7. Statistical Analyses
Statistical significance for data in Tables 2 and 3 and Figures 3 and 4 was tested using the chi-square test. For the multivariate analyses reported in Tables 1 and 4, a logistic regression was used. All the predictor variables were forced into the model and interactions tested were free to enter the model if p<0.05. The logistic regression analyses provide data on the strength of the contribution of each variable (relative odds) in predicting the outcomes controlling for the effects of the other variables. All analyses used weighted data. The choice of variables to enter into the regression analyses was based on their availability in the data set, and their ability to operationalize the variables needed to test the models outlined in Figures 1 and 2.
Table 3
Rates of Participation in the Last Twelve Months
in Sports, the Arts and
Community Programs, by Gender
|
Rates of Participation (percentage) |
Activity and Age Group |
Most Days |
A Few Times a Week |
About Once a Week |
About Once a Month |
Almost Never |
Supervised Sports |
boys |
5.6 |
39.7 |
21.3 |
4.5 |
28.8 |
girls |
3.4 |
24.6 |
25.9 |
4.2 |
41.8 |
Unsupervised Sports |
boys |
41.4 |
26.9 |
15.3 |
4.8 |
11.5 |
girls |
24.9 |
27.5 |
19.8 |
7.6 |
20.2 |
The Arts |
boys |
0.4 |
5.3 |
16.1 |
1.7 |
76.4 |
girls |
1.2 |
10.7 |
30.5 |
2.6 |
54.9 |
Community Programs |
boys |
0.6 |
3.4 |
22.1 |
2.9 |
70.9 |
girls |
0.2 |
4.3 |
29.6 |
2.5 |
63.4 |