Methodology
Follow Methodology in the Factlen app and get an alert when there is news. Get the app
Statistical Methodology
How Winsorization Cutoffs Trade Variance Reduction Against Truncation Bias
7 sources · 4d ago
Global Health Demographics
Global Burden of Disease 2023 Analyses Map Shifting Mortality and NCD Trends Across Africa and ASEAN
7 sources · 25d ago
Climate Modeling
New Climate Model Incorporating Earth's Energy Imbalance Projects 25% Higher Global Warming
5 sources · 26d ago
More in Methodology
ExplainerBlock Bootstrapping
How Moving-Window Block Bootstraps Preserve Autocorrelation in Time Series Samples
Nonparametric Statisticians 35%Financial Risk Analysts 35%Computational Data Scientists 30%
ExplainerLongitudinal Analysis
How Linear Mixed Models Separate Individual Trajectories From Baseline Differences in Panel Data
Mixed-Model Proponents 45%Fixed-Effects Advocates 30%Methodological Skeptics 25%
ExplainerStatistical Modeling
Why Exponentiating Log Regressions Underestimates Means and How Duan's Smearing Fixes It
Classical Statisticians 40%Health Economists 35%Machine Learning Practitioners 25%
ExplainerMachine Learning
Why Feature Selection Before Cross-Validation Leaks Labels and Fakes Accuracy on Pure Noise
Statistical Theorists 40%Applied Practitioners 35%Domain Researchers 25%
ExplainerRegression Diagnostics
Why Dropping High-VIF Controls to Fix Multicollinearity Induces Omitted Variable Bias
Causal Inference Researchers 40%Predictive Machine Learning Practitioners 35%Applied Statisticians 25%
ExplainerEconometrics
Already-Treated Controls Subtract Evolving Treatment Effects: Why Two-Way Fixed Effects Assign Negative Weights in Staggered Rollouts
Econometric Theorists 40%Applied Microeconomists 40%Policy Analysts 20%
ExplainerStatistical Bias
How Immortal Time Bias Artificially Slashes Mortality Rates in Observational Medical Research
Clinical Methodologists 40%Real-World Evidence Proponents 30%Regulatory Agencies 30%
ExplainerEconometrics
Weak Instruments Shift Two-Stage Least Squares Toward Ordinary Least Squares Bias When First-Stage F-Statistics Fall Below 10
Econometric Methodologists 40%Applied Empirical Researchers 30%Replication Advocates 30%
ExplainerCovariate Adjustment
Why Adjusting for Balanced Covariates Diverges Conditional and Marginal Odds Ratios
Regulatory Agencies 38%Mathematical Statisticians 31%Causal Inference Methodologists 31%
ExplainerSurvival Analysis
Kaplan-Meier Survival Models Overestimate Clinical Risk by Ignoring Competing Deaths
Clinical Methodologists 40%Etiological Researchers 30%Public Health Planners 30%
ExplainerCausal Inference
The Unconfoundedness Assumption: How the Probability of Treatment Assignment Must Be Independent of Potential Outcomes Given Observed Covariates
Causal Methodologists 40%Social Scientists 30%Epidemiologists 30%
ExplainerStatistical Modeling
The Bayes Factor: How the Ratio of Marginal Likelihoods Quantifies Evidence for Competing Hypotheses
Objective Bayesians 45%Subjective Bayesians 30%Frequentist Defenders 25%
ExplainerTime Series Analysis
Exponential Smoothing's Alpha Parameter Balances Responsiveness and Historical Stability
Algorithmic Optimizers 40%Domain Experts 35%Robustness Advocates 25%
ExplainerStatistical Theory
Why a 95% Confidence Interval Does Not Mean a 95% Chance the True Mean is Within the Range
Frequentist Traditionalists 40%Bayesian Reformers 35%Applied Practitioners 25%
ExplainerCausal Inference
Evidence Pack: The Accuracy and Limits of Propensity Score Matching in Observational Research
Methodological Critics 40%Applied Researchers 30%Causal Inference Theorists 30%
Dimensionality Reduction
Covariance Matrix Eigenvectors Define Directions of Maximum Variance in PCA
Geometric Interpreters 35%Algebraic Purists 35%Applied Data Scientists 30%
ExplainerAnomaly Detection
Evidence Pack: The Accuracy of Benford's Law in Detecting Financial and Electoral Fraud
Forensic Accountants 40%Political Scientists 40%Data Visualisation Analysts 20%
ExplainerAlgorithmic Transparency
How SHAP Values Decompose a Black-Box Model's Prediction into Feature Contributions
Algorithmic Transparency Advocates 35%Causal Inference Skeptics 35%Applied Data Scientists 30%
ExplainerStatistical Inference
Why Heteroskedasticity Distorts Standard Errors and How Robust Standard Errors Correct the Variance Matrix
Classical Econometricians 40%Statistical Diagnosticians 35%Small-Sample Theorists 25%
ExplainerStatistical Modeling
Variance Inflation Factor: Measuring Multicollinearity and Inflated Standard Errors
Applied Researchers 40%Methodologists 35%Latent Variable Analysts 25%
ExplainerOmitted Variable Bias
The Mathematical Formula That Determines the Direction and Magnitude of Omitted Variable Bias in Regression
Econometricians 40%Predictive Data Scientists 30%Financial Risk Modelers 30%
Statistical ModelingMethodology Explainer
How a Mediator Explains the Causal Path While a Moderator Changes Its Strength
