Skip to main content

Evidence Packs

Follow Evidence Packs in the Factlen app and get an alert when there is news. Get the app

More in Evidence Packs

ExplainerMissing Data Bias

How Missing-Indicator Imputation Fabricates Treatment Effects Out of Unobserved Data

Causal Inference Methodologists 45%Predictive Modelers 30%Applied Researchers 25%

4 sources · 4d ago

ExplainerStatistical Methods

Restricted Mean Survival Time Quantifies Gained Lifespan When Crossing Curves Break Cox Proportional Hazards

Methodological Reformers 40%Clinical Pragmatists 35%Regulatory Traditionalists 25%

7 sources · 13d ago

ExplainerStatistical Paradoxes

How Baseline Imbalances Invert Treatment Effects Between ANCOVA and Difference-in-Differences

Causal Inference Researchers 40%Applied Econometricians 30%Clinical Biostatisticians 30%

7 sources · 17d ago

Digital HealthThe Lancet

Lancet Review of Nine Million Youth Quantifies Health Risks of Problematic Digital Media Use

Public Health Advocates 45%Technology Critics 35%Evidence Skeptics 20%

4 sources · 17d ago

WEF OutlookTrend Analysis

WEF Chief Economists Survey Projects Global Economic Stabilization Amid Regional Divergence and AI Pressures

Macroeconomic Optimists 40%Resource & Infrastructure Realists 35%Developing Economy Advocates 25%

7 sources · 24d ago

ExplainerContingency Tables

Why Contingency Tables Multiply Marginal Totals to Find Expected Frequencies

Frequentist Statisticians 40%Data Scientists 30%Quality Control Engineers 30%

6 sources · 32d ago

ExplainerStatistical Theory

How Estimating a Parameter Consumes One Degree of Freedom to Ensure Unbiased Variance

Theoretical Statisticians 45%Applied Data Scientists 35%Pedagogical Instructors 20%

5 sources · 34d ago

Research BriefClinical Trial Design

How Intention-to-Treat Analysis Preserves Randomization and Prevents Selection Bias

Methodologists & Regulators 45%Clinical Practitioners 30%Biomedical Researchers 25%

9 sources · 36d ago

ExplainerConstitutional Law

The U.S. Constitution Is the Second-Hardest to Amend in the Democratic World

Comparative Political Scientists 40%Democratic Reformers 35%Constitutional Originalists 25%

3 sources · 37d ago

ExplainerImbalanced Data

Evidence Pack: The Accuracy and Trade-Offs of SMOTE Versus Class Weights in Imbalanced Data

Data-Level Resamplers 35%Algorithm-Level Penalizers 35%Post-Training Calibrators 30%

6 sources · 39d ago

ExplainerMeta-Analysis

Why High Study Precision Artificially Inflates Meta-Analysis I² Scores

Methodological Purists 40%Pragmatic Reviewers 35%Clinical Consumers 25%

6 sources · 40d ago

Research BriefDemographic Proxies

Evidence Pack: The Accuracy of BISG and Algorithmic Demographic Imputation

Regulatory Agencies 40%Data Scientists & AI Researchers 35%Civil Rights Advocates 25%

5 sources · 41d ago

ExplainerStatistical Modeling

Link Functions: Translating Bounded Outcomes Into Unbounded Linear Predictors

Statistical Purists 40%Applied Data Scientists 40%Software Developers 20%

8 sources · 42d ago

ExplainerModel Selection

Why BIC Identifies the True Model While AIC Optimizes for Prediction

Theoretical Statisticians 40%Predictive Modelers 40%Pragmatic Practitioners 20%

7 sources · 43d ago

ExplainerImbalanced Data

Why the Precision-Recall Curve Exposes Imbalanced Data Failures That ROC AUC Hides

Imbalanced Data Specialists 50%Traditional Statisticians 30%Business Stakeholders 20%

6 sources · 44d ago

ExplainerCausal Inference

The Three Criteria a Variable Must Meet to Be a Confounder in Causal Inference

Classical Epidemiologists 35%Causal Inference Statisticians 35%Clinical Researchers 30%

7 sources · 45d ago

ExplainerCausal Inference

How Local Randomization Near a Cutoff Isolates Causal Effects in Observational Data

Design-Based Empiricists 45%Algorithmic Methodologists 30%Applied Econometricians 25%

9 sources · 46d ago

ExplainerMultiplicity Adjustments

How Bonferroni and False Discovery Rate Adjustments Prevent False Positives in Massive Datasets

Strict Error Controllers 40%Exploratory Researchers 40%Methodological Reformers 20%

5 sources · 47d ago

ExplainerWearable Tech

Evidence Pack: How Accurately Commercial Wearables Measure Sleep Architecture Against Clinical Polysomnography

Clinical Sleep Researchers 40%Consumer Wearable Advocates 35%Hardware Engineers 25%

6 sources · 48d ago

Research BriefWorkplace Trends

Four-Day Workweek Pilots: Why Revenue and Retention Gains Still Lack Causal Proof

Advocates of the 100-80-100 Model 40%Labor and Well-being Researchers 40%Skeptical Industry Leaders 20%

10 sources · 49d ago

ExplainerStatistical Methodology

Meta-Analyses Use Inverse Variance Weighting to Determine True Effect Sizes

Clinical Methodologists 40%Statistical Skeptics 30%Evidence-Based Practitioners 30%

6 sources · 50d ago

ExplainerStatistical Analysis

Benford's Law: Why Natural First Digits Skew to One and How It Detects Fraud

Forensic Accountants 45%Data Scientists 35%Statistical Skeptics 20%

3 sources · 51d ago

ExplainerStatistical Mechanics

Simpson's Paradox: Why Weighted Averages in Aggregated Data Reverse Subgroup Trends

