OUTLIER DETECTION IN TOTAL PHOSPHORUS CONCENTRATION DATA FROM SOUTH FLORIDA RAINFALL1
Author:
- 1 April 1999
- journal article
- Published by Wiley in Jawra Journal of the American Water Resources Association
- Vol. 35 (2) , 301-310
Abstract
Atmospheric deposition can be a significant source of phosphorus to South Florida's aquatic system. Deposition samples are often contaminated to varying degrees by bird droppings or other foreign materials. This study attempted to use statistical and other methods to detect and remove the outliers in the rain‐borne total phosphorus concentration data. Some outliers in the data were identified using field notes derived from visual inspection of the samples. Outlier detection statistics based on a simple linear regression were then used for additional data screening. As a result of these analyses, about 35 percent of the observed values were identified as outlying data which needed to be removed prior to further data analyses. Based on detected outliers in the data from 15 monitoring sites, a lumped cutoff value of 130 4mUg/L was determined. This lumped cutoff value may be useful for further quality control and analyses of the data from the region.Keywords
This publication has 22 references indexed in Scilit:
- Fast Very Robust Methods for the Detection of Multiple OutliersJournal of the American Statistical Association, 1994
- Outlier detection in the state space modelStatistics & Probability Letters, 1994
- Everglades1994
- Procedures for the Identification of Multiple Outliers in Linear ModelsJournal of the American Statistical Association, 1993
- A national critical loads framework for atmospheric deposition effects assessment: III. Deposition characterizationEnvironmental Management, 1993
- The stalactite plot for the detection of multivariate outliersStatistics and Computing, 1993
- Algorithm AS 282: High Breakdown Regression and Multivariate EstimationJournal of the Royal Statistical Society Series C: Applied Statistics, 1993
- Some properties of, and relationships among, several uncorrelated and homoscedastic residual vectorsCommunications in Statistics - Theory and Methods, 1990
- Influence and prevention of bird-droppings in precipitation chemistry experimentsWater, Air, & Soil Pollution, 1982
- Procedures for Detecting Outlying Observations in SamplesTechnometrics, 1969