Skip to main content

Table 8 Robustness checks: Heckman two-step estimation

From: The effect of overseas investors on local market efficiency: evidence from the Shanghai/Shenzhen–Hong Kong Stock Connect

 

(1)

(2)

(3)

HSSC

DailySprd1

DailySprd2

HSSC

 

0.0017***

0.0015***

  

(8.63)

(8.53)

Size

0.7458***

0.0026***

0.0022***

 

(18.84)

(12.93)

(11.79)

Lev

 − 1.1979***

 − 0.0064***

 − 0.0055***

 

(− 7.77)

(− 11.43)

(− 10.69)

ROA

2.0450***

0.0064***

0.0050***

 

(4.03)

(3.18)

(2.77)

Cash_vol

 − 0.0428*

 − 0.0003***

 − 0.0002***

 

(− 1.68)

(− 3.10)

(− 2.87)

Loss

0.0850

0.0008**

0.0007**

 

(1.03)

(2.56)

(2.47)

Age

0.2633***

0.0006***

0.0005***

 

(7.00)

(4.19)

(3.53)

Opinion

0.0357

 − 0.0000

 − 0.0001

 

(0.27)

(− 0.03)

(− 0.31)

Analyst

0.1250***

 − 0.0011***

 − 0.0012***

 

(5.36)

(− 11.83)

(− 13.62)

Turnover

0.0084

 − 0.0008***

 − 0.0007***

 

(1.61)

(− 37.70)

(− 37.97)

IMR

 

0.0001

 − 0.0002

  

(0.28)

(− 0.66)

_cons

 − 23.6797***

 − 0.0944***

 − 0.0793***

 

(− 29.54)

(− 15.25)

(− 14.04)

Industry

Yes

Yes

Yes

Year

Yes

Yes

Yes

N

10,511

10,511

10,511

adj. R2

0.404

0.801

0.803

  1. To ensure that our regression model fits the data and to overcome potential sample selection bias, we conduct the Heckman two-step estimation. In the first step, we add relevant variables in the equations that could affect the selection of underlying stocks eligible for trading under the Stock Connect programs. Consistently, we incorporate a set of control variables—firm size, profitability (ROA and Loss), leverage, audit opinion, listage, analyst coverage, cash flows volatility, and share turnover. We also control for year and industry fixed effects. In the second step, the outcome equation is estimated by ordinary least squares (OLS), in which the outcome equation includes both the explanatory variables and the constructed value of the inverse Mills ratio
  2. ***, **, and * denote significance at the 1%, 5%, and 10% level, respectively