Causal Inference Studies

Causal questions turned into estimands, diagrams and written plans, then answered with difference in differences, matching, synthetic control and other quasi-experimental designs, with assumptions checked and stated.

Free · Mac (Apple silicon) and Windows · v1.0.5 · Other platforms

Then open the Marketplace in the app, search for Causal Inference Studies, and click Install. It goes into your own files, and works offline from then on.

What it installs.

1

Pillar

1

Area

50

Projects

202

Starter tasks

📊 Data & Analytics

Causal Inference Studies

Estimating the true effect of a change when experiments are impossible, using techniques like difference in differences and matching.

  1. Inventory of decisions waiting on a causal answer
  2. Turning a causal question into a precise estimand
  3. Record of why a randomised experiment is ruled out
  4. First causal diagram of treatment, outcome and confounders
  5. Treatment exposure and timing definition
  6. Outcome measure and follow-up window
  7. Confounder data audit against the diagram
  8. Choosing the identification strategy
  9. Causal analysis toolkit and environment
  10. Pre-analysis plan for an observational study
  11. Causal study register and evidence library
  12. Natural experiment watchlist
  13. Evaluability review for planned launches
  14. Weekly causal inference reading and replication
  15. Quarterly look-back on past causal estimates
  16. Peer review of causal claims before release
  17. Evidence grade on every business case
  18. Pre-period data snapshots before records are overwritten
  19. Annual evaluation agenda with leadership
  20. Potential outcomes and counterfactual thinking
  21. Confounders, colliders and mediators in causal diagrams
  22. Difference in differences and parallel trends
  23. Staggered adoption and modern difference in differences estimators
  24. Propensity score matching and weighting with balance checks
  25. Regression discontinuity around eligibility thresholds
  26. Instrumental variables and the exclusion restriction
  27. Synthetic control for a single treated market
  28. Interrupted time series for a single change date
  29. Difference in differences study of a regional rollout
  30. Matched comparison for a voluntary programme
  31. Placebo and falsification tests for an existing estimate
  32. Sensitivity analysis for unmeasured confounding
  33. Quasi-experiment or pilot experiment decision
  34. Re-analysing a before-and-after claim
  35. Triangulating one effect with two designs
  36. Threats to validity register for a study
  37. Presenting a causal estimate to decision-makers
  38. One-year evaluation of a launched initiative
  39. External methods review before a high-stakes release
  40. Submitting an observational study for publication
  41. Half-day causal methods workshop for analysts
  42. Moving from academic causal research to industry
  43. First causal study without a data team
  44. Commissioned evaluation for a funder or regulator
  45. Inheriting a causal study with undocumented choices
  46. Few treated units and small-sample inference
  47. Target trial emulation with longitudinal records
  48. Heterogeneous effects with causal forests
  49. Double machine learning for many confounders
  50. Mediation analysis of how an effect works

Where it starts.

Each project arrives with its purpose, milestones and first tasks written out. Here is how the first three read.

Inventory of decisions waiting on a causal answer

Most organisations carry a backlog of questions phrased as did it work: the loyalty scheme, the new onboarding call, the regional price change, the leadership course. Listing them with the decision each one feeds, who is asking and when the answer is needed shows which deserve a proper study and which only need a description of what happened.

First tasks

  • List every did-it-work question you have been asked in the last six months
  • Write beside each one the decision it feeds and who makes it
  • Ask each owner what answer would change what they do
  • Pick the three questions most worth a proper study
  • Revisit the question list and drop any that have gone stale @recurring(quarterly)

Turning a causal question into a precise estimand

Asking whether the loyalty scheme increased spending hides choices that change the answer: increased it for whom, compared with what, measured over how long. Writing the estimand down, with the treated population, the comparison, the outcome, the time horizon and whether you want the average effect on everyone or on those treated, prevents a correct analysis of the wrong question.

First tasks

  • Write the causal question for your first study as one plain sentence
  • Name the population, treatment, comparison, outcome and time horizon separately
  • Decide whether the decision needs the effect on all units or on treated units only
  • Send the estimand to the decision owner and get a written yes

Record of why a randomised experiment is ruled out

Observational designs need stronger assumptions than a randomised test, so the first honest step is checking whether randomisation really is off the table. Recording the reason, whether the change already shipped to everyone, randomising would be unethical or unlawful, the unit is a whole country or the sample is too small, stops the team defaulting to a weaker design out of habit.

First tasks

  • Ask the change owner whether any part of the rollout could still be randomised
  • Write down the specific reason a full experiment is ruled out
  • Check whether a randomised rollout order is possible instead
  • Record the decision and who agreed it in the study folder

Make it yours.

Install Causal Inference Studies, then tell Aurum the date you're aiming for. It checks whether the plan fits the weeks you actually have.

Free · Mac (Apple silicon) and Windows · v1.0.5 · Other platforms

Blueprints are general information to help you organise your own work. They are not medical, financial, legal or other professional advice. See the Terms.