Regresijska analiza

diplomsko delo

Andreja Korenjak (Author), Dominik Benkovič (Mentor)

Abstract

V diplomskem delu je predstavljena regresijska analiza s poudarkom na linearni regresiji in večkratni regresiji. Na začetku sta v poglavju osnovni pojmi opisani korelacijska analiza in analiza variance, ki sta pomembni za razumevanje diplomskega dela. V nadaljevanju je predstavljen regresijski model. Nato sta v osrednjem delu predstavljeni dve poglavji: linearna regresija in večkratna regresija. V prvem je opisana metoda najmanjših kvadratov, ki je pomembna za pridobivanje ocen regresijskih parametrov. Predstavljen je tudi model in preverjanje podatkov ter osnovni statistični podatki (standardna napaka modela, tabela analize variance, determinacijski koeficient, statistiki F in T, ki sta pomembni za testiranje ničelnih hipotez). V drugem je predstavljen postopek, kako priti do ocen parametrov, ter model in preverjanje podatkov. Obe poglavji sta podprti z zgledi, za katere smo pri obdelavi podatkov uporabili statistični program SPSS. V nadaljevanju so opisani praktični premisleki v regresijski analizi z izbiro regresijske enačbe, eksperimentalnimi cilji in selektivno metodo. Nato je predstavljena uporaba regresijske analize, ki temelji na obliki regresijske enačbe ter na ocenjevanju in napovedovanju. Na koncu je z zgledoma predstavljena nelinearna regresija.

Keywords

matematika;regresija;linearna regresija;večkratna regresija;nelinearna regresija;analiza variance;diplomska dela;

Data

Language:	Slovenian
Year of publishing:	2010
Source:	Maribor
Typology:	2.11 - Undergraduate Thesis
Organization:	UM FNM - Faculty of Natural Sciences and Mathematics
Publisher:	[A. Korenjak]
UDC:	51(043.2)
COBISS:	17742344
Views:	12494
Downloads:	3874
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	REGRESSION ANALYSIS
Secondary abstract:	The graduation thesis presents regression analysis with emphasis on linear regression and multiple regression. The first chapter describes basic concepts of the correlation analysis and analysis of variance, which are important for understanding the thesis. Further, a regression model is presented. The central part of the thesis consists of two chapters: linear regression and multiple regression. The first one describes the method of least squares, which is important for obtaining estimates of regression parameters. A model is presented including a verification of data and basic statistics (standard error of the model, table analysis of variance, coefficient of determination, F and T statistics, which are important for testing the null hypothesis). In the second one we describe a method for obtaining estimates of parameters, and design and verification of data. In both sections many examples are given, which were obtained using statistical data processing program SPSS. Next, some practical arguments in regression analysis are described including the choice of regression equation, the experimental objectives and selective method. We also present applications of regression analysis based on a form of regression equation, and also on evaluation and prediction. Finally, we give two examples presenting nonlinear regression.
Secondary keywords:	linear regression;multiple regression;nonlinear regression;analysis of variance;
URN:	URN:SI:UM:
Type (COBISS):	Undergraduate thesis
Thesis comment:	Univ. v Mariboru, Fak. za naravoslovje in matematiko, Oddelek za matematiko in računalništvo
Pages:	52 f.
Keywords (UDC):	mathematics;natural sciences;naravoslovne vede;matematika;mathematics;matematika;
ID:	18601