University of Tennessee, Knoxville TRACE: Tennessee Research and Creative Exchange Doctoral Dissertations Graduate School 8-2015 Age Estimation with Decision Trees: Testing the Relevance of 94 Aging Indicators on the William M. Bass Donated Collection Kevin Benjamin Dominic Hufnagl University of Tennessee - Knoxville, [email protected] Follow this and additional works at: https://trace.tennessee.edu/utk_graddiss Part of the Biological and Physical Anthropology Commons Recommended Citation Hufnagl, Kevin Benjamin Dominic, "Age Estimation with Decision Trees: Testing the Relevance of 94 Aging Indicators on the William M. Bass Donated Collection. " PhD diss., University of Tennessee, 2015. https://trace.tennessee.edu/utk_graddiss/3425 This Dissertation is brought to you for free and open access by the Graduate School at TRACE: Tennessee Research and Creative Exchange. It has been accepted for inclusion in Doctoral Dissertations by an authorized administrator of TRACE: Tennessee Research and Creative Exchange. For more information, please contact [email protected]. To the Graduate Council: I am submitting herewith a dissertation written by Kevin Benjamin Dominic Hufnagl entitled "Age Estimation with Decision Trees: Testing the Relevance of 94 Aging Indicators on the William M. Bass Donated Collection." I have examined the final electronic copy of this dissertation for form and content and recommend that it be accepted in partial fulfillment of the equirr ements for the degree of Doctor of Philosophy, with a major in Anthropology. Richard Jantz, Major Professor We have read this dissertation and recommend its acceptance: Walter Klippel, Lyle Konigsberg, William Seaver Accepted for the Council: Carolyn R. Hodges Vice Provost and Dean of the Graduate School (Original signatures are on file with official studentecor r ds.) Age Estimation with Decision Trees: Testing the Relevance of 94 Aging Indicators on the William M. Bass Donated Collection A Dissertation Presented for the Doctor of Philosophy Degree The University of Tennessee, Knoxville Kevin Benjamin Dominic Hufnagl August 2015 Acknowledgements Ich bedanke mich bei meinen Eltern, meinen Schwestern, und meinen Grosseltern für all ihre Geduld und Unterstützung über die Jahre. Furthermore I would like to express thanks to the members of my committee for their suggestions and comments that allowed me to polish my dissertation. Thank you to my friends and colleagues at the University for entertaining me otherwise with stories, outings, dinners, and opinions. Thank you for sharing your knowledge and information with me. Thank you to Donna, Heli, and Suzanne for providing me the opportunity to pick their brains, bounce ideas off them, and distracting me when I needed it. They have truly been the cornerstones of my life in Knoxville. ii Abstract Anthropologists have been estimating ages-at-death of skeletons for a long time. A variety of different age indicators has been studied and age estimation methods have been developed in an attempt to standardize the process. Even with all the work that has gone into developing age estimation methods, age estimation of mature skeletons is still very imprecise. This research investigates various age indicator definitions and their performance on an elderly skeletal sample. Using 176 individuals from the William M. Bass Donated Collection, curated in the Department of Anthropology at the University of Tennessee, Knoxville, data were collected on age indicators gathered from fifteen age estimation methods. Ninety-four variables were tested with various decision trees to show patterns among the variables. Regression equations were built using the same variables as the decision trees, and the performance between the two methodologies were compared. The decision trees performed slightly better, with a mean absolute error of prediction of around five years. Variable occurrence was tabulated across various decision tree models. The most common variables are pit shape of the sternal rib end morphology and the phase of the auricular phase. These two variables, along with others commonly selected, present best candidates for building an age estimation method that pertains to older populations. iii Table of Contents Chapter 1: Introduction ................................................................................................................1 Chapter 2: Literature Review .....................................................................................................11 History of Age Determination ...........................................................................................11 Origins....................................................................................................................11 Phase Methods .......................................................................................................13 Component Methods ..............................................................................................21 Multi-Trait Methods...............................................................................................34 Problems in Age Determination.........................................................................................39 Variation in Aging .............................................................................................................44 Interpersonal Variation ......................................................................................................45 Population Differences...........................................................................................45 Pubic Symphysis ........................................................................................47 Auricular Surface .......................................................................................48 Sternal Rib Ends ........................................................................................49 Cranial Sutures ...........................................................................................49 Sex Differences ......................................................................................................50 Pubic Symphysis ........................................................................................52 Auricular Surface .......................................................................................54 Sternal Rib Ends ........................................................................................55 Cranial Sutures ...........................................................................................55 iv Intrapersonal Variation ......................................................................................................56 Observer Error ...................................................................................................................59 Interobserver Error .................................................................................................62 Intraobserver Error .................................................................................................64 Method Validation and Reliability Testing ........................................................................64 Sample Appropriateness ........................................................................................66 Inaccurate Aging of the Elderly .............................................................................69 Regression to the Mean ..........................................................................................71 Age Mimicry ..........................................................................................................73 Examples of Method Validation ............................................................................76 Chapter 3: Materials....................................................................................................................83 The Skeletons .....................................................................................................................83 The Sample ........................................................................................................................84 The Variables .....................................................................................................................88 Chapter 4: Methods .....................................................................................................................91 Variable Manipulation .......................................................................................................91 Missing Data ..........................................................................................................91 Additional Variables ..............................................................................................92 Decision Trees ...................................................................................................................93 Analysis..............................................................................................................................96 Chapter 5: Results......................................................................................................................104 Notation............................................................................................................................104 Chi-Squared Automatic Interaction Detection (CHAID) Decision Trees .......................105 v Classification and Regression Tree (CRT) Decision Trees .............................................125