Regression analysis of current-status data: an application to breast-feeding

Area of Science:

• Biostatistics
• Demography
• Public Health

Background:

• Calculating mean survival time from current-status data presents challenges in multiple regression.
• Breastfeeding duration is a critical health indicator influenced by various socioeconomic and demographic factors.

Purpose of the Study:

• To evaluate and compare different statistical techniques for estimating mean survival time using current-status data.
• To assess the applicability of parametric, nonparametric, and semiparametric models in the context of breastfeeding duration analysis.
• To test these models within proportional-odds and proportional-hazards frameworks.

Main Methods:

• The study employed current-status data on breastfeeding from the Demographic and Health Survey (DHS).
• Various statistical models were considered, including parametric, nonparametric, and semiparametric approaches.
• Models were fitted within both proportional-odds and proportional-hazards regression frameworks.

Main Results:

• The research compared the performance of different statistical models in analyzing current-status breastfeeding data.
• The study identified potential challenges and benefits associated with each modeling technique.
• Results were derived from data across six diverse countries in Africa, Asia, and Latin America.

Conclusions:

• The study provides insights into the most suitable statistical methods for analyzing mean survival time from current-status breastfeeding data.
• Findings contribute to a better understanding of breastfeeding dynamics and inform public health interventions.
• The research highlights the importance of selecting appropriate statistical models for accurate health data analysis.