Multivariate and geostatistical analyses of Phase I Eastern Lake Survey data.
AuthorRhodes, Hannah Rasmussen.
Committee ChairMyers, Donald E.
MetadataShow full item record
PublisherThe University of Arizona.
RightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
AbstractMany difficulties are encountered when analyzing large spatial data sets. The following research focuses on how various univariate, multivariate, geostatistical, and geographic information systems techniques can aid in the examination of spatial data sets containing large numbers of samples, as well as variables. The analyses are applied to data from Phase I of the Eastern Lake Survey which deals with the effects of acidic deposition on aquatic ecosystems. Relationships among chemical analytes are explored, and outlying or atypical lake samples and chemical analytes are identified using statistical techniques including univariate statistics, correlation analysis, normality testing, multivariate outlier testing, correspondence analysis, and ordinary kriging. The primary objective of the correspondence analysis was to obtain a reduction in the number of chemical analytes in order to make subsequent data analyses and interpretations easier. The main reason for performing a geostatistical analysis of the ELS-I data was to obtain maps of interpolated values for unsampled lake locations. Geographic information systems technology was used to examine the influence of lake size on the kriging analysis. This research should provide useful for future efforts to detect and ameliorate the effects of acidic deposition on aquatic ecosystems.
Degree ProgramApplied Mathematics