Ordinal Data Causality Analysis Using Polychoric Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining causality between ordinal data lack precision and accuracy, as existing solutions for continuous and discrete variables are not applicable to ordinal data, resulting in low precision in describing causality between various ordinal data.
Innovation Solution
A method is proposed that involves obtaining multiple samples with ordinal data, constructing a first causal structure, and iteratively refining it to create a second causal structure using expert knowledge and objective functions to accurately represent causality between ordinal data, utilizing techniques such as polychoric correlation and maximum likelihood estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing methods for continuous and discrete variables are applied to ordinal data, then the analysis can be performed, but the precision and accuracy of determining causality deteriorates
Solution Approach 1:
The patent transforms the measurement scale parameter from continuous/discrete to ordinal by introducing polychoric correlation coefficients specifically designed for ordinal data. This parameter change enables accurate causality determination while maintaining compatibility with the ordinal measurement level, resolving the contradiction between precision and adaptability.
Solution Approach 2:
The patent introduces polychoric correlation as an intermediary statistical tool that bridges the gap between ordinal data and causality analysis. This intermediary enables the application of causal inference methods to ordinal data without sacrificing precision, as it properly accounts for the ordinal measurement scale properties.
2Measurement precision
If complex causal structure refinement is performed, then the accuracy of causality determination is improved, but the computational overhead increases
Solution Approach 1:
The patent performs preliminary action by pre-calculating polychoric correlation coefficients and preliminary causal structures before final refinement. This preliminary processing organizes the data and identifies key relationships upfront, reducing the computational complexity of subsequent causal structure refinement while maintaining high accuracy.
Solution Approach 2:
The patent applies partial action by focusing computational resources on refining only the most critical causal relationships identified through preliminary analysis. Instead of exhaustively refining all possible causal structures, it concentrates computational effort on the most significant relationships, achieving high accuracy with reduced computational overhead.
Data Source
AI summary
The present disclosure relates to a method, apparatus, device and storage medium for information processing. Specifically, a method is proposed for information processing. In the method, multiple samples associated with multiple ordinal data in an application system are obtained, each sample among the multiple samples comprising multiple dimensions, a dimension among the multiple dimensions corresponding to ordinal data among the multiple ordinal data. Based on the multiple samples, a first causal structure and a second causal structure representing the causality between the multiple ordinal data are provided, the second causal structure being obtained based on the first causal structure. Further, there is provided an apparatus, device and storage medium for information processing. With example implementations of the present disclosure, the first causal structure and the second causal structure are provided based on the multiple samples, the causality may be determined in a simple and effective way, and the credibility of the causality may be increased.