Big data would not lie: prediction of the 2016 Taiwan election via online heterogeneous information

EPJ Data Science

Table 2 Influential significance of events detected for Tsai Ing-wen

	Estimate	Std. Error	t value	Pr(>\|t\|)
c	−0.0262	0.0224	−1.169	0.2464
\(p^{tsai}_{k-1}\)	1.0503	0.0430	24.414	<2e–16^∗∗∗
\(\gamma _{1}\)	−0.0055	0.0032	−1.724	0.0894^∗
\(\gamma _{2}\)	−0.0078	0.0034	−2.299	0.0246^∗∗
\(\gamma _{3}\)	−0.0016	0.0027	−0.611	0.5430
\(\gamma _{4}\)	0.0007	0.0039	0.190	0.8499
\(\gamma _{5}\)	−0.0024	0.0029	−0.839	0.4047
\(\gamma _{6}\)	0.0011	0.0019	0.604	0.5480
\(\gamma _{7}\)	0.0007	0.0021	0.362	0.7188
\(\gamma _{8}\)	0.0366	0.0057	6.469	1.33e–08^∗∗∗
Residual standard error	0.0055 on 67 degrees of freedom
Multiple R-squared	0.9529
Adjusted R-squared	0.9459
F-statistic	135.6 on 10 and 67 DF	p-value	<2.2e–16

^∗∗∗, ^∗∗, and ^∗ indicate that the coefficients are significantly different from zero at the level of 1%, 5%, and 10%, respectively.