Modeling dropouts by conditional distribution, a copula-based approach |
| |
Authors: | Ene Krik Meelis Krik |
| |
Institution: | aInstitute of Mathematical Statistics, University of Tartu, Tartu, Estonia |
| |
Abstract: | In this paper the concept of copulas is implemented into the methodology for solving the imputation problem in correlated incomplete data. We use the Gaussian copula as alternative to the joint distribution for modeling the conditional distribution, conditioned by the observed values of measurements. The general formula for imputation and its application for compound symmetry correlation structure are given. |
| |
Keywords: | Dropout Gaussian copula Imputation Monotone missingness |
本文献已被 ScienceDirect 等数据库收录! |