Table 5.

Generalized estimating equations comparing parent and child structured interview reports of parent–child conflict as a function of informant, TTI domain, and informant×TTI domain interaction (n=100)

Factor	Mean Differences	B (SE)	95 % CI	p
Main and Interaction Effects
Child Age		0.52 (0.15)	[0.23, 0.81]	p<.001
Child Gender		−0.67 (0.68)	[−2.01, 0.66]	ns
Informant		6.05 (0.72)	[4.63, 7.46]	p<.001
TTI Domain		−0.93 (0.42)	[−1.76, −0.09]	p<.05
Informant×TTI Domain		−3.81 (0.61)	[−5.01, −2.60]	p<.001
Planned Comparisons
TTI-Discrepant Beliefs vs. TTI-Behavioral Conflict (Parent Reports)	−4.74		[−5.82,−3.66]	p<.001
TTI-Discrepant Beliefs vs. TTI-Behavioral Conflict (Child Reports)	−0.93		[−1.76,−0.09]	p<.05
Parent vs. Child Report, TTI-Discrepant Beliefs	2.24		[1.10, 3.37]	p<.001
Parent vs. Child Report, TTI-Behavioral Conflict	6.05		[4.63, 7.46]	p<.001

B unstandardized beta; SE standard error; 95 % CI 95 % Wald confidence interval for unstandardized beta. Factor contrasts based on comparisons in ascending order, with the Informant factor coded Parent and then Child, the Child Gender factor coded Female and then Male, and the TTI Domain factor coded TTI-Discrepant Beliefs and then TTI-Behavioral Conflict. For statistical tests of main and interaction effects, p values and 95 % CIs reported reflect significance tests for the reported unstandardized betas. For statistical tests of planned comparisons, p values and 95 % CIs reported reflect significance tests for estimated marginal means, adjusted for child age and child gender