Table 3.
Bias in Scenarios with X 1 and X 2 Continuous, Coordinated Missing Data Mechanism and Outcome Prevalence = 0.30
| Simulation scenario | Parameter | MVNI | MVNI + deletion | FCS | FCS + deletion |
|---|---|---|---|---|---|
| 1. Corr(X 1, X 2) = 0.70, β 1 = β 2 = log(3), λ = 2 | β 1 | −0.26 | 0.01 | −0.09 | 0.02 |
| β 2 | −0.27 | −0.11 | −0.24 | −0.12 | |
| 2. As in (1.), but with Corr(X 1, X 2) = 0 | β 1 | −0.27 | −0.05 | −0.15 | −0.05 |
| β 2 | −0.21 | −0.06 | −0.16 | −0.06 | |
| 3. As in (1.), but with β 1 = 0 | β 1 | −0.04 | 0.02 | 0.01 | 0.02 |
| β 2 | −0.17 | −0.03 | −0.10 | −0.03 | |
| 4. As in (1.), but with β 2 = 0 | β 1 | −0.24 | 0.00 | −0.10 | 0.00 |
| β 2 | 0.00 | 0.00 | 0.00 | 0.00 | |
| 5. As in (1.), but with β 1 = β 2 = 0 | β 1 | −0.01 | −0.01 | −0.01 | −0.01 |
| β 2 | 0.01 | 0.01 | 0.01 | 0.01 | |
| 6. As in (1.), but with λ = 0 (MCAR) | β 1 | −0.11 | 0.00 | 0.00 | 0.00 |
| β 2 | −0.17 | −0.08 | −0.08 | −0.08 |
Abbreviations: Corr correlation, MCAR missing completely at random, MVNI multivariate normal imputation, FCS fully conditional specification