Regression Diagnostics: Identifying Influential Data and Sources of Collinearity
"The title of the book more or less sums up the contents. It
appears to me to represent a real breakthrough in the art of
dealing in ‘unconventional’ data. . . . I found the
whole book both readable and enjoyable. It is suitable for data
analysts, academic statisticians, and professional software
–Journal of the Royal Statistical Society
"The book assumes a working knowledge of all of the principal
results and techniques used in least squares multiple regression,
as expressed in vector and matrix notation. Given this background,
the book is clear and easy to use. . . . The techniques are
illustrated in great detail with practical data sets from
–Short Book Reviews, International Statistical Institute
Regression Diagnostics: Identifying Influential Data and Sources of Collinearity provides practicing statisticians and econometricians with new tools for assessing quality and reliability of regression estimates. Diagnostic techniques are developed that aid in the systematic location of data points that are unusual or inordinately influential; measure the presence and intensity of collinear relations among the regression data; and help to identify variables involved in each and pinpoint estimated coefficients potentially most adversely affected. The book emphasizes diagnostics and includes suggestions for remedial action
2. Detecting Influential Observations and Outliers.
3. Detecting and Assessing Collinearity.
4. Applications and Remedies.
5. Research Issues and Directions for Extensions.
Edwin Kuh, PhD, is Professor in the Department of Economics at Boston College in Newtonville, Massachusetts.
Roy E. Welsch, PhD, is Professor of Statistics and Management at the Sloan School of Management at the Massachusetts Institute of Technology.