• Identification of structural VAR models via Independent Component Analysis: a performance evaluation study (with A. Moneta). Journal of Economic Dynamics and Control (2022).

    • Link Publication
    • Working Paper
    • View Abstract Independent Component Analysis (ICA) is a statistical method that linearly transforms a random vector. Under the assumption that the observed data are mixtures of non-Gaussian and independent processes, ICA is able to recover the underlying components, but with a scale and order indeterminacy. Its application to structural vector autoregressive (SVAR) models allows the researcher to recover the impact of independent structural shocks on the observed series from estimated residuals. We analyze different ICA estimators, recently proposed within the field of SVAR analysis, and compare their performance in recovering structural coefficients. Moreover, we assess the size distortions of the estimators in hypothesis testing. We conduct our analysis by focusing on non-Gaussian distributional scenarios that get gradually close to the Gaussian case. The latter is the case where ICA methods fail to recover the independent components. Although the ICA estimators that we analyze show similar pattern of performance, two of them — the fastICA algorithm and the pseudo-maximum likelihood estimator — tend to perform relatively better in terms of variability, stability across sub- and super-Gaussian settings, and size distortion. We finally present an empirical illustration using US data to identify the effects of government spending and tax cuts on economic activity, thus providing an example where ICA techniques can be used for hypothesis testing.

Working Papers

  • Does public R&D funding crowd-in private R&D investment? Evidence from military R&D expenditures for US states (with E. Russo, A. Roventini). Revise & Resubmit at Research Policy.

    • Working Paper
    • View Abstract Military Research and Development (R&D) expenditures arguably represent one of the main innovation policy levers for US policy makers. They are sizeable, with a clear-cut public purpose (national defense) and with the government being their exclusive buyer. Exploiting a longitudinal dataset linking public R&D obligations to private R&D expenditures for US states, we investigate the impact of defense R&D on privately-financed R&D. To address potential endogeneity in the allocation of funds, we use an instrumental variable identification strategy leveraging the differential exposure of US states to national shocks in federal military R&D. We document considerable "crowding-in" effects with elasticities in the 0.11-0.14 range. These positive effects extend also to the labor market, when focusing on employment in selected R&D in- tensive industries and especially for engineers.
  • Calibration and Validation of Macroeconomic Simulation Models: A General Protocol by Causal Search (with M. Martinoli, A. Moneta). Under Review .

    • Working Paper
    • View Abstract We propose a general protocol for calibration and validation of complex simulation models by an approach based on discovery and comparison of causal structures. The key idea is that configurations of parameters of a given theoretical model are selected by minimizing a distance index between two structural models: one estimated from the data generated by the theoretical model, another estimated from a set of observed data. Validation is conceived as a measure of matching between the theoretical and the empirical causal structure. Causal structures are identified combining structural vector autoregressive and independent component analysis, so as to avoid a priori re- strictions. We use model confidence set as a tool to measure the uncertainty associated to the alternative configurations of parameters and causal structures. We illustrate the procedure by applying it to a large-scale macroeconomic agent-based model, namely the “dystopian Schumpeter-meeting-Keynes” model