The Voice of Epidemiology

    
    


    Web EpiMonitor

► Home ► About ► News ► Job Bank Events ► Resources ► Contact
Articles Briefs People Blog Books Forum Quote of the Week Reprint of the Month
   

Facebook Makes Fun Of Princeton Research By Using Correlation As Causation

“Not All Research Is Created Equal”
 

If you watched the news at all this month, you heard about the attention-grabbing research conducted by two Princeton engineers predicted the demise of Facebook, and the amusing tongue in cheek research carried out in response by Facebook. What happened?

Research Model

The Princeton researchers assumed that online social networks behave like infectious diseases, that is, adoption of social media is like getting an infection, and abandoning social media is like recovery from illness. They modified an infectious disease model to predict what would happen with susceptibles, infected persons, and those who recovered.

They used Google search query data as a surrogate for usership of online social networks and then looked at the performance of the model for MySpace, a social network site whose members came and went in the recent past. They were satisfied with the model and applied it to Google query data about Facebook. Based on the results from the model, they predicted that Facebook “will undergo a rapid decline in the coming years, losing 80% of its peak user base between 2015 and 2017.”

Facebook Reaction

Facebook data scientists responded not in bureaucratic fashion but by spoofing the “robust” methodology of the Princeton engineers, namely by following the principle that correlation equals causation. Facebook research based on Facebook Likes showed that Princeton is itself at risk of disappearing, and based on Google search data showed Princeton papers in journals dropping dramatically. Also, Google search scores reveal that Princeton trends have been declining for years.

Acknowledging their paper was not peer-reviewed, the authors acknowledged that they were mostly trying to provide a fun reminder that not all research is created equal, and some methods of analysis lead to pretty crazy conclusions.

To read the reports, visit:

Princeton report

http://tinyurl.com/mwknh5l

Facebook report

http://tinyurl.com/kbcr2t7
 


Reader Comments:
Have a thought or comment on this story ?  Fill out the information below and we'll post it on this page once it's been reviewed by our editors.
 

       
  Name:        Phone:   
  Email:         
  Comment: 
                 
 
       

           


 

 
 
 
      ©  2011 The Epidemiology Monitor

Privacy  Terms of Use  Sitemap

Digital Smart Tools, LLC