Priority of Unemployed Immigrants? A Causal Machine Learning Evaluation of Training in Belgium

Cockx, Bart; Lechner, Michael; Bollens, Joost

doi:10.2139/ssrn.3603832

Cited by 6 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bertrand, Crépon, Marguerie, & Premand, 2017;Davis & Heller, 2017;Strittmatter, 2018;Farbmacher, Heinrich, & Spindler, 2019;Gulyas & Pytka, 2019;Knittel, 2019) and to evaluations based on unconfoundedness in particular (e.g. Knaus, 2018;Jacob, Härdle, & Lessmann, 2019;Kreif & DiazOrdaz, 2019;Cockx, Lechner, & Bollens, 2020;Knaus, Lechner, & Strittmatter, 2020).…”

Section: Introductionmentioning

confidence: 99%

Double Machine Learning based Program Evaluation under Unconfoundedness

Knaus

2020

Preprint

View full text Add to dashboard Cite

This paper consolidates recent methodological developments based on DoubleMachine Learning (DML) with a focus on program evaluation under unconfoundedness. DML based methods leverage flexible prediction methods to control for confounding in the estimation of (i) standard average effects, (ii) different forms of heterogeneous effects, and (iii) optimal treatment assignment rules. We emphasize that these estimators build all on the same doubly robust score, which allows to utilize computational synergies. An evaluation of multiple programs of the Swiss Active Labor Market Policy shows how DML based methods enable a comprehensive policy analysis. However, we find evidence that estimates of individualized heterogeneous effects can become unstable.

show abstract

Section: Introductionmentioning

confidence: 99%

Double Machine Learning based Program Evaluation under Unconfoundedness

Knaus

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Most of the studies indicated that there was a positive impact due to the intervention on (re) employment, with one study indicating significance only in the short-term (Nivorozhkin and Nivorozhkin, 2007). Cockx et al (2019) presented a hierarchy of interventions and they found that some had lock-in effects; interventions with impact on employment only after a certain period (e.g. Hodzic et al , 2015).…”

Section: Resultsmentioning

confidence: 99%

“…Regarding direct employment outcomes, the results suggested that European programmes lead in terms of effectiveness. The study by Cockx et al (2019) conducted in Belgium showed that there was a significant improvement in (re) employment after a month for the vocational programmes, that education is a determinant in training effectiveness, and that proposing unemployment training that fosters individual gains can considerably enhance its effectiveness. Considering the social context model of youth transition regimes for European countries (Pohl and Walther, 2007), these findings partially correspond to the employment-centred type which Belgium belongs to.…”

Section: Discussionmentioning

confidence: 99%

Three decades of interventions for the unemployed – review of practices between 1990 and 2020 and their effects on (re) employment competencies

Celume¹,

Korda

2021

View full text Add to dashboard Cite

PurposeThis paper provides evidence of the outcomes proposed by the reviewed programmes and their level of effectiveness.Design/methodology/approachArticles were screened by title and abstract to ensure correspondence with exclusion/inclusion criteria. Themes were analysed through collective coding and scoring. Size effects were calculated.FindingsThree expected outcomes: psychological, technical and (re) employment. The most frequent and significant results are found in psychological. The review could not find consistent results in effectiveness of the type of training, because of the diversity of propositions and socio-cultural origins of interventions.Research limitations/implicationsSocio-cultural context acts as variable; thus, deep interdisciplinary analysis on context where trainings were developed is suggested in order to understand the impact of trainings according to their population defining effectiveness.Originality/valueThere is no previous review of type of interventions for the unemployed focusing on last 30 years.

show abstract

“…18-19) where they summarised the method as follows: (i) improves the splitting rule for individual trees; (ii) penalises splits that do not reduce selection bias; (iii) estimates group average treatment effects (GATEs) and individualised average treatment effects (IATEs) with low computational costs; (iv) suggests and performs unified inference for all aggregation levels; and (v) is applicable to a multiple, discrete treatment framework. The technical and practical details were described best by Lechner (2019), Cockx et al (2020) and the MCF-Tutorial (2022).…”

Section: Methodsmentioning

confidence: 99%

Wolves' contribution to structural change in grazing systems among swiss alpine summer farms: The evidence from causal random forest

Mink

Loginova

Mann

2023

J Agricultural Economics

View full text Add to dashboard Cite

The return of wolves to Swiss mountains and the damage they cause to sheep and goat herds in the region have raised concerns about a consequent wave of farm closures. In this paper, we examine the relationship between wolf attacks and the decline of Alpine summer farms, a specific high‐altitude farm type. We collected farm structure data and monitoring data on wolf attacks between 2004 and 2021 and analysed them using a causal random forest method, enabling a detailed analysis of the relation between wolf attacks and the number of different types of Alpine summer farms at a regional level. The results show that the farming systems are unaffected by incidental and infrequent wolf attacks, but that a high number of wolf attacks in a region is related to faster decrease in number of grazing systems where sheep are most vulnerable to such attacks. In contrast, systems that allow for better herd protection tend to show an increase in areas with frequent wolf attacks.

show abstract

Priority of Unemployed Immigrants? A Causal Machine Learning Evaluation of Training in Belgium

Cited by 6 publications

References 29 publications

Double Machine Learning based Program Evaluation under Unconfoundedness

Double Machine Learning based Program Evaluation under Unconfoundedness

Three decades of interventions for the unemployed – review of practices between 1990 and 2020 and their effects on (re) employment competencies

Wolves' contribution to structural change in grazing systems among swiss alpine summer farms: The evidence from causal random forest

Contact Info

Product

Resources

About