In a cross section of OECD countries we replace the macroeconomic production function by a production possibility frontier, TFP being the composite effect of efficiency scores and possibility frontier changes. We consider, for the periods 1970, 1980, 1990, 2000, one output: GDP per worker; three inputs: human capital, public physical capital per worker and private physical capital per worker. We use a semiparametric analysis, computing Malmquist productivity indexes, and we also resort to stochastic frontier analysis. Results show that private capital is important for growth, although public and human capital also contribute positively. A governance indicator, a non-discretionary input, explains inefficiency. Better governance helps countries to achieve a better performance. Non-parametric and parametric results coincide rather closely on the countries movements vis-à-vis the possibility frontier, and on their relative distances to the frontier.