to have ?” The results of these responses indicate that the three categories as “Teacher”, “Medical Doctor” and “None or Don't Know” are useful criteria for the comparison among East Asian Peoples.
The aim of the study was to examine the relationship between health and social and cultural factors in cross-cultural settings among general populations in the East Asia using statistical survey results of “East Asia Value Survey” in 2002-2004 and “Health and Culture Survey” in 2003. The target population included adults aged 20 years and older residing in each nation and area. Items related to health were satisfaction of health and self-rated health symptoms, while those related to social and cultural factors were gender, age, education, life satisfaction, family life satisfaction, interpersonal relation to trust, anxiety, and self-rated social class. Relationships were examined using Hayashi's Quantification Method III, logistic regression model, and general regression model. It was shown that satisfaction of life, self-rated social class were related to health satisfaction, while self-rated health was much more related to anxiety in addition to satisfaction of life.
The purpose of the present article is to show the frameworks of consumer's multiple purchase behaviors and the influences of store arrangement on these frameworks. There has been an increasing interest in consumer's multiple purchase behaviors. Thus, many significant studies have been made on consumer's multiple purchase behaviors. Most of these studies used the purchase data provided by supermarkets and a very few used the purchase data provided by department stores. Therefore, we focused on in-store marketing at a department store with emphasis on the analysis of the influences of store arrangement on consumer's multiple purchase behaviors. The purchase data provided by the department store were analyzed by INDSCAL. The data were collected from the 16 departments for two years during which store arrangement changed once. On the basis of the present analysis, the authors found that some frameworks of departments exist and store arrangement influences these frameworks.
In this paper we surveyed several fit indices, model modification methods, and other related previous studies in structural equation modeling. Inconsistency in results was detected from the review of the literature. To obtain more reliable knowledge, we performed simulation studies some ten times larger in scale than previous studies to examine the soundness of Golden Rules and the relationship between indices. Also, bias in the distribution of likelihood ratio statistics which depends both sample size and model complexty was indicated as a result of another large simulation study. This could be one of the causes of inconsistency in former studies of fit indices. We also examined fit indices for structural equation modeling with mean structure, multiple groups and categorical indicators. Stepwise estimation methods, model modification methods, and Item Parceling Issues were also reviewed.