Browse by topic, not just chronology
The archive is finally big enough that a date-sorted list is lazy navigation. These topic pages group related guides so readers can stay inside one problem family, whether they care about identification, bias diagnostics, or study design.
AI-Assisted Research
Latest: Data Leakage in Clinical Prediction Models: When the Model Learns the Future
Adaptive Designs
Latest: Platform Trials: When a Shared Control Stops Being the Same Comparison
Bias Diagnostics
Latest: The Will Rogers Phenomenon: When Better Staging Improves Every Group and Nobody Lives Longer
Biomarkers
Latest: Surrogate Endpoints: When a Biomarker Improvement Pretends to Be Patient Benefit
Case-Crossover Design
Latest: Case-Crossover Design: When Patients Become Their Own Controls
Causal Framework
Latest: Structural Causal Models & DAGs: A Practical Guide for Clinical Researchers
Causal Inference
Latest: Causal Readiness: When a Huge Linked Dataset Still Cannot Identify an Effect
Clinical AI
Latest: When More Covariates Break Positivity: Representation-Induced Overlap Failure in Clinical Text
Clinical Epidemiology
Latest: Healthy Screenee Bias: When Screening Attendance Looks Like Screening Benefit
Clinical Outcomes
Latest: Competing Risks: When Kaplan-Meier Tells the Wrong Clinical Story
Clinical Trials
Latest: Small Number of Clusters: When 500 Patients Still Behave Like 10 Sites
Clinical Utility
Latest: Calibration Drift: When a Good Model Keeps the Right Rank and Still Gives the Wrong Risk
Collider Bias
Latest: Collider Bias: How Adjustment Can Manufacture Associations
Confounding
Latest: Covariate Balance Diagnostics: When the Love Plot Says Balanced but the Groups Still Differ
Confounding by Indication
Latest: Confounding by Indication: When Sicker Patients Make Treatments Look Dangerous
DAGs
Latest: Overadjustment Bias: When More Covariates Make Causal Inference Worse
DID
Latest: Difference-in-Differences: A Practical Guide for Clinical Researchers
Effect Measures
Latest: Noncollapsibility of Odds Ratios: Why Adjustment Can Change the Number Even When Confounding Did Not
Effect Modification
Latest: Additive Interaction: When “No Interaction” Depends on the Scale
Estimands
Latest: When Death Changes the Question: Competing Risks, Intercurrent Events, and Truncation by Death
Evidence Appraisal
Latest: Estimation Over Testing: Four Habits That Quietly Break Clinical Statistics
Evidence Synthesis
Latest: Transitivity in Network Meta-Analysis: When Indirect Comparisons Pretend the Trials Were Exchangeable
External Validity
Latest: Transportability & External Validity: When Your Causal Estimate Travels, and When It Absolutely Does Not
G-Computation
Latest: G-Computation: Predict the Outcome Under Each Treatment Strategy
G-Estimation
Latest: G-Estimation: The Causal Method You Reach For When Time-Varying Confounding Breaks Regression
G-Formula
Latest: Parametric G-Formula: Estimating Causal Effects When Covariates Change Over Time
Genetic Epidemiology
Latest: Mendelian Randomization: Using Genetics as Nature's Randomized Trial
Guideline Methods
Latest: Indirectness in Clinical Evidence: When a Good Study Answers the Wrong Question
Heterogeneous Effects
Latest: Causal Forests: Finding Treatment Effect Heterogeneity Without Fooling Yourself
High-Dimensional Data
Latest: Double Machine Learning: A Practical Guide for Clinical Researchers
IPW
Latest: Inverse Probability Weighting: When PSM Discards Your Data
Identification
Latest: Front-Door Criterion: The Causal Backdoor Alternative Nobody Uses Enough
Immortal Time Bias
Latest: Immortal Time Bias: The Fake Survival Advantage Hiding in Bad Study Design
Instrumental Variables
Latest: Instrumental Variables: When Observational Data Meets Unmeasured Confounding
Interference
Latest: Interference & Spillover Effects: When One Patient's Treatment Changes Another's Outcome
Interrupted Time Series
Latest: Interrupted Time Series: Strong Quasi-Experiments Need More Than a Before-and-After Plot
Landmark Analysis
Latest: Landmark Analysis: Useful, Honest, and Frequently Overclaimed
