Can we always trust in the analysis of complex datasets?

Results of statistical operations are far from being intuitive. One needs a lot of experience to reliably judge computed results, and most people would listen to the advice given by experts in the field. This makes a story presented by the BBC all the more remarkable; it is about a student who took over the task to check the calculations of two Harvard professors. He was not only unable to replicate the results that Carmen Reinhart and Ken Rogoff published; it was much more: he spotted a basic error in the spreadsheet and was thus able to correct their research paper called “Growth in a Time of Debt”. That may sound like a modern myth; but sometimes politicians base their decisions on papers like these.

http://www.bbc.com/news/magazine-22223190

 

Jörg Lehmann, FUB

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s