Don’t Use a Short Series of Data

From February 23, 2020

No photo description available.

New cases are back at a level yesterday that is more what I expected. It’s hard to say why there was the three days of considerably lower cased.

It’s also troubling that the case fatality rate has been slowly climbing.

This is a good example of why it’s never a good idea to rely on a very short series of data in a long stretch to identify trends.

Disclaimer: This commentary is my own interpretation and does not represent the analysis by the government or my employer. The data is from the Johns Hopkins University’s Center for Systems Science and Engineering.

Leave a Reply