Quantifying Harm
This work addresses the need for a quantitative harm metric in decision-making, particularly for interventions, but it is incremental as it builds on prior qualitative definitions and decision-theory literature.
The paper tackles the problem of quantifying harm for practical applications, such as choosing the least harmful intervention, by presenting a quantitative definition in deterministic contexts and addressing issues with uncertainty and aggregation to societal harm, showing that naive aggregation methods can lead to counterintuitive results.
In a companion paper (Beckers et al. 2022), we defined a qualitative notion of harm: either harm is caused, or it is not. For practical applications, we often need to quantify harm; for example, we may want to choose the lest harmful of a set of possible interventions. We first present a quantitative definition of harm in a deterministic context involving a single individual, then we consider the issues involved in dealing with uncertainty regarding the context and going from a notion of harm for a single individual to a notion of "societal harm", which involves aggregating the harm to individuals. We show that the "obvious" way of doing this (just taking the expected harm for an individual and then summing the expected harm over all individuals can lead to counterintuitive or inappropriate answers, and discuss alternatives, drawing on work from the decision-theory literature.