An official website of the United States government
NCBI Bookshelf. A service of the National Library of Medicine, National Institutes of Health.
Edwards SL, Berzofsky ME, Biemer PP. Addressing Nonresponse for Categorical Data Items Using Full Information Maximum Likelihood with Latent GOLD 5.0 [Internet]. Research Triangle Park (NC): RTI Press; 2018 Sep. doi: 10.3768/rtipress.2018.mr.0038.1809
| Model Type | Dependent Variable | Independent Variables |
| 1—Fuchs-Mean | FIML MAR via Saturated MAR (Fuchs) | Mean Imputation |
| 2—Fay-Mean (MAR) | FIML MAR via Response Indicator (Fay) | Mean Imputation |
| 3—Fuchs-Fuchs | FIML MAR via Saturated MAR (Fuchs) | FIML MAR via Saturated MAR (Fuchs) |
| 4—Fay-Fuchs (MAR) | FIML MAR via Response Indicator (Fay) | FIML MAR via Saturated MAR (Fuchs) |
| 5—Fay-Fay (MAR) | FIML MAR via Response Indicator (Fay) | FIML MAR via Response Indicator (Fay) |
FIML = full information maximum likelihood; MAR = missing at random.
This work is distributed under the terms of a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 license (CC BY-NC-ND), a copy of which is available at https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode
Your browsing activity is empty.
Activity recording is turned off.
See more...
