Determining the importance of nationality on the outcome of battles using classification trees
Lucas, Thomas W.
Buttrey, Samuel E.
MetadataShow full item record
Throughout history people have searched for a means of predicting the outcomes of battles. Data analysis is a way of understanding the factors associated with battle outcomes. There are objective factors, such as force ratio, and subjective factors, such as leadership, that affect battles. Subjective factors are hard to determine and thus are usually avoided in models. Here, nationality is investigated as a surrogate for subjective factors. That is, we want to see how nationality is associated with battle outcomes by exploring the best available data set on historical land combat-developed by the Center for Army Analysis. We focus on four countries for which there is sufficient data: the USA, Germany, Britain and Israel. We find that these countries historically use a substantial amount of military power to defeat their enemies. In particular, the USA often has overwhelming force. Using classification tree models, with a correct classification rate of 79 percent, the results suggest that nationality was the most important factor in battles before World War I and the second most important factor during the World Wars. Force ratio was the most important factor in WWI and artillery ratio in WWII. In the years following WWII, the dominant variable has been air force ratio.
Approved for public release; distribution is unlimited
Showing items related by title, author, creator and subject.
Coban, Muzaffer. (Monterey, California. Naval Postgraduate School, 2001-12);Historical combat data analysis is a way of understanding the factors affecting battle outcomes. Current studies mostly prefer simulations that are based on mathematical abstractions of battles. However, these abstractions ...
Maritime military decision making in environments of extreme information ambiguity an initial exploration Reeves, Andrew T. (Monterey, California. Naval Postgraduate School, 2005-09);This thesis examines the following hypothesis: Through the combined use of common training and collaborative planning, a decision maker may sufficiently alleviate the harmful effects of an environment of information so ...
Finding the important factors in battle outcomes: a statistical exploration of data from major battles Yigit, Faruk (Monterey, California. Naval Postgraduate School, 2000-12);This study explores important factors in battle outcomes through a statistical analysis of data from major historical battles. The data set of CDB90FT has been made available and documented by the Center for Army Analysis ...