樋口 匡貴

Abstract Case information focusing on a particular person does not provide representative evidence on the risks or benefits for a given population. However, research on judgement and decision‐making has revealed that statistical information focusing on the population is much less influential on recipients than case information, as exemplified by the identifiable victim effect. On the other hand, studies on persuasion have reported that explanatory messages accompanied by statistical evidence change individuals' attitudes more than the narratives alone. Such findings suggest that statistical information can be influential when accompanied by explanations of what the numbers imply. However, few studies have attempted to test this hypothesis in risk perception research. The present study investigated how statistical information with explanations influenced the perceived effectiveness of a measure for reducing disaster risk, earthquake early warnings (EEWs). The results of two studies ( N  = 1423), using actual statistics and person‐focused scenarios, showed that adding an explanation to negatively framed statistics indicating the ineffectiveness of EEWs reduced participants' perceived effectiveness. In contrast, positively framed statistics with an explanation did not change participants' perceptions. This study not only replicated previous findings on case information but also provided new insights into how statistical information could impact individuals' perceptions.

We conducted a systematic review of conference papers in social psychology at two large psychology conferences in Japan: the Japanese Psychological Association and the Japanese Society for Social Psychology. The conference papers were effectively not subjected to peer review; hence, they were suitable for testing if psychologists selectively reported statistically significant findings without pressure from journal editors and reviewers. We investigated the distributions of z-values converted from the p-values reported in the articles presented at the 2013 and 2018 conferences. The z-curve analyses suggest the existence of selective reporting by the authors in 2013. The expected discovery rate (EDR) was much lower than the observed discovery rate (ODR; 7% vs. 76%, respectively), and the 95% confidence interval (CI) did not include the ODR. However, this does not mean that the set of studies completely lacked evidential value. The expected replication rate (ERR) was 31%; this is significantly higher than 5%, which was expected under the null hypothesis of no effect. Changes were observed between 2013 and 2018. The ERR increased (31% to 44%), and the EDR almost doubled (7% to 13%). However, the estimation of the maximum false discovery rate (FDR; 68% in 2013 and 35% in 2018) suggested that a substantial proportion of the reported findings were false positives. Overall, while social psychologists in Japan engaged in selective reporting, this does not mean that the entire field was covered with false positives. In addition, slight signs of improvement were observed in how they reported their findings. Still, the evidential value of the target studies was weak, even in 2018, allowing for no optimism.