Search results

In the last decade advances in statistics, computing power, and data collection has led to an increased interest in forecasting within the field of peace and conflict research and to the adoption of a wide range of methodological approaches for making such forecasts. By making use of these more powerful forecasting methods researchers have been able to produce accurate predictions, as well as better inferences, of many different types of contentious politics events and to create operational early warning systems for such events. Adapting these forecasting methods to the social world in which politics and political behavior operate, however, is not without its challenges. This dissertation explores a number of methodological issues and advances in peace and conflict research, both inferential and forecasting oriented, through a series of four papers. In the first paper, I explore trends in democratization and autocratization using dynamic simulation. In Paper II, my co-author and I take aim at the difficulty of modeling and making forecasts with data which contains both excess zeroes and extreme-values. We propose an extreme-value and zero-inflated regression model which we use to replicate a study on the effects of UN peacekeepers on violence against civilians. Paper III explores latent variable modeling by using Markov models to make forecasts for escalation and de-escalation of armed conflicts. In the last paper, I investigate the effects of missing data and imputation techniques on the predictive performance of models. The four papers of the dissertation make several contributions to the growing literature of forecasting within peace and conflict research. First, the dissertation contributes to the methodological aspects of conflict forecasting by developing new statistical tools, Paper II, and adapting tools from other fields to different processes of armed conflict and contentious politics, Papers I & III, as well as by evaluating the practical effects of common choices in data pre-processing on the performance of forecasts in Paper IV. Second, the dissertation contributes to new ways of drawing inferences about conflict processes by anchoring the inferences in the latent state of the conflict processes in Papers II & III, and through the comparison of aggregated simulations to the historical record in Paper I. Lastly, the dissertation makes a substantive contribution to the broader field of peace and conflict research in Papers I & II by contributing to the debate on the waves of democratization and autocratization, and by nuancing the impact of UN Peacekeepers on violence against civilians.

In the last decade advances in statistics, computing power, and data collection has led to an increased interest in forecasting within the field of peace and conflict research and to the adoption of a wide range of methodological approaches for making such forecasts. By making use of these more powerful forecasting methods researchers have been able to produce accurate predictions, as well as better inferences, of many different types of contentious politics events and to create operational early warning systems for such events. Adapting these forecasting methods to the social world in which politics and political behavior operate, however, is not without its challenges. This dissertation explores a number of methodological issues and advances in peace and conflict research, both inferential and forecasting oriented, through a series of four papers. In the first paper, I explore trends in democratization and autocratization using dynamic simulation. In Paper II, my co-author and I take aim at the difficulty of modeling and making forecasts with data which contains both excess zeroes and extreme-values. We propose an extreme-value and zero-inflated regression model which we use to replicate a study on the effects of UN peacekeepers on violence against civilians. Paper III explores latent variable modeling by using Markov models to make forecasts for escalation and de-escalation of armed conflicts. In the last paper, I investigate the effects of missing data and imputation techniques on the predictive performance of models. The four papers of the dissertation make several contributions to the growing literature of forecasting within peace and conflict research. First, the dissertation contributes to the methodological aspects of conflict forecasting by developing new statistical tools, Paper II, and adapting tools from other fields to different processes of armed conflict and contentious politics, Papers I & III, as well as by evaluating the practical effects of common choices in data pre-processing on the ...

This article presents an update to the ViEWS political Violence Early-Warning System. This update introduces (1) a new infrastructure for training, evaluating, and weighting models that allows us to more optimally combine constituent models into ensembles, and (2) a number of new forecasting models that contribute to improve overall performance, in particular with respect to effectively classifying high- and low-risk cases. Our improved evaluation procedures allow us to develop models that specialize in either the immediate or the more distant future. We also present a formal, 'retrospective' evaluation of how well ViEWS has done since we started publishing our forecasts from July 2018 up to December 2019. Our metrics show that ViEWS is performing well when compared to previous out-of-sample forecasts for the 2015–17 period. Finally, we present our new forecasts for the January 2020–December 2022 period. We continue to predict a near-constant situation of conflict in Nigeria, Somalia, and DRC, but see some signs of decreased risk in Cameroon and Mozambique.

This article presents an update to the ViEWS political Violence Early-Warning System. This update introduces (1) a new infrastructure for training, evaluating, and weighting models that allows us to more optimally combine constituent models into ensembles, and (2) a number of new forecasting models that contribute to improve overall performance, in particular with respect to effectively classifying high- and low-risk cases. Our improved evaluation procedures allow us to develop models that specialize in either the immediate or the more distant future. We also present a formal, 'retrospective' evaluation of how well ViEWS has done since we started publishing our forecasts from July 2018 up to December 2019. Our metrics show that ViEWS is performing well when compared to previous out-of-sample forecasts for the 2015-17 period. Finally, we present our new forecasts for the January 2020-December 2022 period. We continue to predict a near-constant situation of conflict in Nigeria, Somalia, and DRC, but see some signs of decreased risk in Cameroon and Mozambique.

This article presents ViEWS – a political violence early-warning system that seeks to be maximally transparent, publicly available, and have uniform coverage, and sketches the methodological innovations required to achieve these objectives. ViEWS produces monthly forecasts at the country and subnational level for 36 months into the future and all three UCDP types of organized violence: state-based conflict, non-state conflict, and one-sided violence in Africa. The article presents the methodology and data behind these forecasts, evaluates their predictive performance, provides selected forecasts for October 2018 through October 2021, and indicates future extensions. ViEWS is built as an ensemble of constituent models designed to optimize its predictions. Each of these represents a theme that the conflict research literature suggests is relevant, or implements a specific statistical/machine-learning approach. Current forecasts indicate a persistence of conflict in regions in Africa with a recent history of political violence but also alert to new conflicts such as in Southern Cameroon and Northern Mozambique. The subsequent evaluation additionally shows that ViEWS is able to accurately capture the long-term behavior of established political violence, as well as diffusion processes such as the spread of violence in Cameroon. The performance demonstrated here indicates that ViEWS can be a useful complement to non-public conflict-warning systems, and also serves as a reference against which future improvements can be evaluated.

This article presents ViEWS – a political violence early-warning system that seeks to be maximally transparent, publicly available, and have uniform coverage, and sketches the methodological innovations required to achieve these objectives. ViEWS produces monthly forecasts at the country and subnational level for 36 months into the future and all three UCDP types of organized violence: state-based conflict, non-state conflict, and one-sided violence in Africa. The article presents the methodology and data behind these forecasts, evaluates their predictive performance, provides selected forecasts for October 2018 through October 2021, and indicates future extensions. ViEWS is built as an ensemble of constituent models designed to optimize its predictions. Each of these represents a theme that the conflict research literature suggests is relevant, or implements a specific statistical/machine-learning approach. Current forecasts indicate a persistence of conflict in regions in Africa with a recent history of political violence but also alert to new conflicts such as in Southern Cameroon and Northern Mozambique. The subsequent evaluation additionally shows that ViEWS is able to accurately capture the long-term behavior of established political violence, as well as diffusion processes such as the spread of violence in Cameroon. The performance demonstrated here indicates that ViEWS can be a useful complement to non-public conflict-warning systems, and also serves as a reference against which future improvements can be evaluated.