Abstract indicator frameworks address a critical gap in operational indicator design by providing mathematically rigorous foundations for understanding relationships between system variables. This is innovative because it bridges category theory, probabilistic reasoning, and practical system design, enabling more sophisticated analyses that account for mediating variables and complex interdependencies often missed in traditional frameworks.
This work develops abstract indicator frameworks, a diagrammatic tool for constructing correlations between random variables in systems. The approach models operational indicators using process theory, including composition and tensoring of processes. The paper extends categorical theory approaches to indicator analysis, using Rand diagrams and process theories to capture both causal and statistical aspects of complex systems.
The paper demonstrates how abstract indicator frameworks can represent diverse systems including air pollution monitoring and urban planning scenarios. It shows how correlation networks can analyze high-dimensional systems by focusing on weighted correlations and soft thresholds. The approach successfully enables intuitive system descriptions while maintaining mathematical precision for causal and statistical interpretation.
@inproceedings{Tan2017,
author = {Tan, Joshua and Kendrick, Christine and Dubey, Abhishek and Rhee, Sokwoo},
booktitle = {Proceedings of the 2nd International Workshop on Science of Smart City Operations and Platforms Engineering, SCOPE@CPSWeek 2017, Pittsburgh, PA, USA, April 21, 2017},
title = {Indicator frameworks},
year = {2017},
pages = {19--25},
abstract = {We develop a diagrammatic tool for constructing correlations between random variables, called an abstract indicator framework. Abstract indicator frameworks are modeled o operational (key performance) indicator frameworks as they are used in city planning and project governance, and give a rigorous, statistically-motivated process for constructing operational indicator frameworks.},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/bib/conf/cpsweek/TanKDR17},
category = {workshop},
contribution = {minor},
doi = {10.1145/3063386.3063762},
file = {:Tan2017-indicator_frameworks.pdf:PDF},
project = {smart-cities},
timestamp = {Tue, 06 Nov 2018 16:59:05 +0100},
url = {https://doi.org/10.1145/3063386.3063762},
keywords = {indicator frameworks, category theory, process theory, causal networks, correlation analysis, system design, operational indicators}
}