Table 14. Gender effects in selection...

Table 14.

Gender effects in selection (logistic regression)

	Phase I			Phase II
	(1)	(2)	(3)	(4)	(5)	(6)
PI gender	0.05 (0.13)	0.25 (0.19)	0.02 (0.19)	−0.11 (0.30)	−1.23** (0.46)	0.39 (0.58)
History		−0.01 (0.01)			−0.03* (0.02)
PI gender $\times$ history		−0.02 (0.01)			0.11*** (0.03)
PI applications			−0.01 (0.02)			0.02 (0.09)
PI gender $\times$ applications			0.02 (0.04)			−0.35 (0.37)
Year fixed effects	Yes	Yes	Yes	Yes	Yes	Yes
Controls	Yes	Yes	Yes	Yes	Yes	Yes
Observations	8097	8097	8097	1657	1657	1657
PIs	3501	3501	3501	1118	1118	1118
Tjur D	0.41	0.41	0.40	0.28	0.28	0.28

	Phase I			Phase II
	(1)	(2)	(3)	(4)	(5)	(6)
PI gender	0.05 (0.13)	0.25 (0.19)	0.02 (0.19)	−0.11 (0.30)	−1.23** (0.46)	0.39 (0.58)
History		−0.01 (0.01)			−0.03* (0.02)
PI gender $\times$ history		−0.02 (0.01)			0.11*** (0.03)
PI applications			−0.01 (0.02)			0.02 (0.09)
PI gender $\times$ applications			0.02 (0.04)			−0.35 (0.37)
Year fixed effects	Yes	Yes	Yes	Yes	Yes	Yes
Controls	Yes	Yes	Yes	Yes	Yes	Yes
Observations	8097	8097	8097	1657	1657	1657
PIs	3501	3501	3501	1118	1118	1118
Tjur D	0.41	0.41	0.40	0.28	0.28	0.28

Note(s):

***p < 0.01; **p < 0.05; *p < 0.1. Selection outcomes are estimated with logistic regressions. Data are drawn from NASA SBIR/STTR proposal database from 2009–2016. Observations with male PIs are weighted by an entropy balancing algorithm. Controls include patents, headcount, reviewing Center, and the Technical Score. History indicates the number of years since the proposing firm’s first award from the NASA SBIR/STTR programs. Applications indicate the number of proposals by the PI in the proposal database. Standard errors are estimated by clustering by PI. The figure of merit is Tjur’s Coefficient of Discrimination D

[ViewLarge]

Sharing Unavailable