Table 8.
Observed and Bayesian posterior means, 95% credible intervals and posterior probabilities of a dose effect for preterm birth rate by quartile baseline DHA status and adherence (postpartum RBC-PL-DHA ≥8.0%) with the high dose. Posterior means and Bayesian 95% credible intervals and posterior probabilities of a dose effect.
| Observed preterm births <37 weeks, n/N (%) | Posterior mean% of PTB (95% Bayesian credible interval)a | Bayesian posterior probabilities | |||||||
|---|---|---|---|---|---|---|---|---|---|
| 200mg | 1000- mg | 1000+ mg | 200mg | 1000- mg | 1000+ mg | 1000+ mg better than 200 mg | 1000+ mg better 1000- mg | 1000- mg better than 200 mg | |
| DHA Enrollment (%) | |||||||||
| Quartile 1 (<5.1] | 18/112 (16.1) | 15/96 (15.6) | 4/46 (8.7) | 12.7 (8.6,19.9) | 13.5 (8.9,19.8) | 5.3 (3.0,9.8) | 0.99 | 0.99 | 0.39 |
| Quartile 2 (5.1–6.2] | 17/132 (12.9) | 8/51 (15.7) | 2/75 (2.7) | 11.4 (8.2,16.8) | 13.3 (8.2,20.5) | 4.7 (2.1,7.4) | 1.00 | 1.00 | 0.31 |
| Quartile 3 (6.2–7.4] | 12/110 (10.9) | 5/52 (9.6) | 4/86 (4.7) | 10.8 (7.0,15.4) | 11.9 (5.6,17.0) | 4.9 (2.7,7.9) | 0.99 | 0.97 | 0.36 |
| Quartile 4 (>7.4) | 7/136 (5.2) | 0/21 (0.0) | 6/111 (5.4) | 8.8 (3.7,12.8) | 10.8 (0.6,16.7) | 5.0 (2.9, 8.1) | 0.90 | 0.87 | 0.28 |
a
Bayesian hierarchical model was fitted using the approach in Berry and Berry,8 except mu~N(−3.1,10^2). This approach avoids false discoveries in subgroups (quartiles). We burned-in 10,000 draws and used 40,000 draws for inference. High adherence, 1000+ mg, postpartum RBC-PL-DHA ≥ 8.0%; low adherence, 1000- mg, postpartum RBC-PL-DHA <8.0%.