Bayesian data mining techniques in public health and biomedical applications

To my family, in Korea and in Atlanta. iii ACKNOWLEDGEMENTS I am deeply indebted to my advisor Dr. Brani Vidakovic for his guidance and support in countless ways. Without his enlightening instruction, great kindness and patience, unwavering enthusiasm and trust, I could not have completed my thesis. I also want to extend my gratitude to my thesis committee members, Dr. for all their careful reviewing and insightful comments. Their detailed reviews and constructive comments greatly improved this thesis. Many thanks to my CDC-ORISE fellowship supervisors, Laurie Barker and Susan Griffin. They have provided me a wonderful environment and full support to pursue my research. I could not have imagined having better supervisors. Thank you also to my fellow graduate students, especially Hyojung Kang and Chia-Jung Chang. You all have made my life in Atlanta so much more meaningful. Finally, and most importantly, I would like to thank my family. I wouldn't have made it this far without their constant prayer, support, and love. 1 Summary measures and their variance for discrete data meta-analysis. 14 Logistic classification based on the wavelet spectra slope; five different estimation methods were compared, each with real-valued (DWT) and complex (DCWT) wavelet transform. .