Why neural-network imputation? | The architecture: deepimp_arch() | Imputing mixed-type data with impNNet() | Compositional data and rounded zeros with impNNetCoDa() | Choosing a backend | Reproducibility | A note on multiple completions | Reference

Why neural-network imputation? | The architecture: deepimp_arch() | Imputing mixed-type data with impNNet() | Compositional data and rounded zeros with impNNetCoDa() | Choosing a backend | Reproducibility | A note on multiple completions | Reference

Introduction | Proposed Imputation Algorithms | Using the R-package robCompositions for Imputing Missing Values | Information Loss, Uncertainty, and Diagnostics | Conclusions

Few Words about R and CoDa | Motivation to Robust Statistics | Available Functionality | Conclusion and Outline

Introduction | The Data Quality Challenge | What You'll Learn | Prerequisites | Setup | Part 1: Outlier Detection | Why Detect Outliers? | Statistical Methods for Outlier Detection | Method 1: 30-Day Rule (Simple Threshold) | Understanding the Output | Method 2: MAD (Median Absolute Deviation) - Recommended | Method 3: IQR (Interquartile Range) - Also Robust | Method 4: Z-Score - Sensitive but Less Robust | Method 5: GAM Residual - Model-based, Covariate-aware | Method 6: Mahalanobis - Multivariate, Robust (MCD) | Choosing a Method | Summary Statistics | Comparing Outlier Rates Across Species | Visualizing Outliers | 1. Overview Plot | 2. Seasonal Distribution | 3. Detailed Context | 4. Geographic Distribution | 5. Model Diagnostic (for gam_residual / mahalanobis) | 6. Phase-profile Plot (primary Mahalanobis figure) | Part 2: Data Completeness | Why Check Completeness? | Visualizing Completeness Issues | Assessing Completeness | Understanding Completeness Metrics | Filtering by Completeness | Completeness Thresholds for Different Analyses | Visualizing Completeness | Part 3: Phase Presence Validation | Why Check Phase Presence? | Checking Phase Presence | Checking Multiple Species | Common Phases to Check | Part 4: Integrated Quality Workflow | Putting It All Together | Documentation Template | Best Practices Summary | For Outlier Detection | For Abnormal Event Detection | For Completeness Assessment | For Phase Presence Checking | Summary | Key Take-Home Messages | Next Steps | Session Info

What is Phenology? | The PEP725 Database | Why Use the pep725 R Package? | Installation | Loading the Package | Getting Phenological Data | Why Synthetic Data? | Option 1: Download Synthetic Data (Recommended for Learning) | Option 2: Use the Small Seed Dataset | Option 3: Generate Your Own Synthetic Data | Option 4: Import Real PEP725 Data (For Research) | Option 5: Use Your Own Plant Phenological Data | Understanding the Data Structure | What You See in the Output | Key Columns Explained | Understanding Day of Year (DOY) | The pep Class | The Summary Method | Subsetting the Data | Understanding BBCH Codes | How BBCH Codes Work | Looking Up BBCH Codes | Commonly Used BBCH Codes in Phenological Research | Filtering by Phenological Phase | Exploring Data Coverage | Full Coverage Report | Focused Coverage Analysis | Coverage by Groups | Your First Analysis: Tracking Flowering Trends | Comparing with Another Species: Grapevine | Common Pitfalls and Tips | Data Quality Matters | Species Considerations | Next Steps | Phenological Analysis Vignette | Spatial Phenological Patterns Vignette | Data Quality Assessment Vignette | Getting Help | Session Info | References

Introduction | What You'll Learn | Prerequisites | Setup | Part 1: Phenological Normals | What are Phenological Normals? | Standard Reference Periods | Calculating Normals with pheno_normals() | Understanding the Output Statistics | Visualizing Normals | Filtering to Specific Phases | Comparing Two Time Periods | Comparing Species: Grapevine with Longer History | Part 2: Phenological Anomalies | What are Anomalies? | How Anomalies are Calculated | Calculating Anomalies with pheno_anomaly() | Understanding Anomaly Metrics | Identifying Extreme Years | Summary of Anomalies | Visualizing Anomalies | Robust vs. Classical Methods | Part 3: Data Quality Assessment | Why Quality Matters | Quality Dimensions | Running Quality Assessment | Understanding Quality Grades | Visualizing Quality Assessment | Filtering Data by Quality | Assessing Quality at Different Levels | Part 4: Complete Analytical Workflow | Part 5: Visualizing Trends | Time Series Plots | Detecting Trend Turning Points | Simple Trend Statistics | Linking Phenology to Climate | Best Practices Summary | Before Analysis | Calculating Normals | Calculating Anomalies | Analyzing Trends | Reporting | Next Steps | Session Info

