Day 3: Survey of Income and Program Participation

by Agnieszka Atlasik

Today’s challenge was aimed at survey data and my topic was highlighting Education attainment in the USA.

My initial concept was to try highlight any impacts of the economic crisis on the education system in the US. Unfortunately the survey data is not recent enough to confidently highlight significant trends.

The data that was available and in similar formats was:

  1. a PDF of 1984
  2. an excel file of 2002
  3. an excel file of 2018
A PDF of 1984

So at this point a decision was made to ‘use the best tool for the job’ and correct a few fields in excel. The amount of data was not large and would’ve been faster to amend before adding to Alteryx. To add an extra challenge, the PDF was not convertible using Tableau or Alteryx. Again an online ‘best tool for the job’ was used.

Only after touching up the various files, Alteryx was used for transforming the data to a usable format, mainly aligning the various fields and string fields that had mismatched headers and records.

Alteryx workflow

And finally, after a lot of time spent on the QA of the values from the different sources the output shows some strange trends.

How do more adults in the US get a Bachelor’s degree after less of them have completed High school?

The result of day 3: