Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Jacek Koronacki"'
Autor:
Jacek Koronacki, Michał Dramiński
Publikováno v:
Journal of Statistical Software; Vol 85 (2018); 1-28
Journal of Statistical Software, Vol 85, Iss 1, Pp 1-28 (2018)
Journal of Statistical Software, Vol 85, Iss 1, Pp 1-28 (2018)
We describe the R package rmcfs that implements an algorithm for ranking features from high dimensional data according to their importance for a given supervised classification task. The ranking is performed prior to addressing the classification tas
Autor:
Jacek Koronacki, Jan Ćwik
Publikováno v:
Computational Statistics & Data Analysis. 26:199-218
A multivariate extension of the plug-in kernel (and filtered kernel) estimator is proposed and this uses asymptotically optimal bandwidth matrix (matrices) for a normal mixture approximation of a density to be estimated (the filtered kernel estimator
Autor:
Jacek Koronacki, U. Luboińska
Publikováno v:
Computational Statistics & Data Analysis. 18:317-330
Let X (1) ,..., X (m) be m independent, real-valued random variables with unknown densities and let Y = Ψ(X (1) ,...,X (m) ) be their known functional. The aim is to estimate the density of the random variable Y , given n independent realizations of
Autor:
Jacek Koronacki, W. Feluch
Publikováno v:
Computational Statistics & Data Analysis. 13:143-151
In the note, a simple modification of the least-squares cross-validation criterion is proposed for choosing the bandwidth of kernel density estimators. For an i.i.d. sample X1, X2, …, Xn, the modification consists in leaving out a number of terms w
Autor:
Jan Komorowski, Alvaro Rada-Iglesias, Stefan Enroth, Claes Wadelius, Michał Dramiński, Jacek Koronacki
Publikováno v:
Bioinformatics (Oxford, England). 24(1)
Motivation: Pre-selection of informative features for supervised classification is a crucial, albeit delicate, task. It is desirable that feature selection provides the features that contribute most to the classification task per se and which should
Autor:
Jacek Koronacki
Publikováno v:
Journal of Statistical Planning and Inference. 30:137-139
Publikováno v:
The Statistician. 43:345
Autor:
Jacek Koronacki, Wolfgang Wertz
Publikováno v:
Journal of Statistical Planning and Inference. 20:23-39
In this paper asymptotic sequential fixed-width confidence bounds for an unknown density on the real line, based on integrated squared error, are studied. Using a sequence of Wolverton-Wagner kernel estimators, two classes of stopping rules are estab
Autor:
Jacek Koronacki
Publikováno v:
Statistics & Probability Letters. 5:415-419
A stochastic approximation counterpart of the feasible direction method of Topkis and Veinott is considered. No convexity condition on a function to be minimized is imposed and a procedure for one-dimensional minimization along each feasible directio