What Goliaths and Davids among Swiss firms tell us about expected returns on Swiss asset markets

Swiss Journal of Economics and Statistics

Table 4 In-sample predictability of Swiss stock market and bond market excess returns using GVD or its components

Panel A: Predictability of stock market excess returns
	h=1		h=3		h=6		h=12
Predictor	\(\hat {\beta }\)	R²(%)	\(\hat {\beta }\)	R²(%)	\(\hat {\beta }\)	R²(%)	\(\hat {\beta }\)	R²(%)
GVD	0.50**	1.61	0.48**	3.46	0.59**	8.72	0.57**	13.88
(p value)	(0.03)		(0.02)		(0.02)		(0.02)
GVD^new	0.55**	1.92	0.60**	5.33	0.61***	9.44	0.55**	12.93
(p value)	(0.03)		(0.02)		(0.00)		(0.01)
GVD^old	– 0.34	0.72	– 0.18	0.49	– 0.05	0.06	0.14	0.85
(p value)	(0.84)		(0.73)		(0.53)		(0.37)
Panel B: Predictability of bond market excess returns
Predictor	\(\hat {\beta }\)	R²(%)	\(\hat {\beta }\)	R²(%)	\(\hat {\beta }\)	R²(%)	\(\hat {\beta }\)	R²(%)
GVD	0.02	0.05	0.03	0.35	0.04	0.88	0.04	1.56
(p value)	(0.39)		(0.33)		(0.32)		(0.35)
GVD^new	– 0.02	0.07	– 0.01	0.05	0.02	0.29	0.03	0.71
(p value)	(0.67)		(0.57)		(0.38)		(0.36)
GVD^old	0.12**	1.68	0.07	1.63	0.03	0.38	0.01	0.22
(p value)	(0.01)		(0.14)		(0.35)		(0.41)

Notes: This table presents OLS estimates from univariate regressions of h-month ahead Swiss stock (panel A) and bond market (panel B) returns on GVD or one of its components (see Table 1 for a description of the variables). All variables are z-standardized. The sample period runs from January 1999 to December 2017. We compute heteroskedasticity and autocorrelation robust p values (in parentheses below the estimates) from a wild bootstrap procedure that tests the null hypothesis of \(\hat {\beta }^{h}=0\) against the alternative that \(\hat {\beta }^{h}>0\) because the regressors are defined in such a way that high values predict high excess returns. *, **, and *** indicate significance at the 10%, 5%, and 1% level, respectively