TABLE 2.
Beta Coefficients for Variables of Best-Fit Models Examining Adherence With Full Bundle
| Approach | Frequentist, Mean (sd) | Bayesian, Mean (2.5% HPD, 97.5% HPD) | ||
|---|---|---|---|---|
| Predictors | Continuous | Binary | Continuous | Binary |
| Daily variable | ||||
| Ventilator status | –3.0 (0.5)a | –3.0 (0.5)a | –2.1 (–2.9, –1.3)b | –2.6 (–3.5, –1.8)b |
| Patient variables | ||||
| Age | –0.4 (0.2)b | –0.4 (0.2)b | –0.4 (–0.8, 0.07) | –0.4 (–0.7, –0.01)b |
| Body mass index | 0.1 (0.2) | 0.1 (0.2) | 0.05 (–0.4, 0.6) | 0.1 (–0.3, 0.5) |
| Unit variables | ||||
| Unit size | 1.0 (1.6) | 2.9 (3.5) | –0.2 (–2.5, 1.9) | –1.0 (–2.1, 0.03) |
| Canvas sling | 1.9 (1.3) | NA | –0.07 (–2.1, 2.2) | NA |
| Ceiling lift | NA | 1.9 (1.2) | NA | 1.1 (–0.6, 2.8) |
| High back chair | 1.2 (1.0) | NA | –0.4 (–2.4, 1.7) | NA |
| O2 tank | –0.7 (0.8) | NA | –0.9 (–3.2, 1.5) | NA |
| O2 tubing/positive end-expiratory pressure valve | –0.4 (0.8) | NA | 0.1 (–1.4, 1.7) | NA |
| Portable lift | NA | –12.0 (11.6) | NA | 0.7 (–1.2, 2.9) |
| Portable monitor/turning straps/bariatric chair | NA | –8.7 (8.4) | NA | 0.4 (–1.6, 2.2) |
| Portable ventilator/ nonpharmacologic aids | NA | –5.7 (3.3) | NA | –1.0 (–3.0, 0.8) |
| Recliner chair | –0.7 (0.5) | 2.7 (2.7) | 0.4 (–1.4,2.0) | 1.2 (–0.6, 3.0) |
| Specialty walker | 0.4 (0.4) | NA | –0.6 (–2.3,1.1) | NA |
| Standard walker | 0.4 (0.5) | –5.3 (4.7) | 1.0 (–0.4,2.6) | 1.7 (0.3, 3.4)b |
HPD = high probability density, NA = not applicable.
ap < 0.001.
bp < 0.05 (Frequentist) or 95% HPD excludes 0 (Bayesian).
Both Bayesian approaches assume uninformative priors.