B1368
Title: Joint modeling in presence of informative censoring in palliative care studies
Authors: Zhigang Li - Department of Biostatistics, University of Florida (United States) [presenting]
Abstract: Joint modeling of longitudinal data such as quality of life data and survival data is important for palliative care researchers to draw efficient inference because joint modeling can account for the associations between those two types of data that are commonly seen in palliative care studies. However, censoring of death times, especially informative censoring such as informative dropouts, poses challenges for modeling quality of life on a retrospective time scale. We develop a novel joint modeling approach that can address the challenge by allowing informative censoring events to be dependent on patients' quality of life through a random effect. In addition to improving the precision of estimates, our approach can provide unbiased estimates for making valid inference by appropriately modeling the informative censoring time. Model performance is assessed with a simulation study in comparison with existing approaches. A real-world study is presented to showcase the application of the new approach.