Semiparametric varying parameter panel data models: An application po estimation of speed of convergence

In this paper we propose a semiparametric model for studying a general regr ession relationship with varying coefficients. We then develop a local line ar instrumental variable method with a kernel weight function to estimate t he smooth varying coefficient function. The consistency and asymptotic norm ality are established. An application of the proposed method is presented w ith an estimation of the speed of convergence of a panel of cross-countries per capita output.