FDI and onshore task composition: evidence from German firms with affiliates in the Czech Republic

Journal for Labour Market Research

Table 4 Post-lasso logit results for occupational groups

Dep. variable: FDI in 2 years	Post-lasso logit
	Manufacturing	Services
	(1)	(2)
Production occupations
Unskilled manual	–	0.843**
Skilled manual	− 1.044***	− 0.917**
Technicians	− 0.290	0.892**
Engineers	0.232	0.985**
Service occupations
Unskilled services	− 0.589	− 0.152
Skilled services	− 5.545*	− 1.283
Semiprofessionals	− 2.580	1.019
Professionals	0.565	0.965
Administrative occupations
Unskilled commercial and admin.	− 2.068***	–
Skilled commercial and admin.	1.742***	1.604***
Managers	2.171***	0.970**
Nonpenalized in lasso
Log # establishments	0.488***	0.212***
Employment growth	0.0734*	0.172***
Share of women	0.625**	− 0.353*
Log wage bill	0.0157	0.584***
Mean wage growth	0.0432	0.0757*
Log # employees	Yes	Yes
Region fixed effects	Yes	Yes
Industry fixed effects	Yes	Yes
Year fixed effects	Yes	Yes
Observations	57,532	51,519
log \(\lambda\) of min. MSPE	1.71	0.58

This table reports the estimates from a post-lasso logit model. The set of included occupational shares is selected by cross-validating the findings of the model with the lowest MSPE. The covariate employment size and the industry fixed effects control for the stratification of the sample of non-MNEs. Standard errors are clustered at the treatment level, i.e., the firm level, following Abadie et al. (2017)
*\(p<0.1\), **\(p<0.05\), and ***\(p<0.01\)