Sensitivity and Stratification Analysis on the Accuracy of the Cause of Deaths Diagnosis in Shanghai


  • Yue Zhao


Vital Statistics, Cause of Death, Shanghai, Confounding


This study was to examine the accuracy of the Cause of Deaths (CoD) for the hospital doctors in Shanghai, China. Medical Record (MR) doctors were trained first and then the MR doctor diagnosis was treated as the gold standard. Then we used this gold standard to compare the performance of the hospital doctors. The initial result showed that the tertiary hospital doctors have a lower rate of concordance. After further stratification, the result showed that the concordance rate was confounded by the complication of the diseases.


Chiao, Chi-Ming, Thompson, Warren S and Chen, DT. (1938). Experiment in the registration of vital statistics in China. Scripps Foundation for Research in Population Problems, Oxford.

Wagner, Clifford H. (1982). Simpson's paradox in real life. The American Statistician 36(1), 46-48.

Wang, Chen, Rao, Keqin, Wu, Sinan and Liu, Qian. (2013). Health care in china: improvement, challenges, and reform. Chest 143(2), 524-531.

Yang, Gonghuan, Hu, Jianping, Rao, Ke Quin, Ma, Jeimin, Rao, Chalapati and Lopez, Alan D. (2005). Mortality registration and surveillance in china: history, current situation and challenges. Population health metrics 3(1), 3.

Zar, Fred A, Bakkanagari, Srinivasa R, Moorthi, KMLST and Davis, Melinda B. (2007). A comparison of vancomycin and metronidazole for the treatment of clostridium dificile-associated diarrhea, stratified by disease severity. Clinical Infectious Diseases 45(3),302-307.



How to Cite

Zhao, Y. (2020). Sensitivity and Stratification Analysis on the Accuracy of the Cause of Deaths Diagnosis in Shanghai. Journal of Statistics and Machine Learning, 1(1), 1-11. Retrieved from