Binary-outcome MNAR estimation is made identifiable through an exponential tilt model with a sufficient identifiability condition, estimated by KL matching without instruments or shadow variables.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Estimation with missing not at random binary outcomes via exponential tilts
Binary-outcome MNAR estimation is made identifiable through an exponential tilt model with a sufficient identifiability condition, estimated by KL matching without instruments or shadow variables.