Page 44 - DECO504_STATISTICAL_METHODS_IN_ECONOMICS_ENGLISH

Statistical Methods in Economics

Notes Characteristics of a Good Average

The above discussion reveals that an average or the value of central tendency is a representative
figure. Therefore, a good average would be the one which has the capability of representing the data
most efficiently and effectively. For this, certain are the characteristics of the average so that it can
prove to be good. These essential characteristics for an average to prove to be good are:
(1) It should be rigidly defined: According to Prof. Yule and Kendall, the average should be defined
rigidly so that there is only one possible interpretation and is not subject to observers’ own
interpretation and bias. For this, the average should be defined in terms of alzebraic formula.
(2) It should be based on all the observations: In order to make the data representative it is very
essential that it is based on all the observations.
(3) It should be capable of further alzebraic treatment: For the average to be good, it is essential
that it is capable of further alzebraic treatment, otherwise its use will become very limited. For
example, in the absence of this quality, the combined average of two or more series from their
individual averages will not be calculated. This would hinder the possibility to study the average
relationship of various parts of a variable, if it is expressed as the sum of two or more variables.
(4) It should not be affected by fluctuations of sampling: If two independent sample studies are
made in any particular field, their averages obtained, should not differ from each other ideally.
Practically, it is difficult to obtain no difference, but the average in which this difference,
technically called as ‘fluctuation of sampling’ is least, is considered to be a better average.
(5) It should be easy to compute: An average should be capable of being calculated with reasonable
ease and within reasonable time. If the time taken is long or the calculations are tedious and
complicated, the average shall have only limited use.
(6) It should be easy to understand: A good average is the one which is easily understood by the
common people. It should neither be abstract nor too mathematical; otherwise its use will again
be restricted.
Types of Statistical Averages
The following are the main types of statistical averages:
(1) Positional Averages: These include —
(a) Median (represented by M)
(b) Mode (represented by Mo).
(2) Mathematical Averages: These include —
(a) Arithmatic Average or Mean (represented by X )
(b) Geometric Mean (represented by ‘G.M.’)
(c) Harmonic Mean (represented by ‘H.M.’)
(d) Quadratic Mean (represented by ‘Q.M.’)
(3) Commercial Averages:
(a) Moving Average.
(b) Progressive Average.
(c) Composite Average.

38 LOVELY PROFESSIONAL UNIVERSITY