Unequal-variance response plan ============================== StatMedAnalysis | Original downloadable worksheet | 6 November 2026 Choose an uncertainty method consistent with observed variance structure. How to use this worksheet Inspect residual spread across fitted values and meaningful groups. Distinguish changing variance from an incorrect mean model or data errors. Compare justified approaches such as robust covariance, weighted modeling or transformation. Record what each approach changes and the dependence assumptions it retains. Save a working copy and keep the original blank version. Use public, hypothetical or aggregate information only; do not enter patient identifiers, credentials or confidential records. Keep source evidence in your approved project workspace. Mark unresolved text fields UNKNOWN or NOT REPORTED with a reason; never substitute zero for an unknown count. Project/version __________________ Prepared by role/date __________________ Working fields 1. Model and observation unit Response/evidence: _________________________________________________________ ___________________________________________________________________________ 2. Evidence of changing residual spread Response/evidence: _________________________________________________________ ___________________________________________________________________________ 3. Mean-model adequacy check Response/evidence: _________________________________________________________ ___________________________________________________________________________ 4. Independent versus clustered observations Response/evidence: _________________________________________________________ ___________________________________________________________________________ 5. Candidate covariance or variance model Response/evidence: _________________________________________________________ ___________________________________________________________________________ 6. Weight source if weighted fitting Response/evidence: _________________________________________________________ ___________________________________________________________________________ 7. Estimate and interval comparison Response/evidence: _________________________________________________________ ___________________________________________________________________________ 8. Chosen method and limitations Response/evidence: _________________________________________________________ ___________________________________________________________________________ Hypothetical worked case A fictional model has similar residual centers but larger spread at high fitted values. A heteroskedasticity-robust SE may change uncertainty while retaining coefficients, but it does not fix omitted nonlinear structure or correlated observations. Decision rule and limitations Select the method for the sampling and variance structure, not the smallest p-value. State small-sample and dependence limitations of the chosen covariance estimator. Decision _______________________ Remaining uncertainty ____________________ Next action ____________________ Owner / review date ______________________ Independent check and discrepancy resolution _______________________________ Official method or reporting reference checked 6 November 2026 https://www.statsmodels.org/stable/diagnostic.html This is an original planning aid, not an official checklist, validated instrument, clinical recommendation or certificate of expert approval. Apply the referenced guidance to the specific design and record any additional requirements.