Subscribe to DSC Newsletter

Assessing ability to "sight-read" data; EDA

If you've ever learned to play an instrument, at some point an instructor will give you a sheet of music that you've never seen before and ask you to play it.  It is a very objective way to assess one's skill level and the act of playing unseen music is called sight reading.

Wikipedia on Sight Reading

I've often wanted to use this technique to quantify a candidate's ability to analyze data.  We often hire people and won't know their real skill level until weeks or months into the position.  I'm toying with asking candidates to analyze a dataset.  My feeling is that people who have very good skills at exploratory data analysis make the best analysts/statsticians/data scientists.  

Has anyone done this successfully in an interview setting?

Would you be turned off to doing it as a candidate?



Views: 216

Tags: Analysis, Data, EDA, Exploratory


You need to be a member of AnalyticBridge to add comments!

Join AnalyticBridge

Comment by Tim Negris on December 25, 2012 at 5:59am
Interesting parallel between data science and music. Perhaps your purpose could be served expediently in an interview situation with a few pages of SQL or JASON metadata and other information about a new dataset. Most good analysts/scientists I know, when entering a new project, start by asking about the subject dataset, like where did the data come from, how was it collected, what are the element definitions, how much data is there, how are missing values accounted for, etc., and then asking questions about individual fields, about ranges, limits, distributions, etc.

On Data Science Central

© 2020   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service