In this paper, we consider expectations of the form E[log(y)|x] = a'log(x) as a good starting point for a more general analysis. We show why this naturally leads to the following flexible functional form E[y|x]= f(h(x)), where all functions are estimated by cubic splines. One of the main goals...

Almost all economic data sets are discretized or rounded to some extent. This paper proposes a regression and a density estimator that work especially well when the data is very discrete. The estimators are a weighted average of the data, and the weights are composed of cubic B-splines. Unlike...