The impact of sectoral minimum wage laws on employment, wages, and hours of work in South Africa

IZA Journal of Labor & Development

Table 5 Probability of employment by sector (Dependent variable = Pr (Employment))

Sector	Retail		Domestic		Forestry		Taxi		Security
Sector	I	II	I	II	I	II	I	II	I	II
Post	0.0038^**	0.0038^**	0.0066^***	0.0061^***	−0.0005	0.0003	−0.0030^***	−0.0030^***	0.0039^***	0.0026^**
Post	(0.0017)	(0.0018)	(0.0022)	(0.0022)	(0.0009)	(0.0007)	(0.0004)	(0.0004)	(0.0012)	(0.0011)
Wage gap	−0.0001		−0.0126^***		0.0058^**		−0.00001		−0.0034^*
Wage gap	(0.0018)		(0.0045)		(0.0026)		(0.0001)		(0.0017)
Wage gap*Post	−0.0002	−0.0003	−0.0005	−0.0004	−0.0001	−0.0004	0.00005	0.00004	0.0001	0.0002
Wage gap*Post	(0.0015)	(0.0015)	(0.0017)	(0.0017)	(0.0008)	(0.0007)	(0.0001)	(0.00005)	(0.0009)	(0.0009)
Individual controls included	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes
District controls included	No	Yes	No	Yes	No	Yes	No	Yes	No	Yes
Constant	0.0231^***	0.0327^***	0.0192^**	−0.0003	0.0006	0.0222^***	0.0059^***	0.0033^***	0.0293^***	−0.0047
Constant	(0.0064)	(0.0062)	(0.0086)	(0.0066)	(0.0011)	(0.0057)	(0.0007)	(0.0009)	(0.0032)	(0.0036)
Observations	493,809	493,809	493,809	493,809	267,108	267,108	455,266	455,266	464,046	464,046
Number of districts	52	52	52	52	30	30	45	45	46	46
R-squared	0.0130	0.0150	0.0970	0.1040	0.0040	0.0180	0.0040	0.0050	0.0100	0.0160
F-statistic	193.75^***	162.68^***	124^***	167.85^***	2.51^**	2.41^*	26.36^***	51.9^***	43.76^***	52.59^***

Source: Data are from South African Labour Force Surveys (LFS) conducted by Statistics South Africa (15 waves September 2000 to September 2007).
Notes: Dependent variable is a dummy variable equal to 1 if the individual is employed in the respective sector and equal to 0 otherwise. The sample includes individuals of working age who are employed or seeking work, and who have completed no more than 12 years of schooling (Matric). Robust standard errors clustered by district council are shown in parentheses.^***p < 0.01, ^** p < 0.05, ^* p < 0.1. Individual controls include controls for race, years of schooling and gender. The wage gap measures the proportional increase in the real wages of workers in district council i at time t-1 necessary to meet the minimum wage at time t. The F-statistic refers to the test for the null hypothesis that the regression coefficients are equal to zero, which is rejected at the 1, 5 and 10 percent levels.