. Author manuscript; available in PMC: 2014 Oct 20.

Published in final edited form as: Sociol Methodol. 2012 Aug 1;42(1):155–205. doi: 10.1177/0081175012455628

Table A4.

Add Health Results: 25 Percent Sample, 5 Step Reachability

		Ego Network Configuration Model				Degree Model		Homophily Model

Net ID	True Value	Mean Estimate	SE^a	Bias^b	Relative Bias^c	Bias^b	Relative Bias^c	Bias^b	Relative Bias^c
1	.348	.380	.049	.032	.091	.224	.643	.195	.562
2	.801	.851	.024	.049	.061	.078	.098	.068	.085
3	.564	.649	.041	.085	.150	.230	.408	.196	.347
4	.464	.526	.049	.062	.133	.340	.732	.244	.526
5	.926	.932	.020	.006	.006	.047	.050	.040	.043
6	.233	.267	.034	.034	.146	.381	1.639	.227	.975
7	.775	.844	.029	.069	.090	.140	.181	.134	.173
8	.882	.924	.015	.042	.048	.063	.072	.065	.074
9	.565	.640	.038	.075	.133	.265	.469	.242	.428
10	.687	.746	.035	.058	.085	.221	.321	.174	.253
11	.610	.691	.037	.081	.133	.206	.338	.180	.294
12	.763	.812	.022	.049	.065	.108	.142	.101	.133
13	.800	.859	.024	.059	.074	.139	.173	.123	.154
14	.420	.492	.044	.072	.171	.313	.745	.265	.631
15	.881	.910	.016	.029	.033	.069	.078	.063	.071
16	.881	.924	.016	.043	.048	.082	.093	.073	.083
17	.591	.626	.033	.035	.059	.276	.466	.153	.260
18	.720	.824	.027	.104	.145	.203	.282	.193	.268
19	.882	.919	.012	.037	.042	.071	.080	.063	.072
20	.393	.440	.033	.047	.119	.202	.514	.177	.451

Note: The values for Mean Estimate, SE, Bias, and Relative Bias are calculated over 30 independent samples, where each sample yields one estimate of the network measure

The Standard Error is the standard deviation of the sampling distribution.

Bias=E(estimates)−True Value

Relative Bias= |Bias/True Value|