Skip to main content
. 2019 Feb 28;5(1):e9176. doi: 10.2196/publichealth.9176

Table 1.

Regression analyses to detect potential association between novel data streams (Google Trends, WikiTrends, Google News, and YouTube) and real-world epidemiological figures.

Source Regression coefficient SE 95% CI t31 P value
Google Trends





Intercept 3327.876 966.213 1380.603, 5275.150 3.444 .001

Trimester –0.531 1.535 –3.624, 2.561 –0.346 .73

Year –1.653 0.481 –2.622, –0.684 –3.438 .001

West Nile virus cases 0.014 0.001 0.011, 0.017 9.629 <.001
WikiTrends





Intercept –7402.427 4130.337 –15863.039, 1058.184 –1.792 .08

Trimester 1.715 4.288 –7.068, 10.498 0.400 .69

Year 3.694 2.053 –0.512, 7.900 1.799 .08

West Nile virus cases –0.003 0.005 –0.012, 0.007 –0.566 .58
Google News





Intercept 8875.080 3807.169 1076.447, 16673.712 2.331 .03

Trimester 1.478 3.952 –6.618, 9.574 0.374 .71

Year –4.407 1.893 –8.284, –0.530 –2.328 .03

West Nile virus cases –0.001 0.004 –0.010, 0.008 –0.237 .81
YouTube





Intercept 3297.355 3606.758 –4090.754, 10685.464 0.914 .37

Trimester 3.454 3.744 –4.216, 11.124 0.923 .36

Year –1.622 1.793 –5.295, 2.051 –0.904 .37

West Nile virus cases –0.002 0.004 –0.010, 0.007 –0.453 .65