Summary
“This observation does not fit in with the trend”, “If the sample had been slightly different, we had reached another resul” — such statements shall be formalized. Regression diagnostics look for observations badly explained by the model. This is done by means of an influence measure that arises from a definition of influence. As influence has many aspects, there are many such diagnostics. Considering classical and Bayesian regression models, this work shall illustrate how to derive and use the diagnostics needed in specific cases.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
BELSLEY, D. A.; KUH, E. and WELSCH, R. E. (1980): Regression Diagnostics: Identifying Influential Data and Sources of Collinearity. Wiley, New York.
CHATTERJEE, S. and HADI, A. S. (1988): Sensitivity Analysis in Linear Regression. Wiley, New York.
COOK, R. D. and WEISBERG, S. (1982): Residuals and Influence in Regression. Chapman and Hall, New York.
POLASEK, W. (1993): Variance Diagnostics for Classical and Bayesian Linear Regression. WWZ Discussion Papers Nr. 9302. WWZ, Universität Basel, Basel.
WEISS, R. (1996): Sufficiency and Influence. Journal of the Royal Statistical Society Series B, to appear.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vonthein, R. (1997). Classes of Influential Observations. In: Klar, R., Opitz, O. (eds) Classification and Knowledge Organization. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-59051-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-642-59051-1_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62981-8
Online ISBN: 978-3-642-59051-1
eBook Packages: Springer Book Archive