Suicide and unemployment in Japan: Evidence from municipal level suicide rates and age-specific suicide rates

Most previous studies on the relationship between unemployment and suicide use either individual level data or large unit aggregate level data. The former typically fail to distinguish the observed association from the causal link, and the latter often produce inconsistent findings on the unemployment-suicide relationship, making it difficult to draw policy implications. The present study contributes to this line of research by using two semi-aggregate level data in Japan. The results show that unemployment is significantly associated with male suicide rates, especially those of prime age working men, while the results are not straightforward for female suicide rates.     

New Classification of Research Misconduct from the Viewpoint of Truth,Trust, and Risk

ABSTRACT

Fabrication, Falsification and Plagiarism (FFP) and Questionable Research Practice (QRP) have been used worldwide in the classification of research misconduct. However, FFP comprises two distinct categories of misconduct: FF is extreme research misconduct that betrays truth, while P undermines trust of science community. Irreproducibility and inadequate practice of research also betray trust. Research misconduct has the potential to cause serious risk of safety in daily life. The proposed classification system is outlined as follows: Class I misconduct: Betrayal of the truth: (1) Fabrication and (2) Falsification. Class II misconduct: Betrayal of trust: (1) Plagiarism of text ; Irreproducibility; and (3) Inadequate research practice. Class III misconduct: Risk to safety of health and industrial products: (1) Risk to safety of health and (2) Risk to safety of industrial products. The proposed classification reflects deeper values of truth, trust, and risk more directly than the previous classification and elucidates issues about nature and significance of misconduct.     

Racial diversity,immigrants and the well-being of residents: evidence from US counties

This paper presents empirical evidence that racial diversity and immigrant population at the local level tend to be associated with lower life satisfaction for Whites by matching individual data with the county-level population data during the period 2005–2010. The magnitudes I find suggest that a ten-percentage-point increase in the share of the non-White population (approximately one half of a standard deviation) is associated with 0.006 and 0.007 points reduction in life satisfaction on a four-point scale for White men and White women, respectively. For White men, this effect appears to be driven by the percentage of the population that is Black. I also find that a ten-percentage-point increase in the percentage of the immigrant population (approximately 2 standard deviations) is associated with 0.009 and 0.021 points reduction in life satisfaction for White men and White women, respectively. The percentage of the non-White population seems to reduce older Whites’ life satisfaction more than that of younger Whites. Though the scale of the findings relating to the impact of local racial compositions and immigrant population is relatively modest, the findings may pose a challenge in the coming years as the percentage of the population that is non-White rises in the USA.     

Marital Dissolution and Formation for Interracial Couples: Evidence from Parents of Biracial Children

There is a large amount of literature on whether interracial relationships are more unstable than same-race relationships. This study utilizes data on the race of respondents’ children and examines how marital dissolution and formation differ for those who mate interracially. Contrary to several previous studies, this study finds that some interracial couples are more likely to proceed to marriage and have more stable marriage than same-race couples. White men with Asian biracial children are more likely to be married than other white male parents, black women with white biracial children are more likely to be married than other black female parents, and Asian women with white biracial children are more likely to get married (but more likely to get divorced or separated once married) than other Asian female parents.     

Covariate selection for estimating the causal effect of control plans by using causal diagrams

Summary. Consider a case where cause–effect relationships between variables can be described by a causal path diagram and the corresponding linear structural equation model. The paper proposes a graphical selection criterion for covariates to estimate the causal effect of a control plan. For designing the control plan, it is essential to determine both covariates that are used for control and covariates that are used for identification. The selection of covariates used for control is only constrained by the requirement that the covariates be non-descendants of a treatment variable. However, the selection of covariates used for identification is dependent on the selection of covariates used for control and is not unique. In the paper, the difference between covariates that are used for identification is evaluated on the basis of the asymptotic variance of the estimated causal effect of an effective control plan. Furthermore, the results can be also described in terms of a graph structure.     

Variance Estimators for Three "Probabilities of Causation"

This article introduces the definitions of three "probabilities of causation" suggested by Pearl (1999), which are used to evaluate the causal effect of an exposure on a disease in epidemiological studies. Pearl (1999) and Tian and Pearl (2000a, 2000b) provided identification formulas for three "probabilities of causation" from statistical data under some assumptions. In order to examine the estimation accuracy problem, this article derives variance estimators for three "probabilities of causation" correspondent to each case in Pearl (1999) and at the same time clarify their properties. In addition, we conduct simulation experiments and show that the proposed method can approximate sufficiently to the variance of "probabilities of causation." The results of this article provide a complete framework for using "probabilities of causation" effectively in order to analyze responsibility and susceptibility in epidemiological studies.     

Optimizing a control plan using a structural equation model with an application to statistical process analysis

In the case where non-experimental data are available from an industrial process and a directed graph for how various factors affect a response variable is known based on a substantive understanding of the process, we consider a problem in which a control plan involving multiple treatment variables is conducted in order to bring a response variable close to a target value with variation reduction. Using statistical causal analysis with linear (recursive and non-recursive) structural equation models, we configure an optimal control plan involving multiple treatment variables through causal parameters. Based on the formulation, we clarify the causal mechanism for how the variance of a response variable changes when the control plan is conducted. The results enable us to evaluate the effect of a control plan on the variance of a response variable from non-experimental data and provide a new application of linear structural equation models to engineering science.     

Repeating probability of authors with retracted scientific publications

Both the scientific community and the general public have expressed concern over scientific misconduct. The number of retracted articles has increased dramatically over the past 20 years and now comprises about .02% of the 2 million articles published each year. Retraction of publications available in large public databases can be analyzed as an objective measure for scientific misconduct and errors. In this project, we analyzed retractions of scientific publications using the Web of Science (WoS) and PubMed databases. We found that a power law is applicable to distributions of retracting authors and retracted publications with exponents of about ?.6 and ?3.0, respectively. Application of a power-law model for retracted publications implies that retraction is not a random event. Analysis of the retraction distributions suggests that a small fraction (1–2%) of retracting authors with ≧5 retractions are responsible for around 10% of retraction. The probabilities for their repeating retraction are calculated using a statistical model: 3–5% likelihood of repeat retraction for authors with a single retraction at five years after the latest retraction and 26–37% for authors with five retractions at five years after the latest retraction. By focusing on those with repeated retractions, this analysis could contribute to identification of measures to reduce such repetition of retractions.     

The Identification of Direct and Indirect Effects in Studies with an Unmeasured Intermediate Variable

This paper considers the identification problem of direct and indirect effects of treatment on a response, when observed data are available but an important intermediate variable is unmeasured. To solve this problem, we propose identification conditions for direct and indirect effects based on (conditionally independent) proxy variables of the unmeasured intermediate variable. This paper establishes feasible approaches for evaluating direct and indirect effects in studies with a single unmeasured intermediate variable.     

On the Estimation Accuracy of Causal Effects using Supplementary Variables

This paper focuses on a situation in which a set of treatments is associated with a response through a set of supplementary variables in linear models as well as discrete models. Under the situation, we demonstrate that the causal effect can be estimated more accurately from the set of supplementary variables. In addition, we show that the set of supplementary variables can include selection variables and proxy variables as well. Furthermore, we propose selection criteria for supplementary variables based on the estimation accuracy of causal effects. From graph structures based on our results, we can judge certain situations under which the causal effect can be estimated more accurately by supplementary variables and reliably evaluate the causal effects from observed data.