Read about my motivation for this series here.
The number of Ebola cases is growing. Roughly exponentially, in fact. Cases in Liberia continue to grow exponentially (2,712 as of Sept 17). Sierra Leone is a bit slower, but not slow enough (1,603 cases). Guinea looked like it was getting under control until the last several weeks, when case counts have begun to climb again (861 cases).
The World Health Organization produces updates about twice a week, but the data are usually several days behind by the time the reports hit the Internet. The Sierra Leone and Liberia Ministries of Health both publish daily reports to their websites. Agreement between the sources is good.
However, the data are not entirely reliable. For example, the Liberia Ministry of Health publishes both incident (new) cases in healthcare workers, as well as the cumulative number of healthcare workers who have been infected. These two numbers do not agree. You'll also notice a random spike in mid-July. I assume someone at the MoH made a typo. Errors like that show up often enough that I have to proceed carefully.
One of the most basic and useful things epidemiologists want to know is where most of the infectious are happening. The country level doesn't give us enough information - we have to look at the county level to know for sure. In Liberia, Montserrado County (home of Monrovia) has overtaken Lofa County as the most affected.
Even more worrisome, the number of new cases each week is growing dramatically in Montserrado. Lofa on the other hand seems to either have achieved some level of control, or is suffering reporting issues.
Here are some nerdy details on that last plot: normally it's easiest to just do daily incidence. But when the outbreak last six months, that makes for a really ugly plot. Doing weekly incidence makes more sense, but it's tough if you have a sparse time series. To find weekly incidence, I reindex the time series to include every date (not just the dates where I've collected data). Then instead of plotting new cases, I interpolate the cumulative cases, and take the difference of every seventh day.
"Send me your data - PDF is fine," said no one ever
The public health paradox ("When public health works, it's invisible")
Let's make data a civic right
Scholarly impact of open access journals
Six months later, disease detectives still battling fungal meningitis outbreak