| Contents Notes |
Preface1 Introduction1.1 The Kola Ecogeochemistry Project2 Preparing the Data for Use in R and DAS+R2.1 Required Data Format for Import in R and DAS+R2.2 The Detection Limit Problem2.3 Missing Values2.4 Some "Typical" Problems Encountered When Editing a Laboratory Data Report2.5 Appending and Linking Data Files2.6 Requirements for a Geochemical Database2.7 Summary3 Graphics to Display the Data Distribution3.1 The One-Dimensional Scatter Plot3.2 The Histogram3.3 The Density Trace3.4 Plots of the Distribution Function3.5 Boxplots3.6 Combination of Histogram, Density Trace, One-Dimensional Scattergram, Boxplot, and ECDF-plot3.7 Combination of Histogram, Boxplot or Box-and-Whisker plot, ECDF-plot, and CPplot3.8 Summary4 Statistical Distribution Measures4.1 Central Value4.2 Measures of Spread4.3 Quartiles, Quantiles and Percentiles4.4 Skewness4.5 Kurtosis4.6 Summary Table of Statistical Distribution Measures4.7 Summary5 Mapping Spatial Data5.1 Map Coordinate Systems (Map Projection)5.2 Map Scale5.3 Choice of the Base Map for Geochemical Mapping5.4 Mapping Geochemical Data With Proportional Dots5.5 Mapping Geochemical Data Using Classes5.6 Surface Maps Constructed with Smoothing Techniques5.7 Surface Maps Constructed with Kriging5.8 Colour Maps5.9 Some Common Mistakes in Geochemical Mapping5.10 Summary6 Further Graphics for Exploratory Data Analysis6.1 Scatterplots (xy-plots)6.2 Linear Regression Lines6.3 Time Trends6.4 Spatial Trends6.5 Spatial Distance Plot6.6 Spiderplots (Normalised Multi-Element Diagrams)6.7 Scatterplot Matrix6.8 Ternary Plots6.9 Summary7 Defining Background and Threshold, Identification of Data Outliers and Element Sources7.1 Statistical Methods to Identify Extreme Values and Data Outliers7.2 Detecting Outliers and Extreme Values in the ECDF- or CP-Plot7.3 Including the Spatial Distribution in the Definition of Background7.4 Methods to Distinguish Geogenic from Anthropogenic Element Sources7.5 Summary8 Comparing Data in Tables and Graphics8.1 Comparing Data in Tables8.2 Graphical Comparison of the Data Distributions of Several Data Sets8.3 Comparing the Spatial Data Structure8.4 Subset Creation -- a Mighty Tool in Graphical Data Analysis8.5 Data Subsets in Scatterplots8.6 Data Subsets in Time and Spatial Trend Diagrams8.7 Data Subsets in Ternary Diagrams8.8 Data Subsets in the Scatterplot Matrix8.9 Data Subsets in Maps8.10 Summary9 Comparing Data Using Statistical Tests9.1 Tests for Distribution (Kolmogorov-Smirnov and Shapiro-Wilk Tests)9.2 The One-Sample t-Test (Test for the Central Value)9.3 Wilcoxon Signed-rank Test9.4 Comparing Two Central Values of the Distributions of Independent Data Groups9.5 Comparing Two Central Values of Matched Pairs of Data9.6 Comparing the Variance of Two Data Sets9.7 Comparing Several Central Values9.8 Comparing the Variance of Several Data Groups9.9 Comparing Several Central Values of Dependent Groups9.10 Summary10 Improving Data Behaviour for Statistical Analysis: Ranking and Transformations10.1 Ranking/Sorting10.2 Non-linear Transformations10.3 Linear Transformations10.4 Preparing a Dataset for Multivariate Data Analysis10.5 The Special Case of Closed Number Systems10.6 Summary11 Correlation11.1 Pearson Correlation11.2 Spearman Rank Correlation11.3 Kendall-tau Correlation11.4 Robust Correlation Coefficients11.5 When is a Correlation Coefficient Significant?11.6 Working With Many Variables11.7 Correlation Analysis and Inhomogeneous Data11.8 Correlation Results Following Additive Logratio or Centred Logratio Transformations11.9 Summary12 Multivariate Graphics12.1 Profiles 12.2 Stars12.3 Segments12.4 Boxes12.5 Castles and Trees12.6 Parallel Coordinates Plot12.7 Summary13 Multivariate Outlier Detection13.1 Univariate Versus Multivariate Outlier Detection13.2 Robust Versus Non-robust Outlier Detection13.3 The Chi2-plot13.4 Automated Multivariate Outlier Detection and Visualisation13.5 Other Graphical Approaches for Identifying Outliers and Groups13.6 Summary14 Principal Component Analysis (PCA) and Factor Analysis (FA)14.1 Conditioning the Data for PCA and FA14.2 Principal Component Analysis (PCA)14.3 Factor Analysis14.4 Summary15 Cluster Analysis15.1 Possible Data Problems in the Context of Cluster Analysis15.2 Distance Measures15.3 Clustering Samples15.4 Clustering Variables15.5 Evaluation of Cluster Validity15.6 Selection of Variables for Cluster Analysis15.7 Summary16 Regression Analysis (RA)16.1 Data Requirements for Regression Analysis16.2 Multiple Regression16.3 Classical Least Squares (LS) Regression16.4 Robust Regression16.5 Model Selection in Regression Analysis16.6 Other Regression Methods16.7 Summary17 Discriminant Analysis (DA) and other Knowledge Based Classification Methods17.1 Methods for Discriminant Analysis17.2 Data Requirements for Discriminant Analysis17.3 Visualisation of the Discriminant Function17.4 Prediction with DA17.5 Exploring for similar data structures17.6 Other Knowledge Based Classification Methods17.7 Summary18 Quality Control (QC) 29518.1 Randomised samples18.2 Trueness18.3 Accuracy18.4 Precision18.5 Analysis of Variance (ANOVA)18.6 Using Maps to Assess Data Quality18.7 Variables Analysed by Two Different Analytical Techniques18.8 Working with Censored Data -- a Practical Example18.9 Summary19 Introduction to R and Structure of the DAS+R Graphical User Interface19.1 R19.2 R-scripts19.3 A Brief Overview of Relevant R Commands19.4 DAS+R. |
