In settings with interference, researchers commonly define estimands using exposure mappings to summarize neighborhood variation in treatment assignments. This paper studies the causal interpretation of these estimands under weak restrictions on interference. We demonstrate that the estimands can exhibit unpalatable sign reversals under conventional identification conditions. This motivates the formulation of sign preservation criteria for causal interpretability. To satisfy preferred criteria, it is necessary to impose restrictions on interference, either in potential outcomes or selection into treatment. We provide sufficient conditions and show that they can be satisfied by nonparametric models with interference in both the outcome and selection stages.

翻译：在存在干扰效应的情境下，研究者通常使用暴露映射来概括处理分配中的邻域变异，并据此定义目标量。本文研究了在弱干扰限制条件下这些目标量的因果解释。我们证明，在传统识别条件下，这些目标量可能出现令人不快的符号反转现象。这促使我们提出了用于因果解释性的符号保持标准。为满足优先标准，必须对干扰施加限制——无论是潜在结果层面还是选择进入处理层面。我们给出了充分条件，并证明这些条件可以通过在结果阶段和选择阶段均包含干扰的非参数模型得到满足。