Table 14 Logit marginal effects on the probability of social sciences or humanities final major conditional on social sciences or humanities not being the initial major

From: What happens after enrollment? An analysis of the time path of racial differences in GPA and major choice

	Specification
	(1)	(2)	(3)	(4)
No Initial Major	0.393^***	0.395^***	0.385^***	0.389^***
	(0.039)	(0.039)	(0.040)	(0.041)
Female	0.219^***	0.203^***	0.217^***	0.233^***
	(0.042)	(0.043)	(0.043)	(0.044)
Black	0.175^***	0.056	0.017	-0.021
	(0.062)	(0.072)	(0.074)	(0.071)
Hispanic	0.126^**	0.070	0.103	0.079
	(0.058)	(0.061)	(0.066)	(0.066)
Asian	-0.161^***	-0.136 ^***	-0.094^*	-0.100^*
	(0.048)	(0.050)	(0.054)	(0.054)
SAT Score		-0.102^***	-0.063^**	-0.029
		(0.029)	(0.031)	(0.032)
Duke Achievement			-0.156^***	-0.087
			(0.055)	(0.057)
Duke Curriculum			-0.158^***	-0.134^**
			(0.052)	(0.053)
Duke Essay			-0.038	-0.047
			(0.048)	(0.050)
Duke Recommendation			0.017	0.054
			(0.048)	(0.048)
Duke Personal Qualities			0.025	0.019
			(0.048)	(0.049)
Year 1 Student Effect				-0.121^***
				(0.027)
Log likelihood	-452.8	-442.6	-430	-417.5
Observations	822

Note: See Table 1 for a description of the Duke admission's office variables. Standard errors in parentheses. *, ** and *** indicate that the coefficient is significant at 10%, 5% and 1% respectively. “Year 1 Student Effect” refers to the first period student effect (α_{i
1}) from the grades analysis in subsection Class rank adjusted for selection “No Initial Major” denotes students that reported “do not know” as initial major. SAT score was normed toN (0,1).

Back to article page