Skip to content

IPTW handle PerfectSeparationErrors in the marginal structural model better #147

@pzivich

Description

@pzivich

When the MSM are fit in the IPTW.fit() statement, it is possible for a PerfectSeparationError to occur. This is more of a concern for the linear-binomial models (as opposed to the other). To deal with this issue, I should update to try-except that fills the RD (or RR) with nan's and throw a warning.

Current behavior would be an error and no other models being fit

Metadata

Metadata

Assignees

No one assigned

    Labels

    Causal inferenceUpdates for the causal inference branchbug

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions