Triangulation Research is a research program studying what happens when two ways of answering the same medical question disagree, across four lines of work: agreement methods, diagnostic boundaries, cross-design evidence and ecological inference. Research Program →
Methods. Recovering the 2×2 table behind a published agreement statistic from the figures a study already prints; reading from the table whether switching criteria only adds patients or also drops some; and testing whether two definitions of a disease disagree more than one definition’s own implementations. See enum2x2 and enum2x2-r.
Reporting. Studies comparing criteria already compute the 2×2 table and should print it; four reporting fields would make the patients a criterion revision adds or removes visible from enrollment records.
Reproducibility. Analyses are preregistered before they are run, code and data are public, and quoted source values are checked against their sources.
People
Elliot Tower
Background in mathematics, philosophy, and machine learning. M.S. Computer Science (Data Science), UMass Amherst.