學術產出-Periodical Articles

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 Suppression and enhancement in multiple linear regression: A viewpoint from the perspective of a semipartial correlation coefficient
作者 江振東
Chiang, Jeng-Tung
Hsu, Szu-Yuan
貢獻者 統計系
日期 2020-05
上傳時間 25-Jun-2021 10:15:44 (UTC+8)
摘要 For a linear regression model with two-predictor variables, the effects of the correlation between the two predictors on estimated standardized regression coefficients and R2R2 have been well studied. However, the role the correlation plays may sometimes be overstated, such that confusion and misconceptions may arise. In this article, we revisit the issue from the perspective of a semipartial correlation coefficient. We find that by taking this perspective we are not only able to reach the same conclusions while avoiding those misunderstandings, we are also able to gain more insight. In addition, we also take a geometrical approach to illustrate how estimated standardized regression coefficients and R2R2 behave as the correlation varies. Geometrical displays provide readers with a way to visualize the behavior changes and to understand the reasons behind those changes more easily. Although we focus mainly on two predictors in this article, the conclusions can be easily extended to a general k-predictor case.
關聯 Communications in Statistics - Theory and Methods, pp.1-16
資料類型 article
DOI https://doi.org/10.1080/03610926.2020.1759094
dc.contributor 統計系
dc.creator (作者) 江振東
dc.creator (作者) Chiang, Jeng-Tung
dc.creator (作者) Hsu, Szu-Yuan
dc.date (日期) 2020-05
dc.date.accessioned 25-Jun-2021 10:15:44 (UTC+8)-
dc.date.available 25-Jun-2021 10:15:44 (UTC+8)-
dc.date.issued (上傳時間) 25-Jun-2021 10:15:44 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/135884-
dc.description.abstract (摘要) For a linear regression model with two-predictor variables, the effects of the correlation between the two predictors on estimated standardized regression coefficients and R2R2 have been well studied. However, the role the correlation plays may sometimes be overstated, such that confusion and misconceptions may arise. In this article, we revisit the issue from the perspective of a semipartial correlation coefficient. We find that by taking this perspective we are not only able to reach the same conclusions while avoiding those misunderstandings, we are also able to gain more insight. In addition, we also take a geometrical approach to illustrate how estimated standardized regression coefficients and R2R2 behave as the correlation varies. Geometrical displays provide readers with a way to visualize the behavior changes and to understand the reasons behind those changes more easily. Although we focus mainly on two predictors in this article, the conclusions can be easily extended to a general k-predictor case.
dc.format.extent 391792 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) Communications in Statistics - Theory and Methods, pp.1-16
dc.title (題名) Suppression and enhancement in multiple linear regression: A viewpoint from the perspective of a semipartial correlation coefficient
dc.type (資料類型) article
dc.identifier.doi (DOI) 10.1080/03610926.2020.1759094
dc.doi.uri (DOI) https://doi.org/10.1080/03610926.2020.1759094