In:
Statistical Methods in Medical Research, SAGE Publications, Vol. 29, No. 7 ( 2020-07), p. 1787-1798
Kurzfassung:
Biomedical studies often involve an event that occurs to individuals at different times and has a significant influence on individual trajectories of response variables over time. We propose a statistical model to capture the mean trajectory alteration caused by not only the occurrence of the event but also the subject-specific time of the event. The proposed model provides a post-event mean trajectory smoothly connected with the pre-event mean trajectory by allowing the model parameters associated with the post-event mean trajectory to vary over time of the event. A goodness-of-fit test is considered to investigate how well the proposed model is fit to the data. Hypothesis tests are also developed to assess the influence of the subject-specific time of event on the mean trajectory. Theoretical and simulation studies confirm that the proposed tests choose the correctly specified model consistently and examine the effect of the subject-specific time of event successfully. The proposed model and tests are also illustrated by the analysis of two real-life data from a biomarker study for HIV patients along with their own time of treatment initiation and a body fatness study in girls with different age of menarche.
Materialart:
Online-Ressource
ISSN:
0962-2802
,
1477-0334
DOI:
10.1177/0962280219876957
Sprache:
Englisch
Verlag:
SAGE Publications
Publikationsdatum:
2020
ZDB Id:
2001539-2
ZDB Id:
1136948-6