Chapter 3 — Organisation of Data

Chapter 3 explains how to classify raw, unclassified data into a meaningful structure for statistical analysis. It covers four types of classification — Chronological, Spatial, Qualitative, and Quantitative — and teaches students how to construct frequency distributions using tally marking, class limits, and class marks.

Raw data is unclassified, disorganised data that is large and cumbersome to handle. For example, the marks of 100 students listed without any order make it difficult to find the highest mark or draw any conclusion. Classification brings order to raw data so that meaningful comparisons and statistical analysis become easy.

The four types are: (1) Chronological Classification — data arranged in ascending or descending order with reference to time such as years or months; (2) Spatial Classification — data classified by geographical locations such as countries or states; (3) Qualitative Classification — data grouped on the basis of attributes that cannot be measured, such as gender or marital status; (4) Quantitative Classification — data grouped by measurable characteristics such as marks, height, or income.

A continuous variable can take any numerical value including fractions and irrational numbers — for example, height of a student growing from 90 cm to 150 cm can take every value in between. A discrete variable can take only certain values and changes only by finite jumps — for example, the number of students in a class can only be a whole number like 25 or 26, never 25.5.

A frequency distribution is a comprehensive way to classify raw data of a quantitative variable, showing how different values are distributed in different classes along with their class frequencies. It is constructed by deciding on equal or unequal class intervals, determining the number of classes (usually six to fifteen), setting class limits, and counting frequencies using tally marks.

The class mark is the middle value of a class and lies halfway between the lower and upper class limits. It is calculated as: Class Mark = (Upper Class Limit + Lower Class Limit) / 2. For example, the class mark for the class 60–70 is (60 + 70) / 2 = 65. Once data are grouped into classes, further statistical calculations use the class mark rather than individual observation values.

In Inclusive class intervals, values equal to both the lower and upper class limits are included in the frequency of that class (e.g., 0–10, 11–20, 21–30). In Exclusive class intervals, a value equal to either the upper or lower class limit is excluded from that class (e.g., 0–10, 10–20, 20–30, where 10 falls in 10–20 rather than 0–10). For continuous variables, an adjustment of ±0.5 is applied to restore continuity when using the inclusive method.

Tally marking is the method of counting how many observations fall in each class. A tally mark (/) is put against a class for each observation belonging to it. When four tallies are recorded, the fifth is placed across them, making groups of five for easy counting. The total number of tallies against a class gives its class frequency.

When raw data is grouped into classes, individual observations lose their identity and are no longer used in further statistical calculations. All values within a class are assumed equal to the class mark. For example, in the class 20–30 with observations 25, 25, 20, 22, 25, and 28, all six values are treated as 25 (the class mark). This replacement of actual values by the class mark is called loss of information.

A Bivariate Frequency Distribution is the frequency distribution of two variables simultaneously. For example, if a sample of 20 companies provides data on both sales and advertisement expenditure, these two variables can be cross-tabulated in a bivariate frequency table where each cell shows the frequency of companies falling in the corresponding row and column class.

Unequal class intervals are used in two situations: first, when the range of the data is very high (such as income, which can range from near zero to many crores), where equal intervals would either create too many classes or suppress details at the extremes. Second, when a large number of observations are concentrated in a small part of the range, unequal intervals — with narrower classes in the dense area — better represent the data by keeping class marks close to the observed values.

The number of classes in a frequency distribution is usually between six and fifteen. When using equal-sized class intervals, the number of classes is calculated by dividing the range (difference between the largest and smallest values) by the size of each class interval. For instance, if the range is 100 and the class interval is 10, the number of classes would be 10.

When inclusive class intervals create a gap (discontinuity) between consecutive classes, continuity is restored by subtracting half the gap from all lower class limits and adding half the gap to all upper class limits. For example, if the gap between 899 (upper limit of first class) and 900 (lower limit of second class) is 1, we subtract 0.5 from lower limits and add 0.5 to upper limits, converting 800–899 into 799.5–899.5 and so on.

Yes, the NCERT PDF for Chapter 3 Organisation of Data is completely free to download on cbseprepmaster.com. No sign-up or account is required — just open the page and access the PDF directly.