Table 5 Results based on propensity score matching, entropy balancing, and coarsened exact matching methods.

From: Change starts within: does managerial ability matter to green innovation?

Variable

Panel A: PSM method

Panel B: Entropy balancing method

Panel C: Coarsened exact matching

(1)

(2)

(3)

(4)

(5)

(6)

y = GP

y = GIP

y = GP

y = GIP

y = GP

y = GIP

MA

3.713*

3.897***

4.311***

3.332***

0.575**

0.618***

 

(1.782)

(2.625)

(2.728)

(3.104)

(2.233)

(3.864)

Controls

Yes

Yes

Yes

Yes

Yes

Yes

Intercept

−22.766

−18.813

−54.675*

−38.210**

−89.094**

−57.930**

 

(−0.793)

(−0.748)

(−1.883)

(−2.120)

(−2.411)

(−2.524)

Firm FE

Yes

Yes

Yes

Yes

Yes

Yes

Year FE

Yes

Yes

Yes

Yes

Yes

Yes

N

3692

3692

15,457

15,457

15,392

15,392

Adj./Pseudo-R2

0.658

0.651

0.615

0.586

0.651

0.628

  1. Estimates are based on OLS regressions with standard errors adjusted for heteroscedasticity and clustered at the listed company level. Numbers reported are regression coefficients with z(t)-statistics in parentheses in the first (second) stage regressions. *, **, and *** indicate statistical significance at the 10%, 5%, and 1% levels, respectively, based on two-tailed tests. All continuous variables are winsorized at the 1st and 99th percentiles. Variable definitions are presented in Appendix A.
Back to article page