Santos, Bruno R., Bolfarine, Heleno (2015) Analysis of Brazil’s presidential election via Bayesian spatial quantile regression. In: Proceedings of the 30th International Workshop on Statistical Modelling. 2. pp. 247-248. Johannes Kepler University Linz (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:90515)
The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. | |
Official URL: http://www.statmod.org/files/proceedings/iwsm2015_... |
Abstract
We show an extension of Bayesian quantile regression models when the response variable is reported as a proportion and spatial correlation is present. We are specially interested in the data of the last presidential election in Brazil, which was decided by 2% of the valid votes, approximately. We use quantile regression models to show how some sociodemographic variables are associated with different quantiles of the distribution of votes in this close election.
Item Type: | Conference or workshop item (Poster) |
---|---|
Uncontrolled keywords: | Bayesian spatial quantile regression; Asymmetric Laplace predictive process; Brazil’s presidential election data. |
Subjects: | Q Science > QA Mathematics (inc Computing science) > QA297 Numerical analysis |
Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Mathematics, Statistics and Actuarial Science |
Depositing User: | Amy Boaler |
Date Deposited: | 01 Oct 2021 10:05 UTC |
Last Modified: | 17 Aug 2022 11:02 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/90515 (The current URI for this page, for reference purposes) |
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):