. Author manuscript; available in PMC: 2015 Aug 7.

Published in final edited form as: Multivariate Behav Res. 2015;50(4):383–397. doi: 10.1080/00273171.2015.1022641

Table 4.

Partial Correlations for Selected Variable Pairs within Contributing and Calibration Samples

	Sample
	Add Health		CDP		GSMS		Calibration

	pr	95% CL	pr	95% CL	pr	95% CL	pr	95% CL
	n = 687						n = 123
Add Health variables:
H3TO41-H3TO43	.53	(.48,.59)					.47	(.31,.60)
H3TO41-H3TO52	.25	(.18,.32)					.14	(−.05,.32)^a
H3TO41-H3T104	.40	(.34,.46)					.27	(.09,.44)^b
H3TO43-H3TO52	.35	(.28,.41)					.38	(.20,.52)
H3TO43-H3T104	.45	(.38,.50)					.46	(.30,.59)
H3TO52-H3T104	.47	(.41,.53)					.44	(.27,.57)

			n = 269				n = 131
CDP variables:
DAU15RDF-DAU15EDF			.51	(.41,.59)			.43	(.28,.56)
DAU15RDF-Y15A39			.13	(.01,.25)			.13	(-.04,.30)
DAU15EDF-Y15A39			.20	(.09,.32)			.38	(.21,.52)

					n = 756		n = 117
GSMS variables:
CHA3101-CAV8I02					.29	(.22,.35)	.18	(−.00,.36)

Note. Add Health = National Longitudinal Study of Adolescent Health; CDP = Child Development Project; GSMS = Great Smoky Mountains Study of Youth; pr = partial correlation estimate; 95% CL = 95% Confidence Limits. Confidence limits were obtained using Fisher's z transformation.

When two unusual observations are excluded, pr = .21.

When two unusual observations are excluded, pr = .32.