Title Bayesova statistika u Pythonu
Title (english) Bayesian statistics in Python
Author Vito Radovniković
Mentor Ani Grubišić (mentor)
Committee member Ani Grubišić (predsjednik povjerenstva)
Committee member Branko Žitko (član povjerenstva)
Committee member Divna Krpan (član povjerenstva)
Granter University of Split Faculty of Science (Department of Informatics) Split
Defense date and country 2016-12-15, Croatia
Scientific / art field, discipline and subdiscipline TECHNICAL SCIENCES Computing
Abstract Kada se pokušava objasniti nešto što ima kompleksnu i opširnu primjenu kao što to ima Bayes-ov teorem, jako je teško zapravo predstaviti ga u punom svjetlu. Ovaj teorem, iako jednostavan u teoriji, ima neizmjerno veliku i kompliciranu primjenu kroz razne industrijske, statističarske i gospodarske grane. Cilj je kroz ovaj rad napraviti kratak uvod i pregled osnova Bayes-ovog teorema i njegove primjene. Počevši od definiranja teorema i njegovih osnovnih karakteristika, prelazimo na pregled teorema kroz najjednostavnije probleme. Počevši od jednostavnih problema kao što je problem izvlačenja kolačića iz nasumičnih zdjela, Elvis-ovog brata blizanca i drugih problema, možemo objasniti na jednostavnim primjerima osnove Bayes-ove statistike i njegovog teorema. Kroz rad prijeći ćemo i na kompliciranije probleme gdje ćemo se prikazati kako korištenje cijele teorije vjerojatnost i Bayes-ovog teorema ima primjenu u stvarnom životu i kompliciranijim problemima. Problemi kao što su Oliver-ova krv, njemački tenkovi i Monty Hall su samo neki od primjera stvarnih i čestih problema koji se mogu riješiti koristeći teoriju vjerojatnosti. Nemoguće je prikazati potpune mogućnosti Bayes-ove statistike i njegovog teorema, stoga ćemo prikazati kratak pregled i uvod u napredne mogućnosti samog teorema u rješavanju višedimenzionalne problematike. Oni koji žele saznati više o naprednim mogućnostima i raznim primjenama, mogu pronaći razne reference i literature u posebnom poglavlju.
Abstract (english) When trying to explain something as complex as the Bayes theorem, it's rather hard to do it justice. This theorem, even though it is simple in theory, has a rather huge and complex application throughout different industrial, statisthical, economical and business enterprises and institutions. It's hard to really shine a light on the full spectrum of it's possibilities. However, the goal was to make a short and intuitive compedium of the basics of the Bayes theorem and it's application. Starting off with the definition of the theorem and it's basic characteristics, we advance to the implementation of the theorem in the simplest of problems. Starting with the simple problems, such as pulling a vanilla cookie from random bowls, the identical twin of Elvis and others , we try to explain the basics of the Bayesian statistics and it's theorem. Throughout the compedium, we shall go over the more complicated problems where we shall display how using the entire theory of probability and the Bayesian theorem has a significant role in every day tasks and more complex issues. Problems such as Oliver's blood, german tanks and Monty Hall, are just some of the often and real issues that can be solved using the theory of probability. Since it is impossible to showcase the full potential of the Bayesian statistics and it's theorem we will showcase a short overview into the more advanced and really complex capabilities and applications of the theorem when dealing with multidimensional problems. Those who want to know more, can find references and literature in the appropriate section.
Keywords
Bayes
statistika
Bayesov teorem
Python
vjerojatnost
pretpostavke
procjene
Euro problem
napredne primjene
distribucije podataka vjerojatnosti
Keywords (english)
Bayes
statistika
Bayesian theorem
Python
probability
assumptions
evaluations
Euro problem
advanced applications
data distribution
likelihood
Language croatian
URN:NBN urn:nbn:hr:166:077667
Study programme Title: Computer Science; specializations in: major in teaching Course: major in teaching Study programme type: university Study level: graduate Academic / professional title: magistar/magistra edukacije informatike (magistar/magistra edukacije informatike)
Type of resource Text
File origin Born digital
Access conditions Open access
Terms of use
Created on 2017-07-05 15:49:10