Module 10 · The supportive-supervision dataset
The dataset we'll carry through the course
- Read a crisp-set supervision dataset row by row.
- Spot, by eye, which conditions separate the outcomes.
- Describe how each facility becomes one case.
Picture your supervision teams visiting six facilities and recording, for each one, whether four things were missing or broken, plus whether coverage was low. Everything is crisp-set: 1 means yes, 0 means no. Because we're in problem-solving mode, our conditions are framed as gaps, and the outcome is LowCov, where 1 means coverage fell below target.
| Facility | NoTrain | NoCold | NoSuper | NoComm | LowCov |
|---|---|---|---|---|---|
| HF1 | 0 | 1 | 0 | 0 | 1 |
| HF2 | 0 | 0 | 1 | 0 | 1 |
| HF3 | 1 | 1 | 0 | 1 | 1 |
| HF4 | 0 | 0 | 0 | 1 | 0 |
| HF5 | 1 | 0 | 0 | 0 | 0 |
| HF6 | 0 | 1 | 1 | 1 | 1 |
NoTrain = vaccinators untrained · NoCold = cold chain broken · NoSuper = no monthly supervision · NoComm = no community mobilisation. We build the real R model on this exact table in Part 6.
Look at every facility where coverage was low. In each one, either the cold chain was broken (NoCold) or supervision was missing (NoSuper), and sometimes both. Now look at the two facilities that were fine: neither problem was present. Notice that NoTrain and NoComm show up on both sides, so they're red herrings. Hold that thought, because CNA is about to back up your detective work.
Look only at the facilities where coverage was low.
- What do they share that the others don't?
- Which conditions appear on both sides, and so probably don't matter?