Date of Completion

2014

Document Type

Honors College Thesis

Department

Mathematics and Statistics

First Advisor

Jeff Buzas

Second Advisor

Ruth Mickey

Third Advisor

Jeff Dinitz

Keywords

Functional Data Analysis, Weather, Statistics, Splines

Abstract

This thesis explores the use of functional data analytic methods to examine climate change in a select group of 16 cities in the United States. The purpose of the project was to explore methods of functional data analysis in the context of climate change.Data used in this study was collected from NOAA's National Climatic Data Center. Major cities from around the United States were selected provided they had 100 percent coverage for the span of years of interest, 1950 through 2013. Sixteen cities were found to have complete data for every day of the 64-year period.Spline functions were fit to the temperature time series after removing seasonal variation. Mean temperature curves and associated confidence limits were computed.The results show a significant rise of temperature in U.S. cities within the last few decades and that the rate of increase has consistently stayed above zero since the 1970s.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.

Download

Share

COinS