Bayesian inference of Ethiopian politics: The case of mid-term election in Addis Ababa


Yalemzewd Negash Shiferaw*

Bayesian Inference, a statistical method that utilizes Bayes’ Theorem, employs data to update prior beliefs about parameters. Bayesian method is characterized by its explicit use of probability to quantify uncertainty in statistical data analysis-based inferences. This paper applies Bayesian data analysis to infer the voting intensions of the Addis Ababa residents for the ruling party assuming a mid-term election is held in November 2023. By incorporating prior beliefs derived from previous election results and data from survey, the posterior probability of the ruling party’s election outcome is estimated. Subsequently, a sensitivity analysis is performed to assess the influence of prior choice of the results. Despite the polling results showing a 32% share for the ruling party, Bayesian analysis, when combined with historical information (results of the previous elections), suggests that the ruling party will secure 60% of the parliamentary seats representing Addis Ababa.

Share this article

Awards Nomination

Select your language of interest to view the total content in your interested language

Indexed In
  • Index Copernicus
  • Google Scholar
  • Open J Gate
  • Genamics JournalSeek
  • CiteFactor
  • OCLC- WorldCat
  • Eurasian Scientific Journal Index
  • Rootindexing
  • Academic Resource Index
  • African e-journals Project
  • Africa Bibliographic Database
  • Center for Research Libraries
  • University of Leiden Catalogue
  • African Journals OnLine (AJOL)
  • African Studies Centre
  • University of Saskatchewan Library
  • University of Toronto Libraries
  • Mirabel Network
  • Michigan State University Library
  • Jstor Library