Bc. Michal Humaj

Master's thesis

Bayesian and Sequential Evaluation Techniques Comparison in Online Experiments

Bayesian and Sequential Evaluation Techniques Comparison in Online Experiments
Abstract:
A / B testovanie je výborná metóda na zlepšenie kľúčových metrík webových stránok. V práci prezentujeme prehľad literatúry zameranej na štatistické metódy použité pri A/B testovaní . Niektorí autori uprednostňujú bayesianské paradigmu, iní frekventistické. Nie je medzi bayesiánmi ani konsenzus o tom, do akej miery je dôležité prvotné rozdelenie a či sa dá objektívne naučiť. Autori sa však zhodujú v …more
Abstract:
A/B testing is a powerful method for improving website performance. We present overview of the literature focused on statistical methods used in A/B testing. Some authors prefer bayesian paradigm, others frequentist. Amongst bayesians, there is also no consensus to what extent is the prior distribution important and whether it can be objectively learnt. However, authors agree that in an online environment …more
 
 
Language used: English
Date on which the thesis was submitted / produced: 21. 5. 2018

Thesis defence

  • Date of defence: 21. 6. 2018
  • Supervisor: PhD Bruno Rossi
  • Reader: Mgr. David Komárek

Citation record

Full text of thesis

Contents of on-line thesis archive
Published in Theses:
  • světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatiky

Masaryk University

Faculty of Informatics

Master programme / field:
Applied Informatics / Service Science, Management and Engineering