Definitions
of Statistics
Statistics has been defined by
various statisticians.
‘Statistics is the science of counting’ -A. L .Bowley
‘Statistics is the science which deals with the collection,
presentation, analysis and interpretation of numerical data’ - Croxton and Cowden
Wallist and Roberts defines
statistics as “Statistics is a body
of methods for making decisions in
the face of uncertainty”
Ya-Lun-Chou slightly modifies Wallist and
Roberts definition and come with the
following definition : “Statistics is a
method of decision making in the face of
uncertainty on the basis of numerical data and calculated risk.”
It
may be seen that most of the above definitions of statistics are restricted to
numerical measurements of facts and figures of a state. But modern thinkers
like Secrist defines statistics as
‘By statistics we mean
the aggregate of facts affected to a marked extent by multiplicity of causes,
numerically expressed, enumerated or estimated to reasonable standards of
accuracy collected in a systematic manner for a predetermined purpose and placed
in relation to each other’.
Among
them, the definition by Croxton and Cowden is considered as the most preferable
one due to its comprehensiveness. It is clear from this definition that
statistics brings out the following characteristics.
Statistics
deals with the aggregate of facts and figures. A single number cannot be called
as statistics. For example, the weight of a person with 65kg is not statistics
but the weights of a class of 60 persons is statistics, since they can be
studied together and meaningful comparisons are made in relation to the other.
This reminds us of Joseph Stalin’s well known quote, “One death is a tragedy; a million is
a statistics.”
Further the purpose for which the data is collected is to be made clear,
otherwise the whole exercise will be futile. The data so collected must be in a
systematic way and should not be haphazard.
Statistical
data so collected should be affected by various factors at the same time. This
will help the statistician to identify the factors that influence the
statistics. For example, the sales of commodities in the market are affected by
causes such as supply, demand, and import quality etc. Similarly, as mentioned
earlier if a million deaths occur the policy makers will be immediately in
action to find out the causes for these deaths to see that such events will not
occur.
The
statistical facts and figures are collected numerically for meaningful
inference. For instance, the service provided by a telephone company may be
classified as poor, average, good, very good and excellent. They are
qualitative in nature and cannot be called statistics. They should be expressed
numerically such as 0 to denote poor,1 for average, 2 for good, 4 to denote
very good and 5 for excellent. Then this can be regarded as statistics and is
suitable for analysis. The other types of quality characteristics such as
honesty, beauty, intelligence, defective etc which cannot be measured
numerically cannot be called statistics. They should be suitably expressed in
the form of numbers so that they are called statistics.
The
numerical data are collected by counting, measuring or by estimating. For
example, to find out the number of patients admitted in a hospital, data is
collected by actual counting or to find out the obesity of patients, data are
collected by actual measurements on height and weight. In a large scale study
like crop estimation, data are collected by estimation and using the powerful
sampling techniques, because the actual counting may or may not be possible.
Even if it is possible, the measurements involve more time and cost. The
estimated figures may not be accurate and precise. However certain degree of
accuracy has to be maintained for a meaningful analysis.
One
of the main reasons for the collection of statistical data is for comparisons
In order to make meaningful and valid comparisons, the data should be on the
same characteristic as far as possible. For instance, we can compare the
monthly savings of male employees to that of the female employees in a company.
It is meaningless if we compare the heights of 20 year-old boys to the heights
20 year- old trees in a forest.
Having
looked into various definitions given by different authors to the term
statistics in different contexts it would be appropriate to define
“Statistics
in the sense of data are numerical statements of facts capable of analysis and
interpretation”.
“Statistics
in the sense of science is the study of principles and methods used in the collection,
presentation, analysis and interpretation of numerical data in any sphere of
enquiry”.
Related Topics
Privacy Policy, Terms and Conditions, DMCA Policy and Compliant
Copyright © 2018-2023 BrainKart.com; All Rights Reserved. Developed by Therithal info, Chennai.