The effect of careers guidance for employed adults on continuing education: assessing the importance of attitudinal information

Summary. The validity of the matching estimator in programme evaluation depends on the completeness of the set of variables that are used for matching. When an attitudinal variable is relevant for the decision about participation, but is either unmeasured or measured only after entry to the programme, estimates of effects may be biased or difficult to interpret. This issue was investigated with data from an evaluation study of careers guidance for employed adults which utilized the method of propensity score matching. Job satisfaction, measured shortly after entry to the programme, was found to be strongly associated with participation but might itself have been influenced by the early experience of careers guidance. Estimates of the effects of guidance were considered both including and excluding the job satisfaction measure from the participation model. Data experiments with adjusted values of job satisfaction were also performed. The results illustrate that omitted attitudinal information poses a particular difficulty for the matching estimator.