Meaning and Need for Classification of Data

Raw data collected through a survey, a census, or business records is usually a long, unorganised list of numbers or facts. In this form it tells a student or a manager almost nothing at a glance — a Gujarat trader's daily cash-memo entries for a whole month, or the marks of 60 students in a Std 11 commerce division, are simply too many individual figures for the human eye to make sense of directly.

Classification is the process of arranging raw data into groups or classes according to some common characteristic, so that items with a similar nature fall together. It is the first step of statistical analysis — data must be classified before it can be tabulated, presented diagrammatically, or summarised with an average.

Why classification is needed

• It condenses a large mass of figures into a compact, meaningful form.
• It highlights similarities and dissimilarities among items by grouping like with like.
• It makes data comparable — across time periods, regions, or categories.
• It prepares the ground for tabulation, diagrammatic/graphic presentation, and further analysis such as averages, dispersion, and correlation (studied in later Std 11/12 chapters of this Gujarat Std-11 statistics syllabus).

A Gujarat cotton-market committee, for instance, does not report every individual farmer's daily arrival in quintals; it classifies arrivals by taluka, by month, or by quality grade, and only then presents the classified figures.