Causal Inference Advocates 40%Statistical Methodologists 35%Data Literacy Educators 25%

5 sources · 52d ago

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%

9 sources · 53d ago

ExplainerPrecision Oncology

How AI-Guided Biomarker Discovery is Rewriting the Odds of Cancer Survival

Computational Pathologists 40%Clinical Oncologists 35%Trial Designers 25%

5 sources · 54d ago

ExplainerAMOC Tipping Point

New Data Analysis Finds Atlantic Current Slowdown 60% Worse Than Forecast, Closer to Tipping Point

Observational Modellers 40%Paleoclimatologists 30%Impact Forecasters 30%

4 sources · 56d ago

ExplainerSovereign Debt

Who Owns the World's $353 Trillion Debt and How Sovereign Borrowing Is Structured

Institutional Monitors 40%Encyclopedic Consensus 30%Analytical Synthesis 30%

4 sources · 57d ago

ExplainerPoverty Data

New MPI Data: 80% of World's Poor (887M People) Exposed to Concurrent Climate Hazards

Development Economists 40%Climate Adaptation Advocates 35%Public Health Officials 25%

3 sources · 58d ago

Research BriefNeurology Data

Massive Data Analysis of 100 Million People Links Recreational Drug Use to Doubled Stroke Risk in Young Adults

Epidemiological Researchers 40%Emergency Neurologists 35%Public Health Advocates 25%

2 sources · 59d ago

Research BriefClimate Modeling

Data Analysis Confirms World Passed First Climate Tipping Point, Amazon Threshold Now Estimated at 1.5°C

Earth System Scientists 40%Conservation Ecologists 35%Data Synthesis Analysts 25%

4 sources · 60d ago

UAP DataEvidence Pack

Declassified UAP Data Reveals 25 Cold Orbs Moving at Mach 1.7 in Formation Over Gulf of Oman

National Security Observers 40%Scientific Investigators 30%Transparency Advocates 30%

5 sources · 61d ago

Global GDP ForecastEvidence Pack

NBER Model Predicts U.S. Economic Hegemony Over China by 2100 Due to Demographics and AI

Demographic Determinists 40%Techno-Optimists 35%Immigration Advocates 25%

3 sources · 62d ago

Media ConsumptionEvidence Pack

Reuters Data Finds Social Media Now Leading Global News Source, Surpassing TV and News Websites

Media Researchers 40%Independent Creators 30%Legacy News Organizations 30%

6 sources · 64d ago

ExplainerPediatric Heat Risk

Evidence Pack: How Climate Change Increased Children's Extreme Heat Exposure Risk by 55%

Climate Attribution Researchers 40%Public Health Advocates 35%Generational Analysts 25%

7 sources · 65d ago

Research BriefAI Agents

How AI Agents Achieve 96% Accuracy in Econometric Coding Through Self-Correction

Empirical Researchers 40%AI Developers 35%Methodological Skeptics 25%

4 sources · 66d ago

ExplainerMacroeconomic Modeling

NBER Study Finds Even Optimistic AI Growth Scenarios Leave US Federal Debt Near 126% of GDP by 2056

Macroeconomic Modelers 40%Fiscal Policy Analysts 40%Techno-Optimists 20%

2 sources · 67d ago

Research BriefWorkforce Data

Inside the MIT Data: The 11.7% of the US Workforce Exposed to AI Automation

Labor Economists 40%State Policymakers 30%Enterprise Leaders 30%

3 sources · 70d ago

Enabled EmissionsEvidence Pack

AI's Productivity Gains in Fossil Fuels Outweigh Its Climate Benefits for Renewables, Study Finds

Climate Researchers & Modelers 40%Environmental Advocates 30%Energy Industry Analysts 30%

7 sources · 72d ago

ExplainerEconomic Metrics

UN Expert Group Proposes Global Dashboard to Measure Progress Beyond GDP

Multilateral Institutions 40%Development Economists 35%Fiscal Pragmatists 25%

6 sources · 73d ago

Research BriefGenomic Data

Inside the NIH 'All of Us' Database: The Evidence Powering Precision Medicine

Precision Medicine Researchers 45%Health Equity Advocates 35%Clinical Integration Specialists 20%

4 sources · 75d ago

Inflation WatchEvidence Pack

US CPI Plummets 0.4% in June, Driven by Energy and Core Price Decline

Macroeconomic Analysts 44%Financial Markets 33%Official Data & Policymakers 22%

6 sources · 80d ago

Ancient GenomicsEvidence Pack

Harvard Analysis of 16,000 Ancient Genomes Shows Human Evolution Accelerated After Farming

Evolutionary Geneticists 40%Anthropologists & Archaeologists 30%Medical Researchers 30%

7 sources · 99d ago

Research BriefMedical AI

AI Analysis of Routine Blood Tests Cut Colorectal Cancer Mortality by 43%

Clinical AI Researchers 40%Healthcare Administrators 35%Health Equity Advocates 25%

5 sources · 101d ago

Deep DiveAI Benchmarks

Stanford AI Index Finds Systems Beating Human Benchmarks as Funding Hits $581.7 Billion

Technological Optimists 40%Pragmatic Adopters 35%Governance & Safety Advocates 25%

2 sources · 101d ago

Climate ModelingEvidence Pack

New Data: Phytoplankton Emissions Are a Major, Underestimated Source of Climate-Cooling Aerosols

Atmospheric Physicists 45%Climate Optimists 30%Marine Ecologists 25%

4 sources · 116d ago

ExplainerExperiment Design

How Multi-Armed Bandit Algorithms Balance Exploration and Exploitation to Beat A/B Tests

Data Scientists & Marketers 40%Clinical Ethicists & Biostatisticians 35%Traditional Statisticians 25%

5 sources · 120d ago

Per page