Matched-pair analysis based on business survey data to evaluate the policy of supporting the adoption of advanced manufacturing technologies by Swiss firms

We apply different matched-pair methods to evaluate the policy of sustaining the adoption of advanced manufacturing technologies by Swiss firms and we compare it in decomposing the selection bias. In this aim we present the evaluation problem, the decomposition of the selection bias and the estimation techniques used. We base our study on the J. Heckman and al. (1998)'s paper. The empirical results show that the matched-pair method proposed by J. Heckman and al. (1998) is not necessarily better than the alternative methods usually used. The multiple imputations technique, which we propose too, appears to be remarkably good. The impact of the policy of sustaining the new technologies is weak.