delo diplomskega seminarja
Gašper Letnar (Author), Maja Pohar Perme (Mentor)

Abstract

Razmerje tveganj in razmerje obetov sta dve meri, ki ju pogosto srečujemo v medicini, ko želimo ovrednotiti vpliv dejavnika izpostavljenosti na binarni izid. V delu diplomskega seminarja obe meri definiram, predstavim njune lastnosti in se nato posvetim ocenjevanju. Če nadzor nad vplivom motečih dejavnikov pri samem procesu vzorčenja ni mogoč, kar se skoraj gotovo zgodi pri opazovalnih raziskavah, moramo njihov učinek upoštevati v statistični analizi. To navadno storimo z uporabo regresijskih modelov in posledično se v jedru dela osredotočim na osnovno teorijo posplošenih linearnih modelov, ki je potrebna za ocenjevanje obeh mer. Ko ocenjujemo razmerje obetov, je izbira logističnega modela samoumevna. Žal pa za ocenjevanje razmerja tveganj nimamo modela, ki bi imel tako lepe matematične lastnosti, kot jih ima logistični model za razmerje obetov. A vendar, ker je razmerje tveganj tista mera, ki jo v praksi želimo oceniti, je bilo v zadnjih desetletjih veliko truda vloženega v iskanje najustreznejšega pristopa za ocenjevanje te mere. Dva najbolj uporabljena pristopa za ocenjevanje sta log-binomska regresija in Poissonova regresija. V drugem delu diplomskega dela prvi model na kratko omenim, večjo pozornost pa namenim slednjemu.

Keywords

finančna matematika;razmerje tveganj;razmerje obetov;posplošeni linearni modeli;logistična regresija;Poissonova regresija;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UL MF - Faculty of Medicine
Publisher: [G. Letnar]
UDC: 519.2
COBISS: 18710361 Link will open in a new window
Views: 3821
Downloads: 616
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Risk ratio and odds ratio
Secondary abstract: Risk ratio and odds ratio are two measures that are often encountered in medicine when we are evaluating the impact of an exposure factor on binary outcome. This thesis contains definitions, properties and methods for estimating both measures. If control over the influence of confounding factors is not possible in the sampling process itself, which almost certainly happens in observational research, their effect must be taken into account in the statistical analysis. This is usually done using regression models, and consequently, in the core of the work, I concentrate on the basic theory of generalized linear models, which is necessary for estimating both measures. When estimating odds ratio, the choice of a logistic model is self-evident. Unfortunately, there is no model for estimating risk ratio that is as mathematically perfect as logistic model is for estimating odds ratio. However, since risk ratio is usually the parameter of primary interest, a lot of effort has been invested in finding the most appropriate approach to estimating it. The two most common approaches to estimating risk ratio are log-binomial regression and Poisson regression. In the second part of this thesis the former model is briefly mentioned, while the latter is described in greater detail.
Secondary keywords: mathematics;risk ratio;odds ratio;generalized linear models;logistic regression;Poisson regression;
Type (COBISS): Final seminar paper
Study programme: 0
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za matematiko in fiziko, Oddelek za matematiko, Finančna matematika - 1. stopnja
Pages: 34 str.
ID: 11211157