A New Distribution to Describe Big Data

• Activity Number: 445
• Type: Contributed
• Date/Time: Tuesday, August 2, 2016 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistical Learning and Data Science
• Author(s): Yuanyuan Zhang*
• Companies: University of Manchester
• Keywords: Power law distribution ; Social media ; Big Data

Abstract

The Power law distribution is the most common statistical distribution attributed to a variety of human generated big data sources, such as social media. Here, we reanalyse social media data sets such as Twitter, Livejournal and Google+ and show that other new distributions provide better or as good fit as the Power law distribution.