Forecasting leadership transitions around the world

Neila Cáceres and Samuel Malone

International Journal of Forecasting, 2013, vol. 29, issue 4, 575-591

Abstract: We use popular non-parametric (CART, TreeNet) and parametric (logit) techniques to identify robust economic, demographic and political conditions that lead to shifts in control in the executive branch of government in 162 countries during the period 1960–2004. We find that institutional aspects of the political system, executive characteristics, demographic variables, economic growth, and economic trade variables are all very important for predicting leadership turnover in the following year. Financial crises are not robustly useful for this purpose, but a vulnerability to currency crises in times of low economic growth implies very high conditional probabilities of job losses for democratic leaders in non-election years. In-sample, TreeNet predicts 78% of leadership transition events correctly, compared to CART’s 70%, and TreeNet also generally achieves higher overall prediction accuracies than either CART or the logit model out-of-sample.

Keywords: Classification; Economic growth; Financial crises; Elections (search for similar items in EconPapers)
Date: 2013
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0169207013000411
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:intfor:v:29:y:2013:i:4:p:575-591

DOI: 10.1016/j.ijforecast.2013.01.011

Access Statistics for this article

International Journal of Forecasting is currently edited by R. J. Hyndman

More articles in International Journal of Forecasting from Elsevier
Bibliographic data for series maintained by Catherine Liu ().