1 code implementation • 14 Mar 2021 • Zhenhua Wang, Olanrewaju Akande, Jason Poulos, Fan Li
We conduct extensive simulation studies based on a subsample of the American Community Survey to compare the repeated sampling properties of four machine learning based MI methods: MICE with classification trees, MICE with random forests, generative adversarial imputation networks, and multiple imputation using denoising autoencoders.
1 code implementation • 20 Oct 2020 • Chayut Wongkamthong, Olanrewaju Akande
In certain settings, MI using multinomial logistic regression models is able to achieve comparable performance, depending on the missing data mechanism and amount of missing data.
Methodology Applications