prikaz prve stranice dokumenta Neparametarska regresija
  Download
PDF 16.78 MB
master's thesis
Neparametarska regresija
2022. urn:nbn:hr:126:556961
Višić, Karla
Josip Juraj Strossmayer University of Osijek
Department of Mathematics

Cite this document

Višić, K. (2022). Neparametarska regresija (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics. Retrieved from https://urn.nsk.hr/urn:nbn:hr:126:556961

Višić, Karla. "Neparametarska regresija." Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2022. https://urn.nsk.hr/urn:nbn:hr:126:556961

Višić, Karla. "Neparametarska regresija." Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2022. https://urn.nsk.hr/urn:nbn:hr:126:556961

Višić, K. (2022). 'Neparametarska regresija', Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, accessed 23 December 2024, https://urn.nsk.hr/urn:nbn:hr:126:556961

Višić K. Neparametarska regresija [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics; 2022 [cited 2024 December 23] Available at: https://urn.nsk.hr/urn:nbn:hr:126:556961

K. Višić, "Neparametarska regresija", Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, Osijek, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:126:556961

Please login to the repository to save this object to your list.
Metadata
TitleNeparametarska regresija
Title (english)Nonparametric Regression
AuthorKarla Višić
MentorMirta Benšić (mentor)
Committee memberNenad Šuvak (predsjednik povjerenstva)
Committee memberMirta Benšić (član povjerenstva)
Committee memberIvan Papić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Department of Mathematics
Osijek
Defense date and country2022-10-28, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Probability Theory and Statistics
Abstract
U ovom diplomskom radu su predstavljene i opisane metode neparametarskog procjenjivanja funkcije uvjetnog očekivanja (regresijska funkcija) pri čemu smo se fokusirali na lokalne izgladivače jezgrama. Za Nadaraya - Watson i lokalni linearni procjenitelj su analizirana asimptotska svojstva, pristranost, varijanca i srednja kvadratna greška.Širina pojasa utječe na izgled regresijske funkcije pa je prilikom procjenjivanja ključno odabrati optimalnu širinu. Stoga su predstavljene dvije metode za odabir, rule-of-thumb i unakrsno validacijski kriterij. U zadnjem poglavlju smo se osvrnuli na multivarijatni slučaj i problematiku velike dimenzionalnosti u procjenjivanju. Kao odgovor na smanjenu preciznost opisana je metoda parcijalne regresije.
Abstract (english)
In this thesis we present and describe nonparametric estimation of the conditional expectation function (regression function) with focus on local kernal smoothing estimators. For Nadaraya - Watson estimator and local linear estimator we analyzed their asymptotic properties, bias, variance and mean squared error. Bandwidth affects the level of curvature of the regression function so it is crucial to use optimal bandwidth when estimating. We present two methods for choosing the optimal bandwidth, Rule-of-Thumb and cross validation criterion. In the last chapter we consider the multivariate case and problems of large dimensionality. As a response to reduced precision we describe partial linear regression method.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:126:556961
Study programmeTitle: Mathematics; specializations in: Financial and Statistical Mathematics, Mathematics and Computer Science, Industrial and Applied Mathematics
Course: Financial and Statistical Mathematics
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-11-14 07:42:44