Estimation of hazard of death in vertically transmitted HIV-1-infected children for doubly censored failure times and fixed covariates

T. Banerjee, G. Grover, T. Pensi and D. Banerjee

Journal of Applied Statistics, 2011, vol. 38, issue 2, 273-285

Abstract: This work estimates the effect of covariates on survival data when times of both originating and failure events are interval-censored. Proportional hazards model [16] along with log-linear models was applied on a data of 130 vertically infected HIV-1 children visiting the paediatrics clinic. The covariates considered for the analysis were antiretroviral (ARV) therapy, age at diagnosis, and change in CD4+T cell count. Change in CD4+T cell count was the difference in the last and first count in non-ARV therapy group, while in the ARV therapy group the same was considered after the start of the treatment. Our findings suggest that children on ARV therapy had significantly lower risk of death ( p >0.001). We further investigated the effect of age and change in CD4+T cell count on risk of death. These covariates exhibited a possible association with risk of death by both the procedures ( p >0.0001). The effect of number of years under ARV therapy with diagnosis year as a confounding factor was directly related to longevity. The results obtained by the two procedures gave reasonable estimates. We conclude that when the lengths of intervals are narrow, we can opt for parametric modeling which is less computationally intensive.

Date: 2011
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/02664760903406454 (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:japsta:v:38:y:2011:i:2:p:273-285

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/CJAS20

DOI: 10.1080/02664760903406454

Access Statistics for this article

Journal of Applied Statistics is currently edited by Robert Aykroyd

More articles in Journal of Applied Statistics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().