All Times ET
Keywords: Trinary, step-function, air quality, gender/race groups, time series, heath service areas (HSA)
The framework of Trinary (+/0/-) approach for identifying and tracing change over time using short-term transitions will be presented and applied to time-series data for Carbon Monoxide and Nitrogen Dioxide over 20 years in an urban and rural area in northeastern U.S. Switching patterns from +1 to 0 range and from 0 to -1 range were examined with a view to quantifying a decision rule for stability of shifting pattern. This step-function based 3-category approach using switches in patterns serves in clarifying outputs from health related exposure histories. The Cumulative Transitional State Score (CTSS) based upon Trinary classification has been applied to various other scenarios. In Big-Data analytics a Core/Non-Core orientation using "0" as Core and (+/-) as Non-Core also provides delineation ranges within statistical distributions and aids in identifying "hot spots" for further exploration. In a study dealing with lung cancer mortality death rates and race-gender differences in northeastern U.S. Trinary orientation was applied. Mining the database using a Trinary orientation led to identification of "conjoint" (++) identified Health Service Areas (HSA)s in pairs of gender/race groups. Locations in these conjoint subsets represented approximately 5-10 % of the total database and identified observations for further study, demonstrating the pathway to an iterative stepwise approach.