Skip to main content

Table 2 Out-of-sample results. Comparison of models in Table 1 with respect to out-of-sample-predictions. Mean square error is estimated via randomly sampling 80% of the data to estimate the model, using the remaining 20% to test the model, and repeating 100 times. SD = standard deviation. The best out-of-sample prediction statistics are reported in bold

From: Public debate in the media matters: evidence from the European refugee crisis

 Out-of-sample prediction measures
 Mean absolute errorMean square error
 | Predicted% − True% |(SD)(Predicted% − True%)2(SD)
Media models from Table 1    
Model (1)3.08%(0.05)17.2(0.6)
Model (2)3.07%(0.1)17.1(0.6)
Control models from Table 1    
Model (3)35.4%(0.3)1507.4(20.0)
Model (4)35.4%(0.3)1504.3(17.7)
Full models from Table 1    
Model (5)35.4%(0.3)1504.1(19.7)
Model (6)35.4%(0.3)1504.5(17.0)