In conducting an exploratory data analysis to study the hit mechanisms of manga and anime works with appealing supporting characters, the author began by assessing the volume and content of Twitter posts on Demon Slayer and observed that SNS not only facilitated communication between devoted fans, but also served to fulfill the desire to own merchandise and to provide a place for publication of derivative works. Furthermore, in an analysis using the Character Quantitative Survey unaided recall data, the top unaided recall works were classified into four types based on supporting character popularity patterns. The results obtained by creating a composite variable of unaided recall weighted by simple total based on the number of recall of the work's name or character and assessing the mean values and correlations of each variable measured for each work showed that the composite variable of unaided recall had a strong correlation with the indices of tie-in merchandise purchase and purchase intention, and with the indices of ‘high spirit and fun’ and ‘attention and impersonation’ in the field of offered experience.
This review addresses the development of computational models in educational psychology. First, we generally explained computational models and their background. Second, we searched academic articles relating to computational models in psychology and other fields. The search revealed that, on the one hand, international journals in behavioral or cognitive sciences include several articles relating to computational models, and the number is increasing in general psychology journals. On the other hand, domestic and international educational psychology journalsscarcely have relating papers. Third, we described the current challenges in educational psychology and how the ideas and analytical method on computational models would contribute to overcome these challenges.
The purpose of this study is to discussthe implementation and importanceabout the multinomial logit model of Bayesian Age-Period-Cohort analysis. Since the design matrix of three factorsdoes not become full rankdue to the identification problem derived fromlinear dependency between age, period and cohort, few studies have useda complex model. In contrast, this paper presents the practical multinomial logit model withefficient sampling by reparameterizationabout the constraints of assuming a random walk for each effect. Furthermore, we compared the estimates ofthe logit model andthe multidimensional modelabout political issuesthat should be considered from multiple perspectives. Using repeated cross-sectional survey in Japanfrom 1973 to 2013, the multinomial logit model was shown to be effectivebecause it was able to obtain a trendthat were not captured in the logit model.
This paper is an essay on nonrespondent bias in statistical random sampling surveys. In particular, it focuses on the personalities of respondents and nonrespondents in survey cooperation. First, I review previous relevant research on nonrespondent bias and outline the main points of the nonrespondent bias problem. Next, focusing on items related to interpersonal trust, I analyze personality differences between cooperative and non-cooperative respondents using time series data from the Japanese National Character Survey and its related surveys. I then present rules of thumb that may be useful for survey researchers dealing with nonrespondent bias. Finally, I discuss future issues. Particular mention will be made of social disparities in electoral voting and polling, i.e., people who tend to drop out of electoral voting and polling.
This study aims to uncover the mechanism by which certain groups of women developed a methamphetamine addiction and ended up incarcerated. The subjects are 202 female inmates incarcerated for violating the Stimulant Drug Control Law shortly before their release from Japanese penal institutions between January and May 2016. Estimation by structural equation model indicates that higher self-esteem is less likely to be associated with developing depression, and depression is more likely to be correlated with drug addiction. However, we find that the influences of the victimization experiences during childhood or adulthood are not significant for this group of female inmates. These results align with the more recent finding by Carbone-Lopez & Miller (2012) and Smith (2017). We discuss the implication of the result.
Causal mediation analysis estimates causal effects by focusing on the mediators between cause and outcome. Multiple causally related mediators are often strongly correlated, making the estimation of causal effects difficult. In addition, recent years have seen a number of mediators compared to a sample size. In this paper, we propose a two-step estimation method based on sparse partial least squares regression and pathway lasso. The proposed method can identify the causal pathways among many candidate causal pathways. The effectiveness of the proposed method is shown by simulation studies and a real data analysis.
The U.S. president influences the economy in many ways. However, the question of how the president perceives the economy has not been sufficiently analyzed, despite the fact that the president plays an important role in this mechanism. Using the Economic Report of the President of the United States as a case study, this study examines how the president perceives the economic situation. First, we conduct a sentiment analysis of the Economic Report of the President and quantify the positivity and negativity of the Economic Report of the President for each year using polarity values. We will then conduct a multiple regression analysis using this score as the dependent variable to analyze the factors that define the positivity of the President's economic perception. The results of the analysis showed that it was the unemployment rate, not political factors such as Congress and elections, that defined the president's economic perception.
While the crude mortality rate for lung cancer has been increasing year by year for both men and women, the age-adjusted mortality rate, which is calculated based on the base year population, has been decreasing since the 1990s. We will discuss the influence of specific generations on this peak in age-adjusted mortality rates by comparing age-adjusted mortality rates based on multiple base-year populations and by examining time-series trends in the percentage of the population in each 5-year age group in crude mortality rates.
This study examines the factors influencing item nonresponse, especially when it comes to income and sexual behavior, in the Japanese context. Many item nonresponses on questions on income and sexual behavior are a serious problem for analysis since they might cause biased estimations. However, many previous studies on item nonresponse when it comes to income and sexual issues examine surveys carried out in Western societies. Moreover, many previous studies have not distinguished between “Refused” and “Don't Know.” In addition, many previous studies on income nonresponse do not focus on the effect of religion, although questions on religion have been argued to affect survey cooperation. Thus, we analyzed the data from the Japanese General Social Survey 2000/2001 to distinguish the reason for nonresponse properly, reveal factors on income and sexual behavior nonresponses, and examined the effect of religion. We conducted multinomial logistic regressions of nonresponse in household income, individual income, and sexual behavior. Our findings are as follows: (1) Factors that affected nonresponses of income and sexual behavior are different between Japanese and Western societies. (2) The effect of age and educational background are different between “Refused” and “Don't Know.” (3) Respondents whose family has a religion tended to answer with household income. These findings indicate that we should consider the nonresponse mechanism due to the Japanese-specific context, distinguish the reason for nonresponse because of different effects of factors, and focus on the effect of religion on income nonresponse.
Massey's method is a rating system that provides individual teams or players ranking. It is known that Massey's rating is related to the Katz centrality measure of the networks. Analyzing the node centrality of networks provides useful information on how important a node is. This study investigates a sampling distribution of Massey's rating and provides the test statistics of the null hypothesis of equal rating against the alternatives. Monte Carlo simulations are performed to compare the power of the proposed test and show that the asymptotic distribution of the ratings is well approximated by the normal distributions. Real dataset applications using men's tennis ATP ratings are illustrated.