Zero-inflated cure rate model
an aplication to HIV/AIDS patients data in Mato Grosso do Sul
Keywords:
survival analysis, censored data, zero-inflated models, long-term survival modelsAbstract
In this study, it was aimed to adjust some probability distributions to describe survival time in HIV/AIDS patients in Mato Grosso do Sul, Brazil, followed between 2009 and 2018. In the distributions discussed, it was necessary to implement parameters to model the null times (zero inflation) and the long duration times (cure rate). Based on Akaikes Criterion, the Kumaraswamy Generalized Gamma distribution was the best fit to the data, and was then used in a regression model that contained the explanatory variables: sex, race, and education. Based on this adjustment, female gender, white race, and education of more than eight years were associated with longer survival time. Based on these interpretations, one can discuss the need for HIV prevention and early diagnosis policies focused on specific groups associated with lower survival.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Electronic Journal of Exact and Technological Sciences
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
RECET publications are licensed under Creative Commons (CC BY-NC-ND 4.0).
With this license, it is allowed to access, download (download), copy, print, share, reuse and distribute the articles as long as for non-commercial purposes and with the citation of the source, giving due credits of authorship and mention to the RECET Magazine.
By submitting articles to the RECET Magazine, the authors agree to make their texts legally available under this license. Commercial uses of material published in the magazine will only be allowed after written authorization from the magazine.
