Attention to social stratification in the public discourse: An empirical study based on big data of books (1949–2008)

The Journal of Chinese Sociology

Table 3 Results of conditional Granger causality test (1978–2008)

Null hypothesis	N	Chi²	p value
\(fd\_GDP_{cp}\) is not the Granger cause of \(fd\_LC\)	31	11.382**	0.023
\(fd\_GINI\) is not the Granger cause of \(fd\_LC\)	31	34.596***	0.000
\(fd\_PDI\) is not the Granger cause of \(fd\_LC\)	31	26.347***	0.000
\(fd\_IO\,{\text{is}}\,{\text{not}}\,{\text{the}}\,{\text{Granger}}\,{\text{cause}}\,{\text{of}}\,{ }fd\_LC\)	31	1.790	0.774
\(fd\_LC\,{\text{is}}\,{\text{not}}\,{\text{the}}\,{\text{Granger}}\,{\text{cause}}\,{\text{of}}\,{ }fd\_GDP_{cp}\)	31	36.731***	0.000
\(fd\_LC\) is not the Granger cause of \(fd\_GINI\)	31	20.26***	0.000
\(fd\_LC\) is not the Granger cause of \(fd\_PDI\)	31	41.042***	0.000
\(fd\_LC\) is not the Granger cause of \(fd\_IO\)	31	13.182***	0.000

(1) “fd” means first difference. (2) According to the information criteria AIC, SBIC, and HQIC, we select a four-order lag. (3) *p < 0.1, **p < 0.05, ***p < 0.01