From Temporary Help Jobs to Permanent Employment: What Can We Learn from Matching Estimators and Their Sensitivity?

By Andrea Ichino, Fabrizia Mealli, T. Nannicini. Social Science Research Network, 2008

707 citations recorded by the source corpus.

The diffusion of Temporary Work Agency (TWA) jobs originated a harsh policy debate and ambiguous empirical evidence. Results for the US, based on quasi-experimental evidence, suggest that a TWA assignment decreases the probability of finding a stable job, while results for Europe, based on the Conditional Independence Assumption (CIA), typically reach opposite conclusions. Using data for two Italian regions, we use a matching estimator to show that TWA assignments can be an effective springboard to permanent employment. We also propose a simulation-based sensitivity analysis, which highlights that only for one of these two regions our results are robust to specific failures of the CIA. We conclude that European studies based on the CIA should not be automatically discarded, but should be put under the scrutiny of a sensitivity analysis like the one we propose.

Subfields: Economics and Econometrics

View Paper: https://www.semanticscholar.org/paper/9599f449ca5f1d3d581cceebe1fe790c0ee1bc4a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

Citations in the corpus

The Impact of Dual Enrollment on College Degree Attainment (2013, methodology): “Recall that the propensity score model assumes that Y1 and Y2 are independent of D given Pr(Z), which researchers sometime refer to as the conditional independence assumption (CIA).”
Trade, Standards, and Poverty: Evidence from Senegal (2009, methodology): “We use the method with a neutral confounder and with confounders calibrated to mimic observable binary covariates as in Ichino et al. (2006).”
This Time It's Different? Youth Labour Markets during ‘The Great Recession’ (2012, neutral): “In Italy, several studies (for example, Ichino et al., 2005, 2008 and Barbieri and Sestito, 2008) have found a weak positive effect of temporary employment on the chances of finding permanent employment, although Gagliarducci (2005) finds that the intermittence of work experience associated with…”
The Employment Effects of Job Creation Schemes in Germany: A Microeconometric Evaluation (2008, neutral): “We have already mentioned one approach by Lechner (2001) which allows the researcher to check the sensitivity due to failure of the common support.”
Some Practical Guidance for the Implementation of Propensity Score Matching (2008, methodology): “A different approach was recently proposed by Ichino et al. (2006).”
The WTO trade effect (2011, methodology): “Ichino et al. (2008) suggested an alternative, simulation-based, approachof sensitivity analysis formatching estimators.”
The effectiveness of the US endangered species act: An econometric analysis using matching methods (2007, methodology): “[15]), we use Rosenbaum bounds because they are relatively free of parametric assumptions and because the test provides a single, easily interpretable measure of the way in which unobservables enter.”
Contract-farming in Staple Food Chains: The Case of Rice in Benin (2017, methodology): “The method aims at assessing the sensitivity of the treatment effect estimates by calculating ATE estimates under different possible departures from the CIA.”
Unobservable, but unimportant? The relevance of usually unobserved variables for the evaluation of labor market policies☆ (2017, methodology): “Imbens (2003) and Ichino et al. (2008) have proposed methods to assess the sensitivity of unconfoundedness-based estimators to the presence of unobserved variables.”
The Community College Route to the Bachelor’s Degree (2015, methodology): “For our sensitivity tests, we rely on a method devised by Ichino, Mealli, and Nannicini (2008).”
Life satisfaction and self-employment: a matching approach (2010, methodology): “Unless there is substantial overlap in the two covariate distributions, multivariate regression estimates rely heavily on extrapolation, and can therefore be misleading (Imbens, 2004; Ichino et al., 2008, p. 312-13).”