stats4PT
Moves from observations toward scientific claims through the language and methods of statistical and causal inquiry.
Evidence is more than a number
Stats4PT examines how observations become evidence, estimates, and warranted scientific claims through statistical inference, Bayesian reasoning, causal reasoning, and critical reflection.
The course
From observations to warranted claims
New to the series? Read the course orientation.
An optional certificate pathway documenting 8 contact hours of professional learning is available by request.
- 01Statistical Inference: From Observations to ClaimsDistinguish observations, summaries, induction, and uncertain statistical claims.
- 02Causality: From Association to ExplanationMove beyond observed relationships to events, mechanisms, and context.
- 03Bayesian Reasoning: Updating Beliefs Under UncertaintyRevise probabilities transparently without confusing updating with causal identification.
- 04Bayesian Updating in Diagnosis and PrognosisApply prior, diagnostic information, and posterior probability while retaining uncertainty.
- 05Bayesian Methods in Clinical Research and Evidence SynthesisExamine adaptive trials, meta-analysis, heterogeneity, and explicit assumptions.
- 06When Does Population Evidence Apply?Examine transportability, context, individual variation, and omitted mechanisms.
- 07Making Causal Assumptions Visible with DAGsRead and draft causal diagrams that expose assumptions, bias, and missing knowledge.
- 08Statistical Fallacies and Biases in Clinical ResearchRecognize causal illusions in design, interpretation, and personal experience.
Classroom presentations
Causal Models: From What We Know to What We Think Is Happening
A one-hour Clinical Inquiry I presentation about representing population causal knowledge and constructing provisional, patient-specific explanations.
Open the presentationClinical inquiry ecosystem
Distinct forms of scholarship, connected
Stats4PT does not connect every project as one educational path. It develops discovery-oriented inquiry that contributes to, but remains distinct from, integrative model building and practice reasoning.
Physiolog
Contributes physiological knowledge about how and why effects occur, adding causal depth beyond interventions and outcomes.
Models4PT
Integrates evidence, mechanisms, context, and uncertainty into comprehensive population-level causal models.
Clinical Inference Engine
Uses population knowledge with individual information to support inspectable, patient-specific practice reasoning.
stats4PT inquiry + Physiolog mechanisms → Models4PT integration → Clinical Inference Engine practice reasoning