Professional Documents
Culture Documents
Statistical Unit: The items on which measurements are taken. Example; weight in kgs.
In the above table, the years are represented by variable X and the production of
food grains by variable Y. These values of the variables X and Y are the ‘data’,
from which we can obtain information about the trend of the production of food
grains in India.
SOURCES OF COLLECTION OF DATA
In an organisation, when the data is collected from its reports
and records, it is known as internal sources of data. Data
collected and compiled through internal sources is called
internal data. For example, a company publishes its annual
report on profit and loss, total sales, loans, wages etc.
Population Census
Sources of Secondary Data can be classified as
Published Sources
Unpublished Sources
Under this method, the investigator collects data by having direct contact with the informant and conducts on –
the – spot enquiry.
MERITS
1. High response rate- as researcher has access to all the respondents.
2. Allows use of all types of questions: Contact is made between interviewer and
respondent.
3. More suited for using open ended questions: The interviewer can request the
respondent to elaborate on their answers.
4. Misunderstandings can be avoided: Interviewer can explain the study and answer the
queries of the respondents.
5. Reactions of the respondents can provide supplementary information to the
interviewer.
DEMERITS
1. Expensive as it requires trained interviewers.
2. Possibility of influencing the respondents: Presence of the interviewers inhibits the
respondents from expressing their true views.
3. Time consuming: Since the interviewer is involved personally, it takes longer time to
complete the survey.
4. This method is not suitable when the area of coverage is considerably wide or when many
respondents are to be contacted.
Direct personal Investigation
Example: Hindustan Unilever Limited (HUL) wishes to conduct a statistical enquiry regarding
bathing soap used by people of Delhi. For this, HUL will select some investigators, who will
approach the people of Delhi and collect the necessary data. It is necessary that in such cases, the
investigator has a keen sense of observation and he is very polite and courteous. He must be
skilful, tactful, accurate, amiable and neutral.
Suitability of this method:
1. When detailed information has to be collected.
2. When area of investigation is limited.
3. When nature of enquiry is confidential.
4. When maximum degree of accuracy is needed.
5. When importance is given to originality.
Under this method, the investigator approaches third parties, who are in the possession of information
about the subject of enquiry. Eg: Suppose we want to study the number of students of a college who smoke. For this
purpose, personal investigation cannot be successful as students may not provide correct information as regards to their smoking
habits. To get the information, the investigator has to contact the persons who are close to the respondent, like friends, lecturers,
neighbours, relatives or the persons who know the information.
MERITS
1. This method is suitable when the area of investigation is large.
2. It is economical in terms of time, money and manpower.
3. This method is relatively free from personal prejudice as the information is
collected from the persons who are well aware of the situation.
4. Under this method, an investigator can seek opinion of the experts.
DEMERITS
1. The result can be erroneous because information is obtained from other
persons, not directly connected.
2. As compared with direct personal observation, the degree of accuracy
of the data is likely to be lower.
3. The persons, providing the information, may be prejudiced or biased.
4. Since, the interest of the person, providing the information, is not
at stake, the collected information is often vague and unreliable.
5. The information collected from different persons may not be
homogeneous and comparable.
Indirect Oral Investigation
1. When concerned informants are unable to give information due to their ignorance or they
are not prepared to part with the information
2. When the area of investigation is very large
3. When secret or sensitive information about the informant has to be gathered
4. When the problem of investigation is complex and need expert’s opinion.
MERITS
1. This method is useful in situations where the area of investigation is very large and periodic
information is to be collected from the distant places.
2. It is very economical in terms of money and resources.
3. This method is suitable for some special purpose of investigations.
4. It is very useful for collecting regular information.
DEMERITS
1. The information supplied by different correspondents often lacks homogeneity, and hence, not
comparable.
2. The personal bias of the correspondents may enter the reports and to that extent, the accuracy
is affected.
3. This method cannot be used where high degree of accuracy is required.
4. A lot of time is consumed to collect the information.
Information from Correspondents
DEMERITS
1. The disadvantage of this method is access to people. This method is not possible for
people who do not own telephones.
2. Telephone interviews also obstruct visual reactions of the respondents, which becomes
helpful in obtaining information on sensitive issues.
SUITABILITY
This method is suitable where adequate finance and trained enumerators are available to cover
a wide field and some significance is attached to the accuracy of the results obtained.
1. Enumerator should be a person of high integrity and properly trained to use statistical tools.
2. Enumerator should be polite, tactful, laborious and honest to his assigned work.
3. There should be timely evaluation of the work of enumerators.
4. The informant should be properly educated about the objective of investigation.
5. Questions in the schedule should be small in length, simple and clear.
Pilot Survey
[NOTE: Once the draft questionnaire is ready, it is advisable to conduct a try – out
with a small group which is known as Pilot Survey or Pre – Testing of the
questionnaire.]
Pre-testing of a questionnaire with a small group of
respondents is known as a pilot survey.
It could be a two-way question or a multiple choice question. When there are only 2
possible answers it is called a two way question. When there is a possibility of more
than 2 answers it is called multiple choice question.
It could be descriptive types. When a person gets a chance to talk more about any
topic.
Open Ended Questionnaire Closed Ended Questionnaire
The respondents have to write their own Can be multiple choice type or two way
views. ‘yes’ – ‘no’ response type
Difficult to score and codify as responses can Easy to use, score and codify as all
vary. respondents choose from a set of given
options
• This method is generally adopted when area of investigation is limited and an intensive
study of the population is required.
• Highly trained investigators are needed to maintain a high degree of accuracy.
• Demographic (study of population based on age, race and sex)data on birth and death
rates, literacy, workforce, life expectancy, size and composition of population, etc. are
collected and published by the Registrar General of India.
• The famous example of this method is the Census of India conducted after every 10 years.
The last Census of India was held in 2011.
• This method is also known as ‘Complete Enumeration’ or ‘Complete Survey’ or ‘100%
Enumeration’.
Merits of Census Method:
1. Results are accurate and highly reliable because each and every item of the
population is studied.
2. Results are less biased.
3. Information is quite exhaustive and therefore, more meaningful because all the
items of the universe are examined.
4. This method is suitable when different items of the population are not
homogeneous.
1. This method is very costly and is, therefore, generally not used for ordinary
investigations.
2. Census method requires a lot of time and manpower for the collection, analysis and
interpretation of data.
3. This method cannot be applied in case of infinite population.
Sampling METHOD
When only some representative items of a population are selected and data collected from these items are used for the
analysis, the method is known as Sampling Method.
Essential features
• A sample is a part of universe or population.
• The first task in selecting a sample is to identify the population. Once the population is
identified, the researcher selects a representative sample as it is difficult to study the
entire population.
• A good sample is generally smaller than the population and is capable of providing
reasonably accurate information about the population at a much lower cost and shorter
time.
1. In case of large population, sample size would be bigger and vice – versa.
2. If greater degree of accuracy is desired, the size of sample should be larger. However, if
samples are selected by an experienced person on the basis of scientific method, better
results can be ensured, even in case of small size of sample.
3. In case, the population consists of homogeneous units, a small sample will serve the
purpose. On the other hand, if the population consists of heterogeneous units, large sample
is required.
4. In case of intensive and continuous study, a small sample is quite appropriate. On the
contrary in case of unrepeated and extensive study, it may be necessary to take a larger
sample size.
5. If it is seen that a large number of respondents will not cooperate then a larger sample
should be selected.
Requisites of a good Sample
1. The selected sample should be representative of the
characteristics of the population.
2. To ensure that all the characteristics of a population are
represented by the sample, its size must be adequate.
3. As far as possible, the population from which a sample is to
be obtained, should be homogeneous.
4. The selection of various items of the population in the
sample should be done independently of each other.
5. To have correct picture of the problem under investigation,
it is important to draw a sample keeping in view the
objective of investigation.
Election coverage is provided by news
channels during elections for predicting
election results. A random sample of
voters who leave the booth after
casting their vote are asked whom they
voted for. Based on this data, a
prediction is made. Exit Polls may not
always be accurate as voters do not
necessarily tell the truth about their
vote. Voting is done through secret
ballot so that none other than the voter
knows who the vote is cast for.
Merits of Sampling Method:
1. A sample provides reasonably reliable and accurate information at a lower cost and
shorter time.
2. As samples are smaller than the population, detailed information can be collected by
conducting intensive enquiries.
3. A smaller team of enumerators can carry out sample surveys, so their training and
supervision becomes convenient.
4. Sample method is more scientific because the sample data can be conveniently
investigated from various angles.
c) Exit Polls: it is used to predict election results. In this technique a random sample
of voters, who exit from the polling booths are asked who they voted for.
2.Non-Random Sampling
In this all the units of the population do not have an equal chance of being selected.
b) Quota Sampling: Here the investigator is allotted definite quota and he is required to collect the
required data from a specific number of unit of each quota. For example, in a survey of TV
viewers, the interviewers may be told to interview 500 people living in a certain area, and that
55% (i.e.275) of the interviewed are to be housewives, 30% ( i.e.150) school students, 10%
(i.e.50) employees, 5% (i.e.25) children. Within these quotas the interviewer is free to select the
people to be interviewed.
c) Convenience Sampling: Here the investigator collects the sample units on the basis of his
convenience.
In the statistical literature, Statistical Errors refer to the difference
between the collected data and the actual value of facts.
Sampling and
Biased and
Non – Sampling
Unbiased errors
errors
It refers to the difference between the sample estimate and the actual value of a
characteristic of the population. The actual value of the population parameter is
not known and the sample value is used to estimate it. Taking a larger sample
can reduce the magnitude of sampling error.
For example, suppose height of 5 students (in inches) is 50, 55, 60, 65, 70.
Now average height will be: (50 + 55 + 60 + 65 + 70) ÷ 5 = 300 ÷ 5 = 60 inches.
If we select a sample of two students with height of 50 inches and 60 inches,
then average height of sample will be (50 + 60) ÷ 2 = 110 ÷ 2 = 55 inches.
Here the sampling error of the estimate = 60 (true value) – 55(estimate) = 5 inches
Non – sampling errors are errors that occur in acquiring, recording or tabulating
statistical data.
Non – sampling errors are more serious than sampling errors because a sampling error can be
minimised by taking a larger sample. But, non – sampling error cannot be minimised even by
taking a large sample.
The main causes of non – sampling errors are:
This type of error arises from recording of incorrect responses or in recording the data.
Non – response occurs if an interviewer is unable to contact a person listed in the sample or
a person from the sample refuses to respond. In this case, the sample observation may not
be representative.
It occurs when sampling plan is such that some members of the target population could not
possibly be included in the sample.
Biased Error: An error which arises on account of some bias
or imbalance on the part of the investigator, informants or instruments
of counting, measurement or experiment is called biased error.
Absolute Error: The difference between true value of a parameter and the
estimated value.
Relative Error: The ratio of the Absolute error to the actual value.
Relative error is a much more useful measure than the absolute error as it provides a useful
coefficient (a pure number independent of units of measurement) for comparing the degree of
error in different sets of statistical data.
Sources of
secondary data
Many investigations are of private nature and their findings are not published. Such unpublished
data is usually meant for the use of members only.
No proper procedure is adopted to collect the data.
1. The data should be used only if these are collected by a reliable, impartial and competent
agency. So, the ability of the collecting organisation should be checked.
2. Data should be used only if the objective of the study as undertaken earlier matches with the
objective and scope of the current statistical enquiry.
3. The method of data collection used by the original investigator should match the nature of
present statistical enquiry.
4. The investigator should study conditions of investigation. For instance, data collected during
times of war may not be suitable to study an enquiry during times of peace.
5. Accuracy of data should also be kept in mind. If the available data do not possess required
level of accuracy, then such data should not be used.
The Census of India provides the most complete and continuous demographic
record of population. Data on birth and death rates, literacy, employment, life
expectancy, size and composition of population etc. are collected and
published by the Registrar General of India. It has been conducted regularly
every 10 years since 1881.The last census was conducted in 2011. A house - to -
house enquiry is carried out covering all the houses in India.
NSSO (NATIONAL SAMPLE SURVEY ORGANISATION)
Carries out multi – subject integrated socio – economic surveys (which may include
employment and unemployment, housing condition, domestic tourism, drinking water,
sanitation, health, labour force, industries etc.);
Undertakes field work for the Annual Survey of Industries and follow – up surveys of
Economic Census (census of an economy through counting all entrepreneurial units in a
country which are involved in any economic activities of either agricultural or non –
agricultural sector);
Conducts sample checks on area enumeration and crop estimation surveys of State
Statistical Agencies;
Conducts ad – hoc surveys (surveys conducted in response to specific needs) and pilot
enquiries for methodological studies.