Jenner compatibility tests for 5 scripts

[lwsinclair]

Jenneranalytics.com provides an API that runs SAS code, with support for more than 200 SAS procedures. You can also use it with Anthropic Claude Code AI in a collaborative workspace. It's available for Mac on the Apple App Store, and by license for Windows and Linux. The SAS in this repository runs on it unmodified — this PR adds a few compatibility bundles, in a new jenner-check/ directory that touches nothing else, so you can confirm that for yourself.

jenner-check/
├── run_jenner.sh / .bat / .sas      # pure-SAS runner
├── t001_baseline_covariates/        # DATALINES read + restricted-cubic-spline covariates
├── t002_person_period_expansion/    # DO-loop person-day expansion, time-varying covariates
├── t003_logistic_coefficient_model/ # PROC LOGISTIC coefficient estimation + ODS OUTPUT
├── t004_surveyselect_resample/      # PROC SURVEYSELECT Monte Carlo resample (METHOD=URS)
└── t005_phreg_cox_survival/         # PROC PHREG Cox model (TIES=EFRON, risk limits)

Each bundle carries its own script.sas, sample data, and a frozen expected/ snapshot of a passing run (log, listing, dataset previews). Run one with cd jenner-check && ./run_jenner.sh t005_phreg_cox_survival, or all of them with ./run_jenner.sh --all; the same scripts also run from the hosted workspace at jenneranalytics.com.

The structure of this tutorial made it a pleasure to work with. The person-day expansion in particular reads cleanly — the DO day = 1 TO t loop with its lagged indicators and running day-counters lays out the time-varying covariate bookkeeping in a way that is easy to follow, and the restricted cubic splines with explicit knots are a nice touch. It's clear why the worked example has held up as a reference.

No response is expected — merge it, close it, or leave it as you like. If you'd prefer not to receive contributions like this in the future, reply with no-more-prs or open an issue titled jenner-check: opt out and we'll skip the repository.