Parzen Windows(wiki) is a non-parametric density estimation method given samples. Though the name sounds scary (it was, at least to me), it’s not that complicated algorithm. It just considers samples near x for computing p(x). For example, to compute p(x=1), it considers samples near it, e.g., 0, 3, 4 while it ignores samples far from 1 like 1000 and -1000.

http://www.personal.rdg.ac.uk/~sis01xh/teaching/CY2D2/Pattern2.pdf is really well written easy to understand doc on it.