This paper develops a mathematical model to study the evolutionary changes in restriction sites within mitochondrial DNA (mtDNA) and proposes a measure called "nucleotide diversity" to quantify polymorphism at the nucleotide level. The authors assume that restriction sites can be mapped and that the number of shared sites between two organisms can be used to estimate the number of nucleotide substitutions. They derive formulas for estimating the number of nucleotide substitutions between two populations or species, considering both the original and new restriction sites. The paper also discusses the statistical properties of these estimators and their application to real data. Additionally, it explores the relationship between the proportion of shared DNA fragments and the number of nucleotide substitutions, providing a method to estimate the latter from the former. The authors conduct a computer simulation to validate their theoretical findings and discuss the implications of intrapopulation variation on the estimation of interpopulation differences. The study highlights the importance of using multiple restriction enzymes and the potential impact of mutation rates on the accuracy of estimates.This paper develops a mathematical model to study the evolutionary changes in restriction sites within mitochondrial DNA (mtDNA) and proposes a measure called "nucleotide diversity" to quantify polymorphism at the nucleotide level. The authors assume that restriction sites can be mapped and that the number of shared sites between two organisms can be used to estimate the number of nucleotide substitutions. They derive formulas for estimating the number of nucleotide substitutions between two populations or species, considering both the original and new restriction sites. The paper also discusses the statistical properties of these estimators and their application to real data. Additionally, it explores the relationship between the proportion of shared DNA fragments and the number of nucleotide substitutions, providing a method to estimate the latter from the former. The authors conduct a computer simulation to validate their theoretical findings and discuss the implications of intrapopulation variation on the estimation of interpopulation differences. The study highlights the importance of using multiple restriction enzymes and the potential impact of mutation rates on the accuracy of estimates.