klassivahemik

Klassivahemik, in statistics, refers to a class interval—an arbitrary, continuous range of data values treated as a single category in a frequency distribution. It is used to summarize large data sets by grouping individual observations into adjacent intervals, making patterns and spread easier to visualize and analyze.

Constructing klassivahemikud involves choosing the number of classes and determining a common width for each interval. The class width is often computed as (max − min) / number_of_classes, with practical adjustments to use convenient, easy-to-interpret numbers. The intervals are then defined so that every data value belongs to one class and adjacent classes do not overlap. For continuous data, class boundaries may be set halfway between adjacent class limits to avoid gaps; for discrete data, inclusive endpoints are common.

Example: for a data set ranging roughly from 5 to 60, one might use six klassivahemikud with width 10: 5–14, 15–24, 25–34, 35–44, 45–54, 55–60. The frequency of each class is the count of observations falling within that interval, and these frequencies form the basis of a histogram or a grouped frequency distribution.

Klassivahemikud are used in descriptive statistics, enabling construction of histograms, stem-and-leaf displays, and calculations of descriptive measures for grouped data. They require careful choice of the number and width of classes, as too many or too few can obscure patterns or distort the data’s apparent distribution.