Skip to main content

Advertisement

Figure 6 | Population Health Metrics

Figure 6

From: Direct estimation of cause-specific mortality fractions from verbal autopsies: multisite validation study using clinical diagnostic gold standards

Figure 6

Median CSMF accuracy versus number of causes on a cause list for the KL method. The test datasets for this experiment were generated by randomly selecting a set of causes and constructing test datasets using an uninformative Dirichlet distribution. The KL method has excellent performance for short cause lists, but rapidly degrades as the length of the list increases.

Back to article page