Part 4 – Exploration, preregistration and archiving
Part 4 opens the menu of alternatives to the specification you reproduced, has you explore it and put a dot on the class chart, then asks for the one analysis you would defend, preregistered in your report before it runs. The last stretch covers where a finished reanalysis is archived, and what a version history, a licence and a registration each add to the chance that someone else can find and re-run it.
| Work through | What you do | Timing |
|---|---|---|
| Specification menu and slides | The axes you choose from, the three levels they sort into, what Task 2 of Multi100 left open, the ground rules for the menu and the claim-alignment convention that puts every result on one scale. | 15 minutes |
| Task 4 in the workspace or on the Browser lab, then Multiverse | Call try_spec() three or four times, changing one argument at a time, print them with my_experiments(), then submit the one you would defend with submit_exploration(). Your dot is drawn on the chart as an open circle. |
20 minutes |
| Multiverse and slides | The exploratory dots from the class, read against the full curve and the five analysts. | 12 minutes |
| Slides | The critics of multiverse analysis, the argument that a fully specified question has one correct analysis, and what preregistration settles and what it leaves open. | 8 minutes |
| Slides, archiving and registering, with Reproducibility repositories and Social science data sources as the companions | The three OSF addresses connected with the case and what each of them is for; the Multi100 preregistration, which is the protocol that the project filed for itself; the two preregistration templates, and the eight AsPredicted questions with your answers already mapped onto them. | 12 minutes |
| The report skeleton in the workspace, or Browser lab Task 5 | Complete the preregistration block before you run anything, translate it into model syntax yourself, run it, render the report, and submit with report_result(). Your declared result is drawn on the chart as a filled circle. |
18 minutes |
| Slides | Two points from the literature, the single analytical path, and what you take with you. | 5 minutes |
By the end of the part you have an exploratory dot and a declared dot on the class chart, a rendered report that contains a preregistration block with its result underneath, and the addresses at which a reanalysis like yours is archived and registered.