TY - JOUR
T1 - Influential observations in linear regression
AU - Cook, R. Dennis
PY - 1979
Y1 - 1979
N2 - Characteristics of observations which cause them to be influential in a least squares analysis are investigated and related to residual variances, residual correlations, and the convex hull of the observed values of the independent variables. It is shown how deleting an observation can substantially alter an analysis by changing the partial F-tests, the studentized residuals, the residual variances, the convex hull of the independent variables, and the estimated parameter vector. Outliers are discussed briefly, and an example is presented. © 1979, Taylor & Francis Group, LLC.
AB - Characteristics of observations which cause them to be influential in a least squares analysis are investigated and related to residual variances, residual correlations, and the convex hull of the observed values of the independent variables. It is shown how deleting an observation can substantially alter an analysis by changing the partial F-tests, the studentized residuals, the residual variances, the convex hull of the independent variables, and the estimated parameter vector. Outliers are discussed briefly, and an example is presented. © 1979, Taylor & Francis Group, LLC.
KW - Deleting observations
KW - Outliers
KW - Partial F-tests
KW - Residual correlations
KW - Studentized residuals
UR - http://www.scopus.com/inward/record.url?scp=84918743166&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84918743166&partnerID=8YFLogxK
U2 - 10.1080/01621459.1979.10481634
DO - 10.1080/01621459.1979.10481634
M3 - Article
SN - 0162-1459
VL - 74
SP - 169
EP - 174
JO - Journal of the American Statistical Association
JF - Journal of the American Statistical Association
IS - 365
ER -