My goal is to find the worst affected industries from COVID—19 in terms unemployment.

In terms of the data I will use for this task, I have a time series county-wise unemployment rate data of each month and business distribution data. Business distribution data contains number of establishments in each county by their respective industries. (Manufacturing -121, Accommodation and Food Services -564, Construction-32 etc.) Unemployment rate data gives monthly unemployment rate in each county.

From this data, what would your recommendation be to find the worst and least affected industry? Any help is highly appreciated. Thanks in advance.

Unemplyment Rate DataIndustry Data

  • $\begingroup$ Any chance you could include examples of the data so we can see what the data looks like? $\endgroup$
    – shepan6
    Commented Aug 3, 2020 at 6:47
  • $\begingroup$ @shepan6 I have edited the post to include the same $\endgroup$
    – NAS_2339
    Commented Aug 3, 2020 at 11:06
  • $\begingroup$ Thanks for editing your post @Naseef. Am I right to assume the bottom data frame is a breakdown of businesses by industry for a given month and specific county? $\endgroup$
    – shepan6
    Commented Aug 3, 2020 at 12:53
  • $\begingroup$ @shepan6 it is breakdown of business by indutry for a specific county,but not a given month.This is an annual data,doesn't change with month. My question can be reframed as is it possible to find the impact on the industries from these data? $\endgroup$
    – NAS_2339
    Commented Aug 3, 2020 at 13:17

1 Answer 1


Thank you clarifying the question and the current data available. This is a really interesting project idea and I look forward to hearing more developments on this.

So, with what I have seen so far, without the monthly breakdown of number of businesses by month, then you you can't look at the affect of COVID-19 on an industry-level, unless you compare 2019 with 2020 data.

However, with the data so far you can look at how COVID-19 is affecting unemployment rates and see if they affect certain groups of counties which have a certain industry composition/distribution.

If, for example, particular counties with similar distributions of industries (e.g. 90% Manufacturing, 5% Retail and 5% Information) show greater unemployment from those with a different composition.

Let me know if I need to clarify further. But again, very interesting project, please do keep me in the know with how this goes.

  • $\begingroup$ Thanks, @shepan6 for the reply. What additional data you think is helpful for the industry impact analysis?. Do GDP and employment data with industry-wise breakdown will do? $\endgroup$
    – NAS_2339
    Commented Aug 6, 2020 at 9:42
  • $\begingroup$ Hi @Naseef, these are all great questions. The whole fun about this project is you can experiment with how to represent industry impact. So, in this case, try using the data you have, try also with GDP and employment data. These are all different ways of representing industry impact. Some might represent industry impact "better", but that is for you to argue and decide. Sorry for being ambiguous but what I am trying to say is go and explore the possibilities. $\endgroup$
    – shepan6
    Commented Aug 6, 2020 at 10:23

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.