Statistics and neural networks are analytical methods used to learn about observed experience. Both the statistician and neural network researcher develop and analyze data sets, draw relevant conclusions, and validate the conclusions. They also share in the challenge of creating accurate predictions of future events with noisy data.
Both analytical methods are investigated. This is accomplished by examining the veridicality of both with real system data. The real system used in this project is a database of 400 years of historical military combat. The relationships among the variables represented in this database are recognized as being hypercomplex and nonlinear.
The historical database was investigated from two paradigms. Paradigm I states that predicting the winner of combat can be based on post-combat personnel losses. Paradigm II states that predicting the winner can be based on pre-combat initial conditions of personnel strength and skill factors.
The results give evidence that traditional statistical methods may provide greater accuracy in predictions when the data is clean or filtered (perfect) than when it is noisy and unfiltered (imperfect). Neural networks, on the other hand, may provide greater accuracy for the same predictions when the data is left imperfect than when it is cleaned up and filtered (perfect).
","abstract_html":"<p>Statistics and neural networks are analytical methods used to learn about observed experience. Both the statistician and neural network researcher develop and analyze data sets, draw relevant conclusions, and validate the conclusions. They also share in the challenge of creating accurate predictions of future events with noisy data.</p> <p>Both analytical methods are investigated. This is accomplished by examining the veridicality of both with real system data. The real system used in this project is a database of 400 years of historical military combat. The relationships among the variables represented in this database are recognized as being hypercomplex and nonlinear.</p> <p>The historical database was investigated from two paradigms. Paradigm I states that predicting the winner of combat can be based on post-combat personnel losses. Paradigm II states that predicting the winner can be based on pre-combat initial conditions of personnel strength and skill factors.</p> <p>The results give evidence that traditional statistical methods may provide greater accuracy in predictions when the data is clean or filtered (perfect) than when it is noisy and unfiltered (imperfect). Neural networks, on the other hand, may provide greater accuracy for the same predictions when the data is left imperfect than when it is cleaned up and filtered (perfect).</p>","abstract_has_math":false,"creators":["Hedgepeth, William Oliver"],"institution":null,"degree_name":"Doctor of Philosophy (PhD)","degree_level":"Dissertation","degree_discipline":"Engineering Management & Systems Engineering","degree_department":null,"school":null,"contributors":["Derya A. Jacobs","Laurence D. Richards","Billie M. Reed","Mark Scerbo"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":1995,"date_issued":"1995-01-01T08:00:00Z","date_published":"1995-01-01T08:00:00Z","updated_at":"2026-07-24T03:34:25Z","subjects":["Paradigm","Observed experience","Statistical models","Neural network models","Artificial Intelligence and Robotics","Industrial Engineering","Psychology"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.odu.edu/emse_etds/77","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Derya A. Jacobs","Laurence D. Richards","Billie M. Reed","Mark Scerbo"]},{"key":"dc:creator","label":"Author","values":["Hedgepeth, William Oliver"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2019-03-15T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Engineering Management & Systems Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy (PhD)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Paradigm","Observed experience","Statistical models","Neural network models","Artificial Intelligence and Robotics","Industrial Engineering","Psychology"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.odu.edu/emse_etds/77"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Statistics and neural networks are analytical methods used to learn about observed experience. Both the statistician and neural network researcher develop and analyze data sets, draw relevant conclusions, and validate the conclusions. They also share in the challenge of creating accurate predictions of future events with noisy data.
Both analytical methods are investigated. This is accomplished by examining the veridicality of both with real system data. The real system used in this project is a database of 400 years of historical military combat. The relationships among the variables represented in this database are recognized as being hypercomplex and nonlinear.
The historical database was investigated from two paradigms. Paradigm I states that predicting the winner of combat can be based on post-combat personnel losses. Paradigm II states that predicting the winner can be based on pre-combat initial conditions of personnel strength and skill factors.
The results give evidence that traditional statistical methods may provide greater accuracy in predictions when the data is clean or filtered (perfect) than when it is noisy and unfiltered (imperfect). Neural networks, on the other hand, may provide greater accuracy for the same predictions when the data is left imperfect than when it is cleaned up and filtered (perfect).
"]},{"key":"dc:title","label":"Title","values":["Comparing Traditional Statistical Models with Neural Network Models: The Case of the Relation of Human Performance Factors to the Outcomes of Military Combat"]}]}],"canonical_facts":{"dc:contributor":["Derya A. Jacobs","Laurence D. Richards","Billie M. Reed","Mark Scerbo"],"dc:creator":["Hedgepeth, William Oliver"],"dc:date.available":["2019-03-15T07:00:00Z"],"dc:description.abstract":["Statistics and neural networks are analytical methods used to learn about observed experience. Both the statistician and neural network researcher develop and analyze data sets, draw relevant conclusions, and validate the conclusions. They also share in the challenge of creating accurate predictions of future events with noisy data.
Both analytical methods are investigated. This is accomplished by examining the veridicality of both with real system data. The real system used in this project is a database of 400 years of historical military combat. The relationships among the variables represented in this database are recognized as being hypercomplex and nonlinear.
The historical database was investigated from two paradigms. Paradigm I states that predicting the winner of combat can be based on post-combat personnel losses. Paradigm II states that predicting the winner can be based on pre-combat initial conditions of personnel strength and skill factors.
The results give evidence that traditional statistical methods may provide greater accuracy in predictions when the data is clean or filtered (perfect) than when it is noisy and unfiltered (imperfect). Neural networks, on the other hand, may provide greater accuracy for the same predictions when the data is left imperfect than when it is cleaned up and filtered (perfect).
"],"dc:identifier":["https://digitalcommons.odu.edu/emse_etds/77"],"dc:subject":["Paradigm","Observed experience","Statistical models","Neural network models","Artificial Intelligence and Robotics","Industrial Engineering","Psychology"],"dc:title":["Comparing Traditional Statistical Models with Neural Network Models: The Case of the Relation of Human Performance Factors to the Outcomes of Military Combat"],"thesis:degree_discipline":["Engineering Management & Systems Engineering"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Doctor of Philosophy (PhD)"]},"updated_at":"2026-07-24T03:34:25Z"}