Table 5.

Association of friend's depression and ego depression

	Alter type
	Friend	Mutual friend	Alter-perceived friend	Male Friend	Female friend
Alter currently depressed	0.78 (0.36)	1.43 (0.61)	0.49 (0.56)	–0.92 (0.96)	0.93 (0.38)
Alter previously depressed	0.68 (0.42)	2.23 (0.63)	0.71 (0.45)	0.43 (0.75)	0.77 (0.44)
Ego previously depressed	2.34 (0.3l)	2.35 (0.72)	1.12 (0.53)	2.57 (0.71)	2.25 (0.33)
Exam 7	0.47 (0.27)	–0.75 (0.64)	0.22 (0.43)	–0.20 (0.50)	0.68 (0.32)
Ego's age	0.00 (0.02)	0.08 (0.04)	0.01 (0.02)	0.03 (0.04)	–0.02 (0.03)
Ego female	0.63 (0.40)	–0.35 (0.58)	1.09 (0.45)	1.42 (0.60)	0.30 (0.70)
Ego s years of education	–0.24 (0.09)	–0.42 (0.21)	0.03 (0.10)	–0.25 (0.13)	–0.25 (0.12)
Constant	–0.48 (2.13)	–3.24 (4.25)	–4.89 (2.41)	–2.48 (3.51)	0.79 (2.65)
Deviance	51	11	36	12	38
Null deviance	66	18	38	16	49
N	858	265	572	359	499

Coefficients and standard errors in parenthesis for linear logit regression of ego's depression status on covariates are shown. Observations for each model are restricted by type of relationship (for example, the leftmost model includes only observations in which the ego named the alter as a ‘friend’ in the previous and current period). Models were estimated using a general estimating equation with clustering on the ego and an independent working covariance structure. Models with an exchangeable correlation structure yielded poorer fit. Fit statistics show sum of squared deviance between predicted and observed values for the model and a null model with no covariates.