Biometrical Letters vol. 48(2), 2011, pp. 83-99
|
INVESTIGATION OF VECTORS OF INFLUENTIAL OBSERVATIONS IN A LINEAR REGRESSION MODEL Anna Budka Department of Mathematical and Statistical Methods, Poznan University of Life Sciences, Wojska Polskiego 28, 60-637 Poznań, Poland; e-mail: budka@up.poznan.pl |
The procedures presented in this work lead to the identification of reasons for the poor fit of a mathematical model. Investigation of vectors of influential observations in a linear regression model leads to the identification of systems of observations regarded as influential. Particularly interesting are those which contain cases which were previously not regarded as influential in the analysis of a full model or 1-cut model.
m-cut linear regression model, vector of influential observations, masking of observations, leverage point
