Support vector regression and beta distribution for modeling incumbent party for presidential elections
OUTPUT TYPE: Journal Article
PUBLICATION YEAR: 2020
TITLE AUTHOR(S): C.R.Kikawa, M.N.Ngungu, D.Ntirampeba, A.Ssematimba
KEYWORDS: ELECTION DATA, ELECTIONS, MULTIVARIATE ANALYSIS, STATISTICS
DEPARTMENT: Developmental, Capable and Ethical State (DCES)
Print: HSRC Library: shelf number 11628
HANDLE: 20.500.11910/15531
URI: http://hdl.handle.net/20.500.11910/15531
If you would like to obtain a copy of this Research Output, please contact Hanlie Baudin at researchoutputs@hsrc.ac.za.
Abstract
The present paper aims to model, predict, and explain presidential election results using selected quarterly macroeconomic indicators, i.e., gross national product, consumer price index, unemployment rate and gross national product from 1994-2017. We also seek to provide predictions of presidential winner prior to the elections based on the beta distribution and the support vector regression (SVR) as prediction models.Two models are primarily built based on beta distribution and SVR. Due to the forecasting aspect, model performance focuses on one goodness-of-fit measure, i.e., the prediction error rather than the squared correlation coefficient R2 as it makes little sense in a practical regression perspective. The best model is the one with the least mean square error (MSE). In this effect it turns out that the SVR with kernel type encapsulated postscript eps radial has a mean square error of 0.006 on the test set and is a better model compared to the beta distribution model with a mean square error of 1.216. Thu, an accurate solution to prediction of presidential vote elections via SVR analysis is proposed.-
Related Research Outputs:
- Popular attitudes towards the South African electoral system: report to the electoral task team.
- An unlikely success: South Africa and Lesotho's election of 2002
- Managing the design and development of a data warehouse: a case study of the HSRC's human resources development data warehouse project
- Public participation in South Africa as we enter the 21st century
- Politics, voting and elections
- Voters' evaluation of the 2000 local government elections in South Africa
- Towards more effective crime prevention in South Africa: the necessity of basic building blocks. Part 1
- Crime analysis and forecasting in South Africa: the need for information. Part 2
- Crime analysis and forecasting in South Africa: the need for information. Part 4
- The social dynamics in public participation in legislative processes in South Africa
- Lesotho: electoral landslide Heralds return to shaky democracy
- Democracy South Africa: evaluating the 1999 election
- Decoding South Africa's 1999 electoral geography
- Politics and voting
- 1998 crime statistics with 1996 census data
- Voting in action: focus group and workshop findings
- Popular attitudes toward the South African electoral system
- Adapting to electoral system change: voters in Lesotho, 2002
- Small parties to face oblivion
- Who will woo her on 14 April?: targeting the female electorate