Things You Need to Know about Index Number Construction




A statistical measure of average change in a variable or a group of variables with respect to time or space is known as index number. The variable may be the enrolment of staff in an organization, the cost of salaries for staff, prices of a particular commodity or a group of commodities, wages of workers, volume of trade, sales, exports and imports, production, etc.

Index numbers are obtained by expressing the data for various periods or places as percentage of some specific period or place selected for the purposes of comparison and technically called the base. Index numbers may be computed on weekly or monthly basis but generally they are computed on annual basis.

Simple and Composite Indices

Index numbers are generally classified into Simple Indices and Composite Indices. An index number is called a simple index when it is computed for a single variable. Index numbers of enrolment in colleges, index numbers of gold prices, etc. are examples of simple indices. A simple index can be very easily computed. The value of the variable for each period is divided by the value in the base period and the result is multiplied by 100.

An index that is computed from two or more variables is referred to as a composite index. Examples of composite indices are the wholesale price index numbers, consumer price index numbers etc. Composite indices are more important as many of the index numbers in common use are composite in nature. Composite indices may further be classified into Unweighted and Weighted index numbers.

3 Important Things about Index Numbers

Following are three important things we must consider while in compilation of index numbers:

  1. Understand the purpose which an index is to serve. The purpose of the index may be to compare the score of two players, or to measures the changes in the general price level or to measures the changes in the production of scooters or to compare the changes in wages of factory workers over different places, etc.

  2. Decide what data should be included. The data to be included should relate to purpose for which the index is to be used. This step also involves the collection of data on scores, production, process, wages or whatever is being compared.

  3. Decide what period should be chosen as the base period, i.e. the period with which the other periods are to be compared. In case of composite index numbers, another problem is to decide what method of averaging should be used to arrive at a single index for each period. The method of averaging usually includes the system of weighting but sometimes one faces the problems of assigning some explicit weights to the various items of the data so that their relative importance is taken into account.

Got A Data Science Question?

Ask our experts anything about machine learning, analytics or statistics.