Recognizing 'Game Changers' in Extrapolation Models: An Application to Counterinsurgency

<p>Recent empirical studies suggest insurgencies may be accurately described by aggregated extrapolation models, such that past behavior becomes the best predictor for future action. I argue that aggregated extrapolation models possess two flaws that make it a poor choice for examining insurgencies. First, aggregated extrapolation models ask the wrong question. The more interesting question is to ask when present action is no longer explainable by past behavior. Secondly, aggregate models mask changes that a phenomenon undergoes over time which are only revealed upon disaggregating the data. Starting with a model and findings provided by Neil Johnson, I use casualty data from the Iraq War to offer an alternative method to identify changes in the phenomenon under observation with the addition of no new data. Presenting an alternate set of findings, I propose it is possible to identify ‘game changer’ events with the introduction of breakpoints to observe for distinct departures from the baseline trajectory</p>

Name thesis:degree_name

M.A.

Level thesis:degree_level

Masters Thesis

Year dc:date.available

2013

Author dc:creator

• Dolcort-Silver, Micah

Contributors dc:contributor

• Erica Chenoweth, Ph.D.
• Ved Nanda
• Barry Hughes
• Lindsay Heger
• Lewis Griffith

• Extrapolation model
• Insurgency
• Power law
• Red Queen hypothesis
• Terrorism
• International Relations
• Political Science

Statement dc:rights

• <p>Copyright is held by the author. User is responsible for all copyright compliance.</p>

Language dc:language

en

Repository record dc:identifier

https://digitalcommons.du.edu/etd/166

OAI identifier oai:identifier

oai:digitalcommons.du.edu:etd-1165