ABSTRACT
Parametric and nonparametric functional mapping can be viewed as alternative to each other in terms of their statistical applications, biological relevance and computational efficiency. While the parametric approach is biologically sensible, the nonparametric approach displays tremendous flexibility and computational advantage. For this reason, both approaches should be able to find their applications in practical data analysis, depending on the biological and statistical features of a particular data set. For some biological processes, there are multiple different phases of development in each of which a variety of genetic and environmental factors play a role through their interactions, leading to changes in the dynamic pattern of development and response. For these processes, a single parametric or nonparametric model may not be adequate. Very often, a combined model that takes advantage of each approach is capable of discerning the differences between developmental phases, and therefore provides a powerful way for gene identification and haplotyping. Such a combined approach is called the semiparametric modeling of functional mapping.
