The regional impact of cultural diversity on wages: evidence from Australia

Table 5 Instrumental variable estimation showing the impact of diversity on wages. Dependent variable: log of weekly wages

Explanatory variables	Whole sample
	IV-OLS		IV-fixed effects
	(1)	(2)	(3)	(4)
Diversity index	0.625***		0.203
	(0.074)		(0.168)
Share of foreigners		0.693***		0.159
		(0.084)		(0.123)
Demographic controls	Yes	Yes	Yes	Yes
Human capital controls	Yes	Yes	Yes	Yes
Time dummies^a	Yes	Yes	Yes	Yes
Individual effects	No	No	Yes	Yes
Observations	20,156	19,795	19,706	19,335
R-squared	0.565	0.581	0.347	0.359
First stage for diversity index
Predicted diversity index	0.614***		0.245***
	(0.016)		(0.030)
First stage for share of foreigners
Predicted share of foreigners		0.835***		0.594***
		(0.021)		(0.039)
Instrument tests
Underidentification test^b	622.98	626.47	52.32	140.65
p value	0.000	0.000	0.000	0.000
Weak identification test^c	1454.11	1637.39	66.10	229.06

Values are estimated for the HILDA wave 4–11 respondents aged 16–45 years. Robust standard errors are in parentheses and are adjusted for clusters by individuals. The reported sample sizes differ from the original (n = 44,634) due to sample weighting and lagging. Demographic controls include age and age-squared in all models, plus gender and marital status in the OLS models. Human capital controls include education, weekly hours worked, and job tenure, in all models, plus English language skill in OLS
Significance values indicate *p < 0.1; **p < 0.05; ***p < 0.01
^aTime dummies are partialled out in the FE models
^bBased on the Kleibergen-Paap rk LM statistic
^cBased on the Kleibergen-Paap rk Wald F statistic: Stock-Yogo weak ID test critical value maximal IV sizes range as follows: 16.38 (10 %), 8.96 (15 %), 6.66 (20 %), and 5.53 (25 %)