Longitudinal Data
Latest: Time-Varying Confounding: When Yesterday's Treatment Changes Today's Confounder
MSM
Latest: Marginal Structural Models: A Practical Guide for Clinical Researchers
Machine Learning
Latest: Targeted Maximum Likelihood Estimation: Doubly Robust, Not Doubly Forgiving
Measurement Error
Latest: Differential Misclassification: When One Study Arm Gets More Chances to Be Wrong
Mechanisms
Latest: Mediation Analysis: When You Want the Mechanism, Not Just the Effect
Mediation Analysis
Latest: Treatment-Induced Mediator-Outcome Confounding: When Mediation Analysis Starts Chasing the Consequences of Treatment
Mendelian Randomization
Latest: Mendelian Randomization: Using Genetics as Nature's Randomized Trial
Methods Critique
Latest: Causal Readiness: When a Huge Linked Dataset Still Cannot Identify an Effect
Missing Data
Latest: Complete-Case Analysis: When Missing Data Quietly Changes the Study Population
Observational Studies
Latest: Bias Amplification: When Adjustment Makes Unmeasured Confounding Worse
Oncology
Latest: Treatment Switching in Oncology Trials: When Overall Survival Becomes a Rescue Protocol Audit
Outcome Measurement
Latest: Baseline Adjustment in Randomized Trials: Why Change From Baseline Keeps Losing to ANCOVA
PSM
Latest: Propensity Score Matching: A Practical Guide for Clinical Researchers
Pharmacoepidemiology
Latest: Washout Periods: When “New Use” Is Just Old Use with Better PR
Policy Evaluation
Latest: Stochastic Interventions: When “Treat Everyone” Is Not the Policy Question
Positivity
Latest: When More Covariates Break Positivity: Representation-Induced Overlap Failure in Clinical Text
Prediction Models
Latest: Predicted Treatment Benefit: When a Risk Model Is Not a Treatment Recommendation
Principal Stratification
Latest: Principal Stratification: Estimating Effects When Post-Treatment Variables Matter
Propensity Scores
Latest: Positivity & Overlap: The Assumption Your Causal Estimate Cannot Survive Without
Quasi-Experimental
Latest: Regression Discontinuity Design: A Practical Guide for Clinical Researchers
RDD
Latest: Regression Discontinuity Design: A Practical Guide for Clinical Researchers
RMST
Latest: Restricted Mean Survival Time: When Hazard Ratios Are Not the Clinical Answer
Real-World Evidence
Latest: Causal Readiness: When a Huge Linked Dataset Still Cannot Identify an Effect
Reporting Bias
Latest: Outcome Switching: When the Primary Endpoint Moves After the Results Get Interesting
Screening Studies
Latest: Healthy Screenee Bias: When Screening Attendance Looks Like Screening Benefit
Selection Bias
Latest: Selection Bias: When Your Study Sample Is the Problem
Self-Controlled Designs
Latest: Self-Controlled Case Series: When Each Patient Becomes Their Own Control
Sensitivity Analysis
Latest: MNAR Sensitivity Analysis: Because “We Assumed MAR” Is Not a Results Section
Standardization
Latest: G-Computation: Predict the Outcome Under Each Treatment Strategy
Study Design
Latest: Causal Readiness: When a Huge Linked Dataset Still Cannot Identify an Effect
Survival Analysis
Latest: Nonproportional Hazards: When One Hazard Ratio Pretends the Treatment Effect Never Changes
Synthetic Control
Latest: Synthetic Control Methods: Building Counterfactuals When DID Fails
TMLE
Latest: Targeted Maximum Likelihood Estimation: Doubly Robust, Not Doubly Forgiving
Target Trial Emulation
Latest: Heterogeneous Treatment Effects: Validate the Average Effect Before Trusting the Subgroups
Time-Varying Confounding
Latest: Time-Varying Confounding: When Yesterday's Treatment Changes Today's Confounder
Trial Design
Latest: Futility Stopping in Clinical Trials: When “No Signal Yet” Starts Pretending the Question Is Answered
Trial Interpretation
Latest: Principal Stratification: Estimating Effects When Post-Treatment Variables Matter
Unmeasured Confounding
Latest: Proximal Causal Inference: What to Do When Unmeasured Confounding Is Still on the Table
Need the full archive instead?
If you already know the method name, the main blog explorer is still the fastest route.