Traditional Regression Framework 44%Computational Process Analysis 33%Structural Causal Inference 22%
Census 2026Methodology Explainer
India Deploys 3 Million Enumerators for World's Largest Digital Census
Government Statisticians 40%Demographic Researchers 30%Social Policy Advocates 30%
ExplainerCausal Inference
How Arbitrary Cutoffs Isolate Cause and Effect in Observational Data
Econometricians 40%Clinical Researchers 35%Policy Evaluators 25%
ExplainerCausal Inference
Propensity Score Matching: Balancing Observational Data to Mimic Randomized Trials
Real-World Evidence Advocates 45%Clinical Trial Purists 30%Methodological Skeptics 25%
Research BriefModel Evaluation
Evaluating Classification Models: How ROC Curves and AUC Measure Discriminatory Power
General-Purpose Statisticians 60%Rare-Event Researchers 40%
ExplainerSurvey Methodology
Correcting Skewed Survey Samples With Post-Stratification, Raking, and Propensity Scores
Traditional Methodologists 40%Modern Data Scientists 40%Data Skeptics 20%
ExplainerStatistical Methods
Why Modern Research Relies on Effect Sizes and Confidence Intervals Over P-Values
Replication Reformers 45%Clinical Practitioners 35%Traditional Frequentists 20%
ExplainerMacroeconomic Measurement
Calculating GDP: Expenditure, Income, and Production Formulas Measure the Economy
Expenditure-First Analysts 40%Income-Side Economists 35%Non-Observed Economy Researchers 25%
ExplainerCancer Screening
Data From 140,000-Person Trial Paves Way for Single Blood Test to Screen for 50 Cancers
Early Detection Advocates 40%Methodology Skeptics 30%Public Health Evaluators 30%
Inflation MetricsEvidence Pack
BEA Methodology Change Will Retroactively Revise US Inflation Data Back to 2021, Lowering PCE Index
Methodological Purists 45%Monetary Policy Watchers 40%Market Skeptics 15%
Research BriefEconomic Measurement
NBER-Led Initiative Pushes Integration of Private Transaction Data Into Core US Economic Statistics
Real-Time Data Advocates 45%Traditional Statisticians 35%Methodological Reformers 20%
Research BriefMechanistic AI
Mechanistic Machine Learning Models Uncover Physical Laws, Shifting AI From Pattern Recognition to Active Scientific Discovery
Mechanistic AI Researchers 40%Applied Domain Scientists 40%Scientific Skeptics 20%
ExplainerEconomic Methodology
Inside the BTOS: How a Biweekly Survey of 1.2 Million Businesses Provides Real-Time Economic Data
High-Frequency Data Advocates 45%Methodological Skeptics 30%Respondent Burden Critics 25%
ExplainerMacroeconomics
New Fed Model Rewrites Inflation Dynamics: Uncertainty, Not Cycles, Drives Fluctuations
Uncertainty-Focused Macroeconomists 45%Traditional Keynesian Economists 30%Corporate Pricing Strategists 25%
Research BriefAI Economy
Stanford Launches AI Economic Indicators to Track AI's Real-Time Impact on Labor and Productivity
Labor Economists 35%Macroeconomists 35%Technology Optimists 30%
ExplainerEconomic Measurement
World Bank's Prosperity Gap Replaces Poverty Lines With an Income Multiplier
Development Economists 40%Global Aid Organizations 35%Data Methodologists 25%
ExplainerEconomic Measurement
ONS Blue Book 2026 Revisions Lift UK 2024 GDP by 0.5% on Service Sector Data
National Statisticians 40%Market Analysts 35%Methodological Reviewers 25%
ExplainerClimate Economics
New Economic Methodology Finds Climate Damages Overestimated by Half Without Accounting for Global Convergence
Macroeconomic Theorists 40%Empirical Econometricians 30%Climate Policy Analysts 30%
Federal DataAccountability Tracker
New Tracker Finds 338 Federal Data Collections Modified, 28 Deleted Since 2025
Civic Data Advocates 45%Research and Nonprofit Sector 35%Federal Administration Officials 20%
ExplainerResearch Integrity
New Study Finds Proprietary AI and 'Black Box' Tools Threaten Scientific Reproducibility
Open Science Advocates 45%Pragmatic Researchers 30%Commercial AI Developers 25%
ExplainerAI Bias
Study Finds AI Models Invent New Biases on Neutral Data, Challenging Training Data Paradigm
Mechanism Researchers 40%Sociotechnical Critics 35%Algorithmic Neutrality Advocates 25%
ExplainerFederal Data
Staffing Crisis and Leadership Vacancies Threaten Integrity of US Federal Economic and Social Data, ASA Report Finds
Statistical Agency Advocates 40%Federal Workforce Analysts 30%Data User Community 30%
ExplainerAI Governance
OMB M-24-10 Requires Federal Agencies to Build Audit Trails for AI Accountability
Federal Policymakers 40%Statistical Agencies 30%Algorithmic Accountability Advocates 30%
Research BriefAI Reproducibility
How Data Reproducibility is Bottlenecking AI-Driven Scientific Discovery
Experimental Scientists 35%Machine Learning Critics 35%Open Science Advocates 30%
Economic DataMethodology Explainer
How Tweaks to Government Data Models Are Shifting Inflation Metrics and Privacy Rules
Statistical Methodologists 40%Market Analysts 35%Policy Watchdogs 25%
Per page