Abstract | Introduction | Prerequisites | Quick start | Background | Statistical disclosure control | LLMs in statistical workflows | Provider landscape | Software design | Architecture overview | Privacy by design | Provider-agnostic LLM access | Structured tool calling | Combined utility measure | LLM-assisted variable classification | The AI_createSdcObj() function | Reasoning transparency | Interactive confirmation | LLM-assisted anonymization | The AI_applyAnonymization() function | Agentic loop: batch and refinement | Example session | Adjusting utility weights | Using different LLM providers | Graphical user interface | AI variable suggestion | AI-Assisted anonymization panel | Reproducibility | Discussion | Advantages and limitations | Privacy considerations | Comparison with related work | Summary and outlook | Computational details | References

Overview | The Problem: What is Heaping? | Detecting Heaping: Heaping Indices | Whipple's Index | Myers' Index | Bachi's Index | Noumbissi's Index | Convenience Function: All Indices at Once | Using Sampling Weights | Correcting Heaping | Basic Correction | Correction Methods | Verbose Output and Diagnostics | 10-Year Heaping | Custom Heap Positions | Single Heap Correction | Model-Based Correction | Multiple Imputation Framework | Protecting Specific Observations | Working with Aggregated Data: Sprague Multipliers | Indices for Old Ages | Summary | References

Introduction | What You'll Learn | Prerequisites | Setup | Part 1: Phenological Gradients | What are Phenological Gradients? | Altitudinal Gradient | Latitudinal Gradient | Why Study Gradients? | Altitudinal Gradient Analysis | Understanding the Function Parameters | Interpreting the Results | Latitudinal Gradient Analysis | Comparing Regression Methods | Which Method Should You Use? | Comparing Species: Grapevine Gradient | Gradients by Region | Visualizing Gradients | Expected Values and Troubleshooting | Reference Values from Literature | When Your Results Differ from Expected | Part 2: Phenological Synchrony | What is Phenological Synchrony? | Visualizing Synchrony Concepts | Why Study Synchrony? | Calculating Synchrony | Understanding the Parameters | Understanding Synchrony Metrics | Temporal Trends in Synchrony | Interpreting Trend Results | Visualizing Synchrony Over Time | Synchrony Without Trend Analysis | Comparing Synchrony: Grapevine vs. Apple | Part 3: Combining Gradient and Synchrony Analysis | Interpreting Combined Results | Part 4: Mapping Phenological Patterns | Interactive Maps with pheno_leaflet() | Features of pheno_leaflet() | Best Practices for Interactive Mapping | Static Maps with pheno_map() | Basic Station Maps | Coloring by Data Attributes | Using Google Maps Background | Mapping Phenological Patterns | Mean Phenological Timing | Phenological Trends | Species-level Variation | Understanding color_by Options | Parameter Reference for pheno_map() | Combining Mapping with Analysis | Best Practices Summary | For Gradient Analysis | For Synchrony Analysis | For Mapping | Summary | Key Take-Home Messages | Next Steps | Session Info

Overview | Functionality | Some differences to SAS-Code | Risk definition | Sampling probability | Swapping Records | Application | Supplying index vectors | Similarity profiles | Carry along variables | Supplying your own risk values | Information loss | sdcMicro Objects

Introduction and Main Features | About/Help | Microdata | Upload microdata | Testdata/internal data | R-dataset (.rdata) | SPSS-file (.sav) | SAS-file (.sasb7dat) | CSV-file (.csv, .txt) | STATA-file (.dta) | Additional options | Modify microdata | Display microdata | Explore variables | Reset variables | Use subset of microdata | Convert numeric to factor | Convert variables to numeric | Modify factor variable | Create a stratification variable | Set specific values to NA | Hierarchical data | Anonymize | Set up a problem | Anonymization Methods | View/Analyze existing sdcProblem | Show summary | Explore variables | Add linked variables | Create new IDs | Anonymize categorical variables | Recoding | k-Anonymity | PRAM (simple) | PRAM (expert) | Supress values with high risks | Anonymize numerical variables | Top-/Bottom Coding | Microaggregation | Adding Noise | Rank Swapping | Risk/Utility | Risk measures | Information of risk | Suda2 risk measure | l-Diversity risk measure | Visualizations | Barplot/Mosaicplot | Tabulations | Information loss | Obs violating k-Anon | Numerical risk measures | Compare summary statistics | Disclosure Risk | Information loss | Export Data | Anonymized Data | Anonymization Report | Change Stata Labels | Reproducibility | View/Save the current script | Import a previously saved sdcProblem | Export/Save the current sdcProblem | Undo