The chapter discusses the measurement of diversity in populations, focusing on two measures: Yule's 'characteristic' and Fisher's 'index of diversity.' These measures are defined as statistics derived from sample data rather than population constants. The index of diversity is typically used with the logarithmic distribution but has limitations, such as not being independent of sample size. The author introduces a new measure, denoted as \(\lambda\), which is defined in terms of population constants. \(\lambda\) is calculated as the sum of the squares of the proportions of individuals in different groups and ranges from \(1/Z\) to 1, where \(Z\) is the number of groups. An unbiased estimator of \(\lambda\) is provided, and its properties are analyzed, including its distribution and variance. The chapter also explores the behavior of \(\lambda\) in different distributions, such as the negative binomial and Poisson distributions, and compares it with Yule's characteristic. The results show that \(\lambda\) can take various values depending on the distribution of group frequencies, and the chapter concludes with a discussion on the consistency of the new measure with previous findings.The chapter discusses the measurement of diversity in populations, focusing on two measures: Yule's 'characteristic' and Fisher's 'index of diversity.' These measures are defined as statistics derived from sample data rather than population constants. The index of diversity is typically used with the logarithmic distribution but has limitations, such as not being independent of sample size. The author introduces a new measure, denoted as \(\lambda\), which is defined in terms of population constants. \(\lambda\) is calculated as the sum of the squares of the proportions of individuals in different groups and ranges from \(1/Z\) to 1, where \(Z\) is the number of groups. An unbiased estimator of \(\lambda\) is provided, and its properties are analyzed, including its distribution and variance. The chapter also explores the behavior of \(\lambda\) in different distributions, such as the negative binomial and Poisson distributions, and compares it with Yule's characteristic. The results show that \(\lambda\) can take various values depending on the distribution of group frequencies, and the chapter concludes with a discussion on the consistency of the new measure with previous findings.