Assessing the employment effects of vocational training using a one-factor model

Abstract

Matching estimators use observed variables to adjust for differences between groups to eliminate sample selection bias. When minimum relevant information is not available, matching estimates are biased. If access to data on usually unobserved factors that determine the selection process is unavailable, other estimators should be used. This study advocates the one-factor control function estimator that allows for unobserved heterogeneity with factor-loading technique. Treatment effects of vocational training in Sweden are estimated with mean and distributional parameters, and then compared with matching estimates. The results indicate that unobservables slightly increase the treatment effect for those treated.

Acknowledgements

Useful comments from Arthur van Soest are acknowledged, and financial support from The Swedish Research Council. Thomas is also grateful for generous financial support from the Jan Wallanders and Tom Hedelius Foundation.

Notes

¹ Presented are the structure and rules of the system valid during 1993–1994, the period analysed by this study.

² Eriksson (1997) carried out an informal telephone interview with Swedish officials, and found that during the contact between the unemployed and the administrator, ambition and motivation of the unemployed were important for recruitment to a training programme. Åtgärdsundersökning (1998) interviewed individuals who participated in a programme in 1997. This survey showed that 60% of the participants took the initiative to participate in the training programme (i.e., by getting informed about different courses and programmes from ring binders, billboards, and/or computer terminals available at the unemployment office).

³ As many unemployment spells are short, a reasonable strategy for officials at labour market offices is to concentrate training offers to people with longer unemployment spells and others who can be assumed to have difficulties being employed without such efforts. Okeke (2001) reports an average waiting time before starting a training programme of three months.

⁴ When selecting into vocational training, two main decision-makers are involved, i.e. the programme administrator and the unemployed. The equation should be seen as a measure for the combined effort of the two with respect to the involved variables, since several decisions easily may be represented by only one index.

⁵ Gauss–Hermite quadrature is used to evaluate the integrals in the model, using five evaluation points. Points and nodes are taken from Judd (1998).

⁶ The first mass-point is defined as P ₁ = exp(a)/(1 − exp(a)), where a is estimated. In order to receive the mass-point, the formula has to applied.

⁷ Note that ATE(X, Z) does not depend on Z, so that ATE(X, Z) = ATE(X). It was chosen to include Z to emphasize that the estimated values of β₁, β₀, ρ₁, and ρ₀ depend on Z, because the selection equation is estimated jointly with the two outcome equations.

⁸ . By Bayes’ rule, , which is used in Equation 6.

⁹ See Heckman (1997), Heckman and Smith (1998), and Heckman et al. (2000).

¹⁰ Assume that an individual has a wage rate of 50 SEK per hour. With an annual income of 40 000 SEK, he or she would be working 800 hours per year, which roughly corresponds to 5 months of full-time work. If instead the wage rate were 100 SEK per hour, the corresponding figure would be 2.5 months of full-time work. It is believed that the true number of full-time equivalence lies somewhere in between these two numbers. In May 2004, 100 SEK = 10.74 EUR.

¹¹ Pseudo R ² is a goodness of fit measure defined as 1 − 1/[1  +  2(logL ₁ − logL ₀)/N], with N being the number of observations used in the estimation. The measure is based on a model estimated only with the factors of the models, because there are no ordinary constants included in the model.

¹² The statistical significance refers to a significance level of 10% or better. This is applied throughout the paper, unless otherwise stated.

¹³ Non-trainees have lower values of U_D , which corresponds to a lower probability to participate in training. Since σ_{0 D} is negative, it follows that they have higher values of U ₀, which corresponds to an increased employment probability compared to what the employment probability would have been if the selection were random.

¹⁴ Edin and Åslund (2001) describe the labour market situation in Sweden for foreign-born, and find that the immigrants as a group have a weak position in the labour market, especially since large groups came to Sweden as refugees during the 1990s.

¹⁵ See Calmfors et al. (2002) for a survey of the evaluation of active labour market programmes in Sweden.

¹⁶ The matching estimator used in the study is the average nearest neighbour estimator, using one neighbour. When estimating the propensity score used in the matching procedure, a parametric probit is used. The choice of variables in the probit model is the same as in the factor model for comparability reasons. Both the balancing score and match of propensity distribution are fulfilled. More details with estimates and statistics about the matching procedure may be received from the authors on request.