You are on page 1of 8

2.

Collection of Data

Statistical survey: It is a scientific inquiry into a problem, using statistical tools.


Investigator: A person who plans and conducts a statistical survey.
Enumerator: A person who is appointed by the investigator to collect data.
Respondent: Person who provides the actual data by answering the questions in the questionnaire.
Questionnaire: A list of questions prepared by the investigator on the subject of investigation for
collecting data from the respondent.

Primary data: Original data collected by the investigator or the enumerator by conducting
investigation are called primary data. Also, the data collected by some other agency and made
available to the investigator in original form (on questionnaire) are primary data.

Secondary data: Data that have been collected and processed (classified, tabulated and represented
diagrammatically) by someone else other than the investigator or his enumerators are called
secondary data.

Distinction between primary data and secondary data

Primary data Secondary data


Data collected by conducting a field survey Data collected and processed already
They are collected by the investigator They have been collected by others not
himself or the enumerators appointed by related to the present investigation.
him.
They are expensive to collect. They are relatively inexpensive to collect.
They are time-consuming. They are relatively less time-consuming.
They are reliable data as they are first- They are less reliable as they are second-
hand. hand data.

Planning of the Fieldwork

Collection of primary data involves investigation. A field investigation must be carefully planned and
organized.

Page 1 of 8
The following areas should be looked into before setting out for the fieldwork.

Preparation of a Questionnaire

The following points should be kept in mind when a questionnaire prepared.


1. The questionnaire should not be too lengthy.
2. The questions must be precise and short. Vague and ambiguous terms should not be used in a
questionnaire.
Poor Question: What percentage of your income do you spend on clothing in order to look
presentable?
Good Question: What percentage of your income do you spend on clothing?

3. The questions should not affect the prestige of the respondent.


4. The questions should not be jumpy. They should flow from one topic to another topic;
from general to specific.
For example, poor Questions
(i) Is increase in electricity charges justified?
(ii) Is the electricity supply in your locality regular?
Good Questions:
(i) Is the electricity supply in your locality regular?
(ii) Is increase in electricity charges justified?
5. Questions should be framed in such a way that the answers could be cross-checked with other
questions.
6. Questions should not involve too many arithmetic calculations.
7. The questions should not use double negatives.
Poor Question: Don’t you think smoking should be prohibited?
Good Question : Do you think smoking should be prohibited?

8. There should not be leading questions.


Poor Question: How do you like the flavour of this high quality tea?
Good question: How do you like the flavour of this tea?
9. The questions should not indicate alternative to the answer.

Page 2 of 8
Poor Question: Would you like to do a job after college or be housewife?
Good question: Would you like to do a job, if possible after college?

Types of questions:
Questions can be closed-ended (structured) or open-ended (unstructured) questions. Closed-ended
questions can be either two-way questions or multiple choice questions.

1. Two-way Questions: In these questions there are only two possible answers. For example,
Are you employed? Yes/No
2. Multiple Choice Questions: In these questions, there is a possibility of ore than two possible
questions. For example,

What is your marital status: Married/Unmarried/ Divorced/Separated/