mice-py

Getting Started

  • Installation
    • Requirements
    • Installation Methods
      • From GitHub
      • Development Installation
    • Optional Dependencies
      • Install with Testing Tools
      • Install with Documentation Tools
      • Install with Development Tools
    • Verifying Installation
    • Troubleshooting
      • Import Errors
      • Dependency Conflicts
      • Version Compatibility
    • Next Steps
  • Quickstart Guide
    • Basic Workflow
    • Minimal Example
    • Understanding the Output
    • Checking for Convergence
    • Visualizing Imputations
    • Using Different Methods
      • PMM (Default)
      • CART
      • Random Forest
      • Method Per Variable
    • Logging
    • Common Parameters
    • Next Steps

User Guide

  • User Guide
    • Understanding Missing Data
      • Checking for Missing Data
      • Visualizing Missing Patterns
      • Types of Missing Data
      • When to Use MICE
      • Next Steps
    • MICE Overview
      • What is MICE?
      • How MICE Works
        • The MICE Algorithm
        • Visual Example
      • Basic Usage
        • Simple Example
        • Key Parameters
      • Controlling the Imputation Process
        • Predictor Matrix
        • Method-Specific Parameters
      • Accessing Results
        • Imputed Datasets
        • Convergence Diagnostics
        • Model Fitting and Pooling
      • When MICE Works Well
      • Limitations of MICE
      • The Imputation Model vs Analysis Model
      • Typical Workflow
        • Example Workflow
      • Next Steps
    • Imputation Methods
      • Overview of Methods
      • PMM: Predictive Mean Matching
        • How It Works
        • Usage
        • Parameters
        • When PMM Works Best
        • Limitations
      • CART: Classification and Regression Trees
        • How It Works
        • Usage
        • Parameters
        • When CART Works Best
        • Limitations
      • Random Forest
        • How It Works
        • Usage
        • Parameters
        • When Random Forest Works Best
        • Limitations
      • MIDAS: Multiple Imputation with Distant Average Substitution
        • How It Works
        • Usage
        • When MIDAS Works Best
        • Limitations
      • Sample: Random Sampling
        • How It Works
        • Usage
        • When Sample Works Best
        • Limitations
      • Choosing a Method
        • Decision Tree
        • General Guidelines
      • Using Different Methods for Different Variables
      • Comparing Methods
      • Research Findings
      • Next Steps
    • Predictor Matrices
      • What is a Predictor Matrix?
        • Example
      • Default Behavior
      • When to Customize
      • Creating Custom Predictor Matrices
        • Start with Default
        • Exclude Specific Predictors
        • Use Only Specific Predictors
        • Block of Variables
      • Common Patterns
        • Include Complete Variables
        • Auxiliary Variables
      • Quickpred: Automatic Predictor Selection
      • Monotone Patterns
      • Practical Examples
        • Example 1: Exclude Future Predictors
        • Example 2: Separate Domains
        • Example 3: High-Dimensional Data
      • Checking Your Predictor Matrix
      • Common Issues
        • Too Few Predictors
        • Too Many Predictors
        • Circular Dependencies
      • Tips and Best Practices
      • Testing Your Choices
      • Next Steps
    • Convergence Diagnostics
      • What is Convergence?
        • Why It Matters
        • How MICE Converges
      • Chain Statistics
      • Visualizing Convergence
        • Interpreting the Plots
      • Numerical Assessment
      • What to Do If Not Converged
        • Increase Iterations
        • Adjust Initial Values
        • Simplify Predictor Matrix
        • Change Method
      • How Many Iterations?
      • Convergence by Variable
      • Other Diagnostic Checks
        • Compare Observed vs Imputed
        • Check Variability Between Imputations
      • Common Convergence Issues
        • Slow Convergence
        • Non-Convergence
        • Oscillating Chains
        • Separated Chains
      • Best Practices
      • Quick Convergence Checklist
      • Next Steps
    • Pooling Analysis
      • Why Pool Results?
      • Rubin’s Rules
        • Basic Concept
      • Using mice-py for Pooling
        • Simple Workflow
      • Understanding the Output
        • Example Output
      • Fraction of Missing Information (FMI)
      • Formula Syntax
        • Basic Formulas
        • Categorical Variables
        • Transformations
      • Advanced Pooling
        • Pool Without Summary
        • Custom Analysis
      • Interpreting Pooled Results
        • Statistical Significance
        • Effect Sizes
        • Model Comparison
      • How Many Imputations?
        • General Guidelines
        • Checking If You Have Enough
      • Common Pitfalls
        • Don’t Use Single Imputation
        • Don’t Average Imputed Values
        • Don’t Ignore Imputation Uncertainty
      • Checking Results
      • Tips for Better Pooling
      • Next Steps
    • Best Practices
      • Basic Setup
      • Recommended Parameters
      • Method Selection
      • Always Check Convergence
      • Compare Distributions
      • Proper Pooling
      • Common Mistakes
      • Variable Selection
      • Predictor Matrix
      • Performance Tips
      • Essential Checklist
      • See Also
    • Overview
    • Getting Help

