On Identifying Total Effects in the Presence of Latent Variables and Selection bias

Assume that cause-effect relationships between variables can be described as a directed acyclic graph and the corresponding linear structural equation model We consider the identification problem of total effects in the presence of latent variables and selection bias between a treatment variable and a response variable. Pearl and his colleagues provided the back door criterion, the front door criterion (Pearl, 2000) and the conditional instrumental variable method (Brito and Pearl, 2002) as identifiability criteria for total effects in the presence of latent variables, but not in the presence of selection bias. In order to solve this problem, we propose new graphical identifiability criteria for total effects based on the identifiable factor models. The results of this paper are useful to identify total effects in observational studies and provide a new viewpoint to the identification conditions of factor models.

• Type: Conference
• Year: 2008
• Where: UAI
• Authors: Manabu Kuroki, Zhihong Cai
• Keywords: Artificial Intelligence, Door Criterion, Latent Variables, Total Effects, UAI 2008