Description: This book introduces each leading statistical analysis technique, downplaying mathematical notation in favor of sample environmental applications and explanations that make sense to non-statisticians. It also addresses common problems in data interpretation: small data sets; the need to correlate constituents to infill missing data or identify outliers; creating early warning systems with fewer "false positives", handling noise; and assessing risk. Coverage includes how to characterize environmental quality data with Normal, Gaussian, Lognormal and other distributions; and how to characterize coincident behavior using regression and correlation. Learn how to make multiple comparisons using ANOVA and associated parametric analysis techniques, and test differences between monitoring records when censored data records exist. Finally, the authors bring their decades of experience to bear on the enormous challenge of using statistical analysis inputs to create realistic risk assessments. This is Volume 3 in the Prentice Hall PTR Environmental Management and Engineering Series.

Please Wait