How the mechanism of missing data on longitudinal biomarkers influences the survival analysis

Feng-shou Ko

Communications in Statistics - Theory and Methods, 2020, vol. 49, issue 23, 5794-5809

Abstract: In this paper, we discuss how missing data affect to identify longitudinal biomarkers or surrogates for a time to event outcome with/without considering the assumption of heterogenous baseline hazards among individuals. The comparison will be applied to the missing data under two missing mechanism – missing at random (MAR) and non-ignorable missing (NMAR).We use simulations to explore how missing mechanism affect the power to detect the association of a longitudinal biomarker and the survival time given the number of individuals, the number of time points per individual and the functional form of the random effects from the longitudinal biomarkers considering heterogeneous baseline hazards in individuals. The longitudinal biomarker will be assumed under two missing mechanism – missing at random (MAR) and non-ignorable missing (NMAR). The result shows that the method considering heterogeneous baseline hazards among individuals can has a performance well in the missing data under missing at random (MAR). The method considering heterogeneous baseline hazards among individuals has the better performance than the method without considering heterogeneous baseline hazards among individuals. The method with/without considering heterogeneous baseline hazards among individuals do not work well under non-ignorable missing mechanism.

Date: 2020
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/03610926.2019.1622724 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:lstaxx:v:49:y:2020:i:23:p:5794-5809

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/lsta20

DOI: 10.1080/03610926.2019.1622724

Access Statistics for this article

Communications in Statistics - Theory and Methods is currently edited by Debbie Iscoe

More articles in Communications in Statistics - Theory and Methods from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().