Theory & Background

  • Theory & Background
    • Missing Data Mechanisms
      • MCAR: Missing Completely at Random
      • MAR: Missing at Random
      • MNAR: Missing Not at Random
      • Practical Implications
    • Multiple Imputation Theory
      • Why Multiple Imputation?
      • The Three-Step Process
      • What is MICE?
      • Key Points
      • When MICE Works
    • Method Details
      • PMM: Predictive Mean Matching
      • CART: Classification and Regression Trees
      • Random Forest
      • MIDAS: Distance Aided Substitution
      • Sample: Random Sampling
      • Comparison Summary
    • Rubin’s Rules
      • The Problem
      • Basic Formulas
      • Fraction of Missing Information (FMI)
      • How Many Imputations?
      • Usage in mice-py
    • Overview

Examples

  • Examples
    • Available Notebooks
      • 01. Basic Imputation
      • 02. Imputation Methods
      • 03. Advanced Parameters
      • 04. Analysis Workflow
      • 05. Diagnostic Plots
    • Dataset
    • Learning Paths
      • New to MICE?
      • Already Familiar with MICE?
      • Want to Dive Deeper?
    • Quick Code Snippets
      • Basic Example
      • With Diagnostics
      • Different Methods for Different Variables
    • Running the Notebooks
      • Local Installation
      • Online Viewing
    • Additional Resources
    • Getting Help
    • Contributing Examples

API Reference

  • API Reference
    • MICE Class
      • MICE
        • MICE.data
        • MICE.id_obs
        • MICE.id_mis
        • MICE.__init__()
        • MICE.impute()
        • MICE.fit()
        • MICE.pool()
      • Overview
      • Basic Usage
      • Main Methods
        • __init__(data)
        • impute()
        • fit(formula)
        • pool(summ=True)
      • Attributes
        • data
        • imputed_datasets
        • chain_mean
        • chain_var
        • id_obs
        • id_mis
      • Examples
        • Basic Imputation
        • Custom Methods Per Variable
        • Custom Predictor Matrix
        • With Method-Specific Parameters
        • Complete Analysis Workflow
      • See Also
    • Imputation Methods
      • PMM: Predictive Mean Matching
        • pmm()
        • quantify_cca()
        • matcherid()
      • CART: Classification and Regression Trees
        • cart()
      • Random Forest
        • rf()
      • MIDAS: Distance Aided Substitution
        • bootfunc_plain()
        • minmax()
        • compute_beta()
        • midas()
      • Sample: Random Sampling
        • sample()
      • See Also
    • Pooling Functions
      • MICEresult Class
        • MICEresult
      • Pooling Module
        • PoolingResult
        • validate_imputed_datasets()
        • apply_rubins_rules()
        • pool_descriptive_statistics()
        • pool_from_files()
        • pool_subset()
      • See Also
    • Plotting Functions
      • Diagnostic Plots
        • stripplot()
        • bwplot()
        • densityplot()
        • densityplot_split()
        • xyplot()
        • plot_chain_stats()
      • Plotting Utilities
        • md_pattern_like()
        • plot_missing_data_pattern()
      • See Also
    • Utilities
      • Logging Configuration
        • setup_logging()
        • get_logger()
        • disable_logging()
        • reset_logging()
      • Validation Functions
        • check_n_imputations()
        • check_maxit()
        • check_method()
        • check_initial_method()
        • check_visit_sequence()
        • validate_predictor_matrix()
        • validate_columns()
        • validate_dataframe()
        • validate_formula()
      • Utility Functions
        • get_imputer_func()
      • Sampler Functions
        • sym()
        • norm_draw()
        • estimice()
      • See Also
    • Overview
    • Main Components
      • MICE Class
      • Imputation Methods
      • Pooling Functions
      • Plotting Functions
      • Utility Functions
    • Quick Reference
      • Common Imports
      • Typical Workflow
    • Parameter Reference
      • MICE.impute() Parameters
      • Method-Specific Parameters
    • Return Values
      • MICE.imputed_datasets
      • MICE.chain_mean, MICE.chain_var
      • MICE.pool()
    • See Also

Development

  • Contributing
    • Ways to Contribute
    • Development Setup
      • Fork and Clone
      • Install Development Dependencies
      • Create a Branch
    • Development Workflow
      • Making Changes
      • Running Tests
      • Code Style
      • Writing Tests
      • Documentation
    • Submitting Changes
      • Commit Your Changes
      • Push to Your Fork
      • Open a Pull Request
    • Pull Request Guidelines
      • After Submission
    • Code Review Process
      • What to Expect
      • Tips for Success
    • Adding New Imputation Methods
    • Building Documentation
      • Local Build
      • Auto-rebuild
    • Getting Help
    • Code of Conduct
      • Be Respectful
      • Be Collaborative
    • License
    • Questions?
    • Thank You!
  • Changelog
    • Version 0.1.0
      • Core Features
      • Imputation Methods
      • Configuration Options
      • Diagnostic Tools
      • Statistical Analysis
      • Documentation
      • Testing
      • Development
      • Contributors
    • Future Plans
    • Reporting Issues
  • References
    • Core References
    • Citing mice-py
mice-py
  • Search

© Copyright 2025, Anna-Carolina Haensch, The Anh Vu, Zhanna Lopuliak.

Built with Sphinx using a theme provided by Read the Docs.