Financial Innovation

Table 6 In-sample probit regression

From: Return direction forecasting: a conditional autoregressive shape model with beta density

Cons.	\(r_{t-1}\)	\(bm_{t-1}\)	\(tbl_{t-1}\)	\(ntis_{t-1}\)	\(infl_{t-1}\)	\(ltr_{t-1}\)	\(svar_{t-1}\)	\(tms_{t-1}\)	\(dfy_{t-1}\)	\(dp_{t-1}\)	\(dy_{t-1}\)	\(ep_{t-1}\)	\(de_{t-1}\)	\(R^2\)(%)
\(\underset{(0.038)}{0.236^{***}}\)	\(\underset{(0.709)}{ 1.147}\)													0.18
\(\underset{(0.090)}{0.360^{***}}\)	\(\underset{(0.710)}{1.047}\)	\(\underset{(0.143)}{-0.219}\)												0.33
\(\underset{(0.057)}{0.310^{***}}\)	\(\underset{(0.710)}{1.149}\)		\(\underset{(1.231)}{-2.174^{*}}\)											0.39
\(\underset{(0.045)}{0.272^{***}}\)	\(\underset{(0.711)}{1.069}\)			\(\underset{(1.499)}{-2.195}\)										0.32
\(\underset{(0.043)}{0.285^{***}}\)	\(\underset{(0.710)}{1.198^{*}}\)				\(\underset{(7.437)}{-19.737^{***}}\)									0.66
\(\underset{(0.039)}{0.231^{***}}\)	\(\underset{(0.710)}{1.110}\)					\(\underset{(1.558)}{1.081}\)								0.21
\(\underset{(0.044)}{0.272^{***}}\)	\(\underset{(0.733)}{0.824}\)						\(\underset{(7.098)}{-12.109^{*}}\)							0.38
\(\underset{(0.061)}{0.214^{***}}\)	\(\underset{(0.709)}{1.148}\)							\(\underset{(2.837)}{1.311}\)						0.19
\(\underset{(0.073)}{0.303^{***}}\)	\(\underset{(0.709)}{1.094}\)								\(\underset{(5.546)}{-5.937}\)					0.25
\(\underset{(0.281)}{0.055}\)	\(\underset{(0.712)}{1.098}\)									\(\underset{(0.082)}{-0.054}\)				0.20
\(\underset{(0.281)}{0.056}\)	\(\underset{(0.708)}{1.151}\)										\(\underset{(0.082)}{-0.053}\)			0.20
\(\underset{(0.255)}{0.230}\)	\(\underset{(0.710)}{1.146}\)											\(\underset{(0.092)}{-0.002}\)		0.18
\(\underset{(0.084)}{0.170}\)	\(\underset{(0.709)}{1.109}\)												\(\underset{(0.116)}{-0.103}\)	0.23

[1] Numbers in the brackets are standard errors
[2] We use \(^{***}\), \(^{**}\) and \(^{*}\) to represent significance at 10%, 5%, and 1%, respectively

Back to article page