Skip to main content
. Author manuscript; available in PMC: 2012 Feb 1.
Published in final edited form as: J Adolesc Health. 2011 Feb;48(2):196–202. doi: 10.1016/j.jadohealth.2010.06.004

Table 1.

Bivariate and Multivariate Tests Examining Pre-Post Differences in Average Cafeteria Attitudes, and Percentage who Drank Soda and Sports/Fruit Drinks the Day before the Survey, among Peer Advocates and Non-Peer Advocates.

Peer Advocates Non-Peer Advocates Peer advocate change minus non-peer advocate change 3
Pre- Intervention Post- Intervention n Pre- Intervention Post- Intervention n b
Cafeteria Attitudes, M(SD)1 3.52 (1.78) 4.07 (1.68)** 107 3.45 (1.60) 3.37 (1.60) 283 0.71***
Soda, %2 36.1 35.2 108 37.2 43.9† 285 −0.38
Sports/Fruit Drinks, %2 33.3 21.3* 108 32.6 26.0† 285 −0.19
†

p <.10

*

p<.05

**

p<.01

***

p<.001

Note: All tests restrict to students with non-missing values for the response at both waves.

1

For continuous outcomes (cafeteria attitudes), paired t-tests were used to test for within-group change, and multivariate linear regressions were used to test for different magnitudes of within-group change across groups.

2

For dichotomous outcomes (drank soda, sports/fruit drinks), McNemar’s tests were used to test for within-group change, and multivariate logistic regressions were used to test for different magnitudes of within-group change across groups.

3

Multivariate regressions controlled for baseline outcome, gender, age, race/ethnicity, and primary language spoken at home.