I have a very simple video today with not a lot of DAX needed; I just want to demonstrate how you can gain insights from data.
On 10th Sept 2021, NSW health made a material change to the Active Cases reported for COVID-19 in Australia (as you can see in the image below). I thought this was strange that it could flip a switch an make such a material change (without an explanation, what’s more), so I set about looking more deeply into the data to see what was happening.
I want to stress that I have no knowledge about the length of time a COVID-19 case is active. The active case numbers are provided by NSW Health (and the other state jurisdictions) each day along with the new cases. So while I can’t say what is right and wrong, what I can do is overlay the Total Cases data against the Active Cases data and look at what has changed.
My simple analysis today shows that there have been significant differences with the patterns in the data last year (Wave 2 – predominantly Melbourne), Wave 3 prior to the change, and Wave 3 after the change. I think this is a good example of how you can use data to gain insights.
Very good. The lines fit very well so it does seem that they have used a 16 day rule, then a 27 day then 12 day.
odd they haven’t explained this.
Odd indeed, but consistent with them only providing data they want you to have, for reasons unknown.
An interesting analysis Matt, The outbreak in Vic in 2020 would have primarily been of the A variant, whereas the NSW outbreak is D. We know that with D symptoms appear a lot more quickly, meaning people are likely to get a test and be diagnosed earlier on in their disease but I’m unsure if there a difference in the length of time people people actually have covid between the variants. If no difference I would expect a longer t values for the third wave to be longer not shorter.
In NZ Recovered cases are defined as “people who had the virus, where at least 10 days have passed since their symptoms started and they have not had symptoms for 72 hours, and they have been cleared by the health professional responsible for their monitoring”. i.e. it would be min 13 days but the duration is tied to symptoms not diagnosis so would vary between individuals
Thanks for sharing your insights
Great video Matt, so simple yet so powerful!