I have cross-sectional data for individuals, $i$, and years, $t$. I need to estimate the density of a random variable, $X_{it}$, which is equal to
$X_{it} = A_{it}/B_t$.
My data is truncated in the sense that I only observe $X_{it}$ if $X_{it} >= \frac{1}{B_{t}}$, i.e. $A_{it} >= 1$. What is the best way to non-parametrically estimate the density of $X_{it}$?
