{"title":"在主体间中介的功效分析和数据分析中,何时使用不同的推理方法","authors":"J. Fossum, A. Montoya","doi":"10.1177/25152459231156606","DOIUrl":null,"url":null,"abstract":"Several options exist for conducting inference on indirect effects in mediation analysis. Although methods that use bootstrapping are the preferred inferential approach for testing mediation, they are time-consuming when the test must be performed many times for a power analysis. Alternatives that are more computationally efficient are not as robust, meaning accuracy of the inferences from these methods is more affected by nonnormal and heteroskedastic data. Previous research has shown that different sample sizes are needed to achieve the same amount of statistical power for different inferential approaches with data that meet all the statistical assumptions of linear regression. By contrast, we explore how similar power estimates are at the same sample size, including when assumptions are violated. We compare the power estimates from six inferential methods for between-subjects mediation using a Monte Carlo simulation study. We varied the path coefficients, inferential methods for the indirect effect, and degree to which assumptions are met. We found that when the assumptions of linear regression are met, three inferential methods consistently perform similarly: the joint significance test, the Monte Carlo confidence interval, and the percentile bootstrap confidence interval. When the assumptions were violated, the nonbootstrapping methods tended to have vastly different power estimates compared with the bootstrapping methods. On the basis of these results, we recommend using the more computationally efficient joint significance test for power analysis only when no assumption violations are hypothesized a priori. We also recommend the joint significance test to pick an optimal starting sample size value for power analysis using the percentile bootstrap confidence interval when assumption violations are suspected.","PeriodicalId":55645,"journal":{"name":"Advances in Methods and Practices in Psychological Science","volume":" ","pages":""},"PeriodicalIF":15.6000,"publicationDate":"2023-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"When to Use Different Inferential Methods for Power Analysis and Data Analysis for Between-Subjects Mediation\",\"authors\":\"J. Fossum, A. Montoya\",\"doi\":\"10.1177/25152459231156606\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Several options exist for conducting inference on indirect effects in mediation analysis. Although methods that use bootstrapping are the preferred inferential approach for testing mediation, they are time-consuming when the test must be performed many times for a power analysis. Alternatives that are more computationally efficient are not as robust, meaning accuracy of the inferences from these methods is more affected by nonnormal and heteroskedastic data. Previous research has shown that different sample sizes are needed to achieve the same amount of statistical power for different inferential approaches with data that meet all the statistical assumptions of linear regression. By contrast, we explore how similar power estimates are at the same sample size, including when assumptions are violated. We compare the power estimates from six inferential methods for between-subjects mediation using a Monte Carlo simulation study. We varied the path coefficients, inferential methods for the indirect effect, and degree to which assumptions are met. We found that when the assumptions of linear regression are met, three inferential methods consistently perform similarly: the joint significance test, the Monte Carlo confidence interval, and the percentile bootstrap confidence interval. When the assumptions were violated, the nonbootstrapping methods tended to have vastly different power estimates compared with the bootstrapping methods. On the basis of these results, we recommend using the more computationally efficient joint significance test for power analysis only when no assumption violations are hypothesized a priori. We also recommend the joint significance test to pick an optimal starting sample size value for power analysis using the percentile bootstrap confidence interval when assumption violations are suspected.\",\"PeriodicalId\":55645,\"journal\":{\"name\":\"Advances in Methods and Practices in Psychological Science\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":15.6000,\"publicationDate\":\"2023-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advances in Methods and Practices in Psychological Science\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://doi.org/10.1177/25152459231156606\",\"RegionNum\":1,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PSYCHOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in Methods and Practices in Psychological Science","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1177/25152459231156606","RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHOLOGY","Score":null,"Total":0}
When to Use Different Inferential Methods for Power Analysis and Data Analysis for Between-Subjects Mediation
Several options exist for conducting inference on indirect effects in mediation analysis. Although methods that use bootstrapping are the preferred inferential approach for testing mediation, they are time-consuming when the test must be performed many times for a power analysis. Alternatives that are more computationally efficient are not as robust, meaning accuracy of the inferences from these methods is more affected by nonnormal and heteroskedastic data. Previous research has shown that different sample sizes are needed to achieve the same amount of statistical power for different inferential approaches with data that meet all the statistical assumptions of linear regression. By contrast, we explore how similar power estimates are at the same sample size, including when assumptions are violated. We compare the power estimates from six inferential methods for between-subjects mediation using a Monte Carlo simulation study. We varied the path coefficients, inferential methods for the indirect effect, and degree to which assumptions are met. We found that when the assumptions of linear regression are met, three inferential methods consistently perform similarly: the joint significance test, the Monte Carlo confidence interval, and the percentile bootstrap confidence interval. When the assumptions were violated, the nonbootstrapping methods tended to have vastly different power estimates compared with the bootstrapping methods. On the basis of these results, we recommend using the more computationally efficient joint significance test for power analysis only when no assumption violations are hypothesized a priori. We also recommend the joint significance test to pick an optimal starting sample size value for power analysis using the percentile bootstrap confidence interval when assumption violations are suspected.
期刊介绍:
In 2021, Advances in Methods and Practices in Psychological Science will undergo a transition to become an open access journal. This journal focuses on publishing innovative developments in research methods, practices, and conduct within the field of psychological science. It embraces a wide range of areas and topics and encourages the integration of methodological and analytical questions.
The aim of AMPPS is to bring the latest methodological advances to researchers from various disciplines, even those who are not methodological experts. Therefore, the journal seeks submissions that are accessible to readers with different research interests and that represent the diverse research trends within the field of psychological science.
The types of content that AMPPS welcomes include articles that communicate advancements in methods, practices, and metascience, as well as empirical scientific best practices. Additionally, tutorials, commentaries, and simulation studies on new techniques and research tools are encouraged. The journal also aims to publish papers that bring advances from specialized subfields to a broader audience. Lastly, AMPPS accepts Registered Replication Reports, which focus on replicating important findings from previously published studies.
Overall, the transition of Advances in Methods and Practices in Psychological Science to an open access journal aims to increase accessibility and promote the dissemination of new developments in research methods and practices within the field of psychological science.