Package: miceFast 0.9.1.9000

Introduction | Quick-start: MI in 10 lines | Missing-Data Mechanisms | MCAR: Missing Completely at Random | MAR: Missing at Random | MNAR: Missing Not at Random | Practical guidance | Multiple Imputation: Theory | The MI procedure | Rubin's rules | Degrees of freedom | Diagnostic quantities | Why MI works | Proper imputation | Congeniality | Multiple Imputation with miceFast | Why miceFast for MI? | Stochastic models for MI | Basic MI workflow | MI with mixed variable types | MI with GLMs | MI with grouped imputation | MI with weighted imputation | MI with PMM (OOP interface) | Sensitivity Analysis | Why sensitivity analysis? | Comparing models with fill_NA_N() | Varying the number of imputations | Comparing with base methods | Choosing the Number of Imputations | Practical Checklist | Von Hippel's two-stage rule for m | Comparison with mice | References

Overview | Available Imputation Models | Example Data | Examining Missingness | Checking for Collinearity | Single Imputation with fill_NA() | Basic usage (dplyr) | With weights and grouped imputation | Log-transformation | Using column position indices | Basic usage (data.table) | Multiple Imputation with fill_NA_N() | dplyr | data.table with grouping | Comparing Imputations | Multiple Imputation with pool() | Full Imputation: Filling All Variables and MI with Rubin's Rules | The miceFast OOP Module | Methods | Simple example | With weights and groups | With unsorted groups | Full MI workflow with OOP | Iterative FCS (Chained Equations) with miceFast | data.table (convenience functions) | Generating Correlated Data with corrData | Tips | References