Measures of Dispersion and Range

Lesson 10 of STA301 introduces Measures of Dispersion, establishing that central tendency measures alone are insufficient to fully characterize a frequency distribution. Two datasets may exhibit identical arithmetic means yet possess vastly different underlying structures—one tightly concentrated around the average, and the other widely scattered across a broad spectrum. Dispersion, also known as variation, scatter, or spread, quantifies the degree to which individual observations deviate from the central value. The lecture categorizes measures of dispersion into Absolute Measures, expressed in the same physical units of measurement as the original data (such as meters, grams, or rupees), and Relative Measures (Coefficients), which are pure, unitless ratios or percentages enabling valid comparisons between datasets measured in differing units or differing orders of magnitude. The simplest absolute measure examined is the Range, defined as the difference between the maximum and minimum observations: Range = X_max - X_min. For grouped continuous data, range represents the difference between the upper boundary of the highest class and the lower boundary of the lowest class. While simple to compute, range relies solely on two extreme values and ignores the remaining data. Its relative counterpart is the Coefficient of Range: (X_max - X_min) / (X_max + X_min). To overcome the sensitivity of range to extreme outliers, the lecture introduces Quartile Deviation (QD), also termed the Semi-Interquartile Range. Quartile deviation evaluates the middle fifty percent of data and is defined as half the interquartile range: QD = (Q3 - Q1) / 2. Its relative counterpart is the Coefficient of Quartile Deviation: (Q3 - Q1) / (Q3 + Q1). Because quartile deviation is based on positional quartiles, it remains stable in the presence of extreme outliers and can be calculated for distributions with open-ended class intervals. In Virtual University midterm examinations, calculations of range, quartile deviation, and their respective unitless coefficients are frequently tested. Reviewing sta301 handouts and practicing solved past paper problems will ensure high exam performance.