Table A12.
Topology Bias Slope Regressions: Directed Networks.
| Variables | Model 1 Component Size | Model 2 Bicomponent Size | Model 3 Distance | Model 4 Transitivity | Model 5 Tau RC | Model 6 CONCOR |
|---|---|---|---|---|---|---|
| Intercept | −0.553 | −0.979 | −4.062*** | −0.957* | −2.251*** | −3.754*** |
| (3.77) | (1.45) | (0.37) | (0.46) | (0.11) | (0.41) | |
| Correlation with Centrality | 0.537 | 0.383*** | 0.521*** | 0.348*** | 0.081** | 0.224*** |
| (0.66) | (0.04) | (0.07) | (0.03) | (0.03) | (0.01) | |
| In-degree Std. Dev. | −0.089 | −0.084 | −0.333*** | −0.303*** | 0.014 | 0.045 |
| (0.35) | (0.13) | (0.06) | (0.08) | (0.01) | (0.04) | |
| Log of Size | −0.471 | −0.262 | 0.496*** | −0.274* | 0.013 | −0.046 |
| (0.81) | (0.31) | (0.09) | (0.11) | (0.02) | (0.09) | |
| Asymmetric Imputation | 0.696 | −0.141 | 0.71* | −0.84** | 1.884 | −0.117 |
| (7.31) | (0.97) | (0.35) | (0.26) | (1.37) | (0.33) | |
| Simple Model-Based Imputation | −14.491 | −0.026 | 1.411* | −1.834*** | −0.588 | −0.392*** |
| (41.66) | (1.17) | (0.68) | (0.39) | (0.62) | (0.11) | |
| Complex Model-Based Imputation | −3.342 | 1.705*** | 2.204** | −1.509** | −0.981* | −0.506*** |
| (7.28) | (0.44) | (0.69) | (0.48) | (0.49) | (0.14) | |
| Probabilistic Imputation | 0.696 | −0.141 | 0.925 | −1.934*** | 4.558*** | −0.212 |
| (4.26) | (1.01) | (0.72) | (0.48) | (1.1) | (0.3) | |
| Symmetric Imputation | 0.696 | −0.141 | 4.024*** | −1.784*** | −0.78 | −0.262 |
| (6.8) | (0.98) | (0.59) | (0.49) | (1.15) | (0.31) | |
| Correlation with Centrality* Asymmetric Imputation | 0.056 | −0.194** | −0.142 | −0.112* | −0.007 | −0.172*** |
| (0.93) | (0.06) | (0.11) | (0.05) | (0.04) | (0.02) | |
| Correlation with Centrality* Simple Model-Based Imputation | 2.348* | −0.443*** | −1.288*** | −0.28*** | −0.024 | −0.209*** |
| (0.93) | (0.06) | (0.11) | (0.05) | (0.04) | (0.02) | |
| Correlation with Centrality* Complex Model-Based Imputation | 1.109 | −0.346*** | −1.31*** | −0.301*** | −0.005 | −0.211*** |
| (0.93) | (0.06) | (0.11) | (0.05) | (0.04) | (0.02) | |
| Correlation with Centrality* Probabilistic Imputation | 0.056 | −0.194** | 0.176 | −0.149** | −0.005 | −0.169*** |
| (0.93) | (0.06) | (0.11) | (0.05) | (0.04) | (0.02) | |
| Correlation with Centrality* Symmetric Imputation | 0.056 | −0.194** | −0.82*** | −0.106* | 0.168*** | −0.176*** |
| (0.93) | (0.06) | (0.11) | (0.05) | (0.04) | (0.02) | |
| In-degree Std. Dev.* Asymmetric Imputation | −0.107 | −0.119 | 0.131* | 0.05 | 0.346** | −0.018 |
| (0.68) | (0.09) | (0.06) | (0.04) | (0.13) | (0.03) | |
| In-degree Std. Dev.*Simple Model-Based Imputation | −2.292 | 0.319** | −0.145 | 0.175** | 0.053 | −0.016 |
| (3.86) | (0.11) | (0.11) | (0.06) | (0.06) | (0.01) | |
| In-degree Std. Dev.*Complex Model-Based Imputation | −0.261 | 0.236*** | −0.056 | 0.361*** | 0.117* | −0.002 |
| (0.67) | (0.04) | (0.11) | (0.08) | (0.05) | (0.01) | |
| In-degree Std. Dev.* Probabilistic Imputation | −0.107 | −0.119 | −0.083 | 0.29*** | 0.423*** | −0.019 |
| (0.39) | (0.09) | (0.12) | (0.08) | (0.1) | (0.03) | |
| In-degree Std. Dev.* Symmetric Imputation | −0.107 | −0.119 | 0.098 | 0.323*** | 0.218* | −0.009 |
| (0.63) | (0.09) | (0.1) | (0.08) | (0.11) | (0.03) | |
| Log of Size* Asymmetric Imputation | −0.377 | 0.038 | −0.185* | −0.002 | −0.811** | 0.013 |
| (1.56) | (0.21) | (0.09) | (0.06) | (0.29) | (0.07) | |
| Log of Size *Simple Model-Based Imputation | 2.96 | −0.774** | −0.364* | 0.452*** | 0.05 | 0.091*** |
| (8.9) | (0.25) | (0.16) | (0.09) | (0.13) | (0.02) | |
| Log of Size* Complex Model-Based Imputation | 0.209 | −1.084*** | −0.629*** | 0.098 | 0.013 | 0.098*** |
| (1.56) | (0.09) | (0.17) | (0.12) | (0.1) | (0.03) | |
| Log of Size * Probabilistic Imputation | −0.377 | 0.038 | −0.229 | 0.262* | −1.461*** | 0.028 |
| (0.91) | (0.21) | (0.17) | (0.11) | (0.23) | (0.06) | |
| Log of Size* Symmetric Imputation | −0.377 | 0.038 | −1.14*** | 0.254* | −0.137 | 0.024 |
| (1.45) | (0.21) | (0.14) | (0.12) | (0.25) | (0.07) | |
| N | 378 | 378 | 324 | 324 | 378 | 378 |
| Networks | 7 | 7 | 7 | 7 | 7 | 7 |
Note: The regression uses the betas slopes from each line as the dependent variable. The betas represent the expected drop in correlation (between the empirical and the observed) for a 10 % increase in the amount of missing data. Larger numbers mean larger bias with more missing data. The correlation with centrality takes four values: − .75, − .25, .25, and .75.