Todeschini, R., 1990. Weighted k-nearest neighbour method for the calculation of missing values. Chemometrics and Intelligent Laboratory Systems, 9: 201-205. The problem of the estimation of the missing values in a multivariate data set is considered and a new method based on the k-nearest neighbour (K-NN) algorithm is proposed. The method is very easy to use and seems to overcome several problems presented by other methods. K values of 3 and 5 and scaling with respect to the maximum seem good practical choices in applying the K-NN algorithm for this purpose. © 1990.
Todeschini, R. (1990). Weighted KNN method for the calculation of missing values. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 9, 201-205.
Citazione: | Todeschini, R. (1990). Weighted KNN method for the calculation of missing values. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 9, 201-205. | |
Tipo: | Articolo in rivista - Articolo scientifico | |
Carattere della pubblicazione: | Scientifica | |
Titolo: | Weighted KNN method for the calculation of missing values. | |
Autori: | Todeschini, R | |
Autori: | ||
Data di pubblicazione: | 1990 | |
Lingua: | English | |
Rivista: | CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS | |
Appare nelle tipologie: | 01 - Articolo su rivista |