Doctor of Philosophy, The Ohio State University, 2024, Industrial and Systems Engineering

This dissertation addresses two applied problems relating to images. The first relates to images of pipeline corrosion and the second relates to images of the human brain and individuals with Attention-Deficit/Hyperactivity Disorder (ADHD). The corrosion of oil and gas pipelines is important because there are thousands of leaks every year costing billions of dollars for cleanups. ADHD is important because a substantial fraction of the world population has the disorder causing significant suffering and hundreds of billions of dollars of losses to the world economy. To address both image analysis problems, novel statistical and operations research techniques are proposed which have potentially wide applicability. Relating to pipeline corrosion, an established simulation method is called the “voxel” method which permits predictions about how images and pipelines or other media will change as corrosion evolves. In most realistic cases, we find that the parameter values or “inputs” (Xs) needed to run the simulation are unknown. We only have the images which are essentially outputs (Ys) which can be generated by real world experiments or simulations. The phenomenon of having incomplete inputs for simulation is common in many engineering and science situations and a critical challenge for both people and artificial intelligence. We and others have called this important subject, “empirical forward-inverse estimation” since we can gather data (empirically) in the forward manner progressing from assumed inputs (Xs) to measured outputs (Ys) and then generate inverse predictions from Ys to Xs. With (hopefully) accurately estimated X values, the experimental setup or simulation can then predict the future corrosion evolution and whether repair in critically needed. Relating to forward-inverse analyses, 24 variants of an established two stage method or framework are studied in relation to enhanced inverse prediction accuracy for two test cases including pipeline corrosion (open full item for complete abstract)

Committee: Theodore T. Allen (Advisor); William (Bill) Notz (Committee Member); Samantha Krening (Committee Member); Marat Khafizov (Committee Member) Subjects: Engineering; Industrial Engineering; Materials Science; Statistics

Doctor of Philosophy, The Ohio State University, 1987, Graduate School

Committee: Not Provided (Other) Subjects: Statistics

Doctor of Philosophy, The Ohio State University, 1986, Graduate School

Committee: Not Provided (Other) Subjects: Statistics

Doctor of Philosophy, The Ohio State University, 1983, Graduate School

Committee: Not Provided (Other) Subjects: Statistics

Doctor of Philosophy, The Ohio State University, 1982, Graduate School

Committee: Not Provided (Other) Subjects: Psychology

Doctor of Philosophy, The Ohio State University, 1981, Graduate School

Committee: Not Provided (Other) Subjects: Statistics

Doctor of Philosophy, The Ohio State University, 1970, Graduate School

Committee: Not Provided (Other) Subjects: Engineering

Doctor of Philosophy (PhD), Ohio University, 2010, Educational Research and Evaluation (Education)

The Type I error rate inflates greatly when multiple hypotheses are tested using an unadjusted alpha per test procedure. Therefore, several alpha-adjustment Multiple Hypothesis Testing (MHT) procedures can be used to control the Type I error inflation while providing adequate statistical power. There are numerous statistical designs that involve MHT, such as factorial ANOVA. This study investigated the Type I error rates and statistical power rates of several alpha-adjustment MHT procedures (Bonferroni, Holm, Hochberg, and Benjamini-Hochberg (B-H)) in a balanced factorial ANOVA. Three indicators for Type I error rates were used: samplewise familywise error rate (SFWER), testwise familywise error rate (TFWER), and false discovery rate (FDR). Three criteria for statistical power rates were employed: samplewise power (SPOWER), testwise power (TPOWER), and true discovery rate (TDR). MHT procedures were also compared to the unadjusted alpha per test procedure. All statistical analyses were done with 20,000 replications as a Monte Carlo simulation in the R programming language. Two-way and three-way fixed-effects balanced designs were analyzed. The sample size per cell was 32 in the two-way and 16 for the three-way. A medium effect size of .50 for all false null effects was used to create data with different patterns of means. MHT procedures were found to have advantages over the unadjusted alpha per test procedure in terms of controlling the Type I error inflation at an accurate level. Specifically, Bonferroni, Holm, and Hochberg were better able to control the Type I error rates at .05. The SFWER and FDR from the B-H procedure inflate under certain conditions. The Bonferroni procedure has the lowest power while the B-H procedure has the greatest power. The Hochberg procedure worked best in this study overall. However, if the independence assumption is not met, the Holm procedure can be the best choice.

Committee: Gordon Brooks PhD (Committee Chair); George Johanson PhD (Committee Member); Valerie Conley PhD (Committee Member); Bruce Carlson PhD (Committee Member) Subjects: Educational Evaluation; Educational Psychology; Statistics