Causal Interfaces
This work addresses a methodological issue in causal inference for researchers, though it appears incremental as it builds on existing frameworks without broad application.
The paper tackles the problem of oversimplifying causal influence between binary variables by proposing a two-constant representation for positive and negative implications, deriving various measures to contrast with traditional one-dimensional indices.
The interaction of two binary variables, assumed to be empirical observations, has three degrees of freedom when expressed as a matrix of frequencies. Usually, the size of causal influence of one variable on the other is calculated as a single value, as increase in recovery rate for a medical treatment, for example. We examine what is lost in this simplification, and propose using two interface constants to represent positive and negative implications separately. Given certain assumptions about non-causal outcomes, the set of resulting epistemologies is a continuum. We derive a variety of particular measures and contrast them with the one-dimensional index.