Introduction

• course aims -
• learn various tools for analysing and communicating environmental data
  
• good preparation for senior thesis
• importance of data analysis in career and everyday life (e.g., for scientists,
  
• environmental problems often difficult to address scientifically because:
• they are complex and interdisciplinary
• many factors come into play (e.g. air quality issues)
  
• often can't manipulate system, lack of controls
• we need to learn how to
• obtain data
• perform your own measurements
  
• Hudson River fieldtrip
• Ion chromatograph
  
• get data from another source
• NYC air quality
• NY states monitoring program
  
• manage & curate data
• handwritten sheet
• tables
• convert data (unit conversions, derivations)
  
• visualize data, e.g.:
  
• bar diagrams
  
• boxplots
  
• e.g. scatter plots
• property/property
• timeseries
• map1 (Tucson), map2 (Bangladesh)
  
• animations
  
• analyse data (within conceptual/mathematical models)
• <>observations of ant nests occurences, table, boxplot, t-test<>
• perform statistical analysis
• measurement uncertainty/errors
  
• regression analysis
• calibration curve
• statistical tests
• interpolations
• other quantitative analyses
  
• communicate data and interpretation to others
• discuss findings with others in an informal environment
• scientific paper (Motor vehicle emissions), labreport (Ozone at Westpoint)
• scientific talk (PPT)
• poster
  

Technical aspects and course overview

• website tour
• overview of modules
• software
• expectations from students (readings, homework, labreports)
  
• login: eda - password:....
  
• textbook
  
• working with the CD Rom on/off line, Statplus 2.5 add-ins in Excel, Mac/PC issues
  
• USB drive (>=1GB) for backing up data
  
• sign-up sheet and questions for students, background, what would you like to get out of this class, access to computers

Prototype sequence for Environmental Data analysis

1 Conceptualization of problem:

• Problem identification; background information; scientific/ engineering context
• What data is important and why? How does information relate to each other and to problem at hand?

2 Data collection

• appropriate methods
• methodological limitations

• data organization and reduction
• data visualization and statistical analysis
• Results of data analysis

4 Discussion of results and conclusions

• expected vs. anomalous results
• reconceptualization
• prediction
• remaining conceptual/data gaps