STATISTICS
1. ORIGIN OF STATISTICS
The word "Statistics" is derived from the Latin word "Status", the Italian word "Statista", or the German
word "Statistik", all of which mean a political state.
● In ancient times, statistics was used mainly by kings and rulers to collect information about their
population, wealth, army, and revenue, for taxation and military purposes.
● Early record-keeping is found in Egypt (census for pyramid construction), Rome (census of citizens
and property), and India (records during the Mauryan and Mughal periods, e.g., Kautilya's
Arthashastra).
● The modern development of statistics as a scientific discipline began in the 17th–18th centuries with
contributions from John Graunt (vital statistics), William Petty, Gottfried Achenwall (who coined
the German term Statistik), and later Karl Pearson, R.A. Fisher, and Sir Francis Galton, who gave
statistics its modern mathematical foundation.
MEANING OF STATISTICS
The term Statistics is used in two senses:
Statistics means numerical data — facts and figures collected on some
subject (e.g., statistics of births, statistics of production).
Statistics means the science/methodology — the body of methods used to
collect, classify, present, analyze, and interpret numerical data.
3. DEFINITIONS OF STATISTICS
A. Definitions emphasizing Statistics as Data
Webster – "Statistics are the classified facts representing the
conditions of the people in a state... especially designed to present
a comprehensive view of the whole state of the country."
Bowley – "Statistics are numerical statements of facts in any
department of enquiry, placed in relation to each other."
B. Definitions emphasizing Statistics as a Science (Method)
Croxton and Cowden – "Statistics may be defined as the science of collection,
presentation, analysis, and interpretation of numerical data." (This is the most widely
accepted and comprehensive definition.)
A.L. Bowley – "Statistics may be called the science of counting" and also "the science of
averages."
Horace Secrist (comprehensive definition) – Statistics are aggregates of facts, affected by
multiplicity of causes, numerically expressed, enumerated or estimated with reasonable
standard of accuracy, collected in a systematic manner, for a predetermined purpose, and
placed in relation to each other.
4. CHARACTERISTICS OF STATISTICS
For any data to be called "Statistics," it must satisfy the following characteristics:
Aggregate of facts – Single, isolated figures are not statistics; a collection of
figures is needed (e.g., the height of one person is not statistics, but heights of
students in a class are).
Affected by multiplicity of causes – Statistical data are the result of many
factors acting together (e.g., crop yield is affected by rainfall, soil, seeds,
fertilizers, etc.), not a single cause.
Numerically expressed – Statistics deals only with quantitative/numerical facts,
not qualitative statements.
Enumerated or estimated with reasonable accuracy – Data must be collected
with a reasonable, pre-decided standard of accuracy depending on the purpose.
Collected in a systematic manner – Data should be gathered through a
planned and organized method, not haphazardly.
Collected for a predetermined purpose – The objective of data collection must
be decided in advance.
Placed in relation to each other – Data should be comparable, so that facts in
one set can be related to facts in another (e.g., comparing sales figures across
years).
5. USES OF STATISTICS
Helps in framing policies – Governments use statistical data for planning in economics,
education, health, defense, etc.
Presents facts in a definite form – Converts vague impressions into precise,
measurable figures.
Condenses
mass data – Summarizes large volumes of data into a few meaningful figures (mean,
median, etc.) for easy understanding.
Facilitates comparison – Enables comparison between different groups, regions, or time
periods.
Helps in forecasting – Used in trend analysis and forecasting future events (sales,
population growth, demand, etc.).
Tests hypotheses – Used in scientific research to test the validity of
assumptions/theories.
Helps in formulating and testing economic theories – Widely used in Economics
(index numbers, national income, demand analysis).
Useful in business and management – For decision-making, quality control, market
research, forecasting, and risk analysis.
Used in Social Sciences and Natural Sciences – Sociology, Psychology, Biology,
Medicine (clinical trials), Agriculture (crop experiments), etc.
Aids in administration – Used in census, elections, budgeting, and resource allocation.
6. LIMITATIONS OF STATISTICS
Does not study qualitative facts – Statistics deals only with numerically expressible data;
qualities like honesty, beauty, intelligence cannot be studied directly unless converted to
scores.
Does not study individual items – Statistics deals with aggregates, not with a single item
or isolated fact.
Statistical laws are not exact – They are true only on average and in the long run
(probabilistic, not exact like laws of physics).
Results are true only on average – Conclusions are generalizations and may not apply to
every individual case.
Data may be misused – Statistics can be manipulated or misinterpreted to draw wrong or
biased conclusions ("Statistics can prove anything").
Requires expert handling – Collection, analysis, and interpretation need skilled, unbiased,
and trained persons; wrong handling gives misleading results.
Statistics is only one of the methods of studying a problem – It should be used along
with other methods, not in isolation.
Homogeneity requirement – Statistical methods apply only to a group of homogeneous
(comparable) items.
7. SOURCES OF STATISTICAL DATA
Statistical data are classified into two broad types based on their source:
A. PRIMARY DATA
Definition: Data collected for the first time, originally, by the investigator
himself/herself for a specific purpose. It is in its raw, original form.
Methods of Collecting Primary Data:
1. Direct Personal Interview/Observation – Investigator personally collects data from respondents.
2. Indirect Oral Interview – Information gathered from third parties/witnesses acquainted with the
subject.
3. Questionnaire Method – A set of questions sent by mail/email to respondents, who fill and return
them.
4. Schedule Method – Enumerators (trained investigators) fill up the questionnaire by visiting
respondents directly.
5. Through Local Correspondents/Agents – Local agents send regular information from different
places (used by newspapers, government agencies).
6. Telephone/ Telephonic and Online Surveys – Data collected via telephone or online tools.
Merits: Original, reliable, accurate, and specific to purpose. Demerits: Time-consuming, costly, requires
more manpower and planning.
B. SECONDARY DATA
Definition: Data that has already been collected by some other person or organization and is used by a
different investigator for their own purpose. It is not original; it has passed through a statistical process at least
once already.
Sources of Secondary Data:
1. Published Sources:
○ Government publications (Census reports, RBI Bulletins, Economic Survey)
○ International bodies (UNO, WHO, World Bank, IMF reports)
○ Semi-government publications (Municipal corporations)
○ Reports of research institutions, journals, newspapers, magazines
2. Unpublished Sources:
○ Records maintained by government/private offices
○ Research scholars' theses and dissertations
○ Records of trade associations and organizations
Precautions before using Secondary Data (as suggested by Bowley): Check for
● Suitability (does it fit the purpose?)
● Adequacy (is it sufficient in scope/period?)
● Reliability (source, method, and accuracy of original collection)
Merits: Saves time, money, and effort; useful for large-scale/comparative studies. Demerits:
May not fit the exact requirement; risk of inaccuracy if source is unreliable; lacks originality.