Inferential statistics from Black Hispanic breast cancer survival data

Area of Science:

• Biostatistics
• Epidemiology
• Oncology

Background:

• Breast cancer survival rates vary significantly across racial and ethnic groups.
• Accurate statistical models are crucial for understanding and predicting survival outcomes.
• The Surveillance, Epidemiology, and End Results (SEER) database provides valuable data for cancer research.

Purpose of the Study:

• To evaluate statistical probability models for breast cancer survival data.
• To specifically analyze survival data for Black Hispanic female patients.
• To identify the best-fitting statistical model for predicting breast cancer survival in this population.

Main Methods:

• Utilized a stratified random sample of Black Hispanic female patients from the SEER database (1973-2009).
• Employed Akaike Information Criteria (AIC), Bayesian Information Criteria (BIC), and Deviance Information Criteria (DIC) for model selection.
• Applied a novel Bayesian method and Markov Chain Monte Carlo (MCMC) for parameter estimation and predictive inference.

Main Results:

• The exponentiated exponential probability model demonstrated the best fit for Black Hispanic female breast cancer survival data.
• Derived posterior density functions for model parameters.
• Reported predictive intervals for future survival times.

Conclusions:

• The exponentiated exponential model offers a robust framework for analyzing breast cancer survival in Black Hispanic females.
• Findings have significant implications for improving treatment planning and healthcare resource allocation.
• This research highlights the importance of race and ethnicity in cancer survival modeling.