Skip to main content

Table 5 Additional tests

From: Estimating suicide occurrence statistics using Google Trends

 

J-B test

p -value

ARCH effect

p -value

CUSUM

p -value

Base model

1.7621

>0.1

17.6826

>0.1

4.1902

<0.01

Control model

0.9725

>0.1

11.3692

>0.1

0.7985

>0.1

Google model

0.2470

>0.1

9.9840

>0.1

0.2472

>0.1

  1. The Jarque-Bera test checks normality of residuals, the ARCH effect test controls for conditional temporal heteroskedasticity in residuals and the CUSUM tests stability of the model across time. We find no evidence that the residuals are not normal, and no evidence of heteroskedasticity in the residuals. For the control model and the Google model, we find no evidence that the parameters change across time, although this does not hold for the base model.