The researchers then conducted a multiple linear regression to predict knowledge score. Age was measured in years, gender was coded as male = 0, female = 1, political interest was coded as no = 0, yes = 1, and rally attendance was coded as no = 0, yes = 1.

Table 2. Summary of Hierarchical Regression Analysis for Variables Predicting Opposition Party Knowledge (N = 1,852). Model I Model 2 Model 3 Variables B SE B SE B B SE B Age -0.013 005 -.048* 0.027 .006 099** Gender 0.030 .006 -0.796 .156 -.105** -0.763 . 149 -.100* Political interest -0.778 . 143 1.261 -.102* 077 345* 1.004 .076 .275* Rally attendance 0.703 .076 2.072 .193* . 187 .233** 1.924 . 179 .216** Education 1.570 .174 176* 0.787 .060 .309* 0.648 Mainstream media use .059 255** 1.223 Alternative media use . 124 .203* 1.696 Mainstream * Education .237 173* 0.094 Alternative x Education .076 024 Adjusted R2 -0.432 . 147 -.066* .243 .308 Adjusted R2 change .365 .244 .065 F for change in adjusted R2 .059 149.215 174.132 42.747 *p <.05.>