Young Voters and Media Use
19
Table 2. Discriminant Analysis of Predictors of
Young Voter Turnout
Table 2-1. Eigenvalues
Function
Eigenvalue
% of variance
Cumulative %
Canonical
correlation
1 .618
a
100.0 100.0 .618
a. First 1 canonical discriminant functions were used in the analysis.
Table 2-2. Wilks’s Lamda
Test of Function(s)
Wilks’ Lamda Chi-square
df
Sig.
1 .62
a
171.0
21
.000***
a. This model predicted 62% of variance in young voter turnout.
*** p<.0001
Table 2-3. Classification Result
Predicted turnout (N = 368)
Actual turnout
(N=368)
Yes, I voted
(predicted N= 249)
No, I didn’t vote
(predicted N=119)
Yes, I voted
(actual N=233)
203
(correctly predicted)
30
(errors)
Original Count
(raw numbers)
No, I didn’t vote
(actual N=135)
46
(errors)
89
(correctly predicted)
Percentage
Yes, I voted
(100%)
87.1
(Correctly predicted)
12.9
(errors)
No, I didn’t vote
(100%)
34.1
(errors)
65.9
(correctly predicted)
a. 79.3% of original grouped cases correctly classified.
Convention