@misc{Misztal_Małgorzata_Zagregowane_2009,
 author={Misztal, Małgorzata},
 year={2009},
 rights={Wszystkie prawa zastrzeżone (Copyright)},
 publisher={Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu},
 description={Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu = Research Papers of Wrocław University of Economics; 2009; Nr 47, s. 132-140},
 language={pol},
 abstract={To improve the stability and prediction accuracy of classification trees we can use ensembles of classifiers or hybrid models, combining recursive partitioning with some others algorithms (i.e. linear discriminant functions, logistic regression, distance-based algorithms, etc.). The aim of the paper is to compare the performances of classifier combination methods (Bagging [Breiman 1996], Boosting [Freund, Shapire 1997], Random forests [Breiman 2001]) and hybrid models (CRUISE [Kim, Loh 2003], LOTUS [Chan, Loh 2004], PLUS [Lim 2000], k-NN Tree [Buttrey, Karo 2002]). A medical diagnosis example is used to demonstrate the advantages and disadvantages of the algorithms examined. (original abstract)},
 title={Zagregowane i hybrydowe modele dyskryminacyjne : próba porównania wybranych algorytmów},
 type={artykuł},
}