Missing Data and Heat Island Effects

• Activity Number: 404
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): Jessica Seeger*+ and Candace Berrett
• Companies: and Brigham Young University
• Keywords: temperature data ; climate change ; spatiotemporal models

Abstract

Environmental data is notorious for containing large amounts of missing data. To get reliable representations of long-term temperature trends, it is important to accurately estimate these missing values. For instance, a heat island effect occurs when a previously un-urbanized area increases in temperature as it becomes urbanized over time. Identifying and analyzing these heat island effects can have profound implications for climate change, but missing data must be accounted for in these analyses. We propose a model that accounts for annual, long-term trends, and spatiotemporal trends to impute the data and examine resulting implications.