Testing the Order of Markov Dependence in DNA Sequences |
| |
Authors: | M L Menéndez L Pardo M C Pardo K Zografos |
| |
Institution: | (2) University of Amsterdam, Amsterdam, The Netherlands;; |
| |
Abstract: | DNA or protein sequences are usually modeled as probabilistic phenomena. The simplest model is created on the assumption that
the nucleotides at the various sites are independently distributed. Usually the type of nucleotide at some site depends on
the type at another site and therefore the DNA sequence is modeled as a Markov chain of random variables taking on the values
A, G, C and T corresponding to the four nucleotides. First order or higher order Markov models provide better fit to a DNA
sequence. Based on this remark, the aim of this paper is to present and study a family of test statistics for testing order
Markov dependence in DNA sequences. This new family includes as a particular case the classical likelihood ratio test. A simulation
study is presented in order to find test statistics, in this family, with a better behaviour than the likelihood ratio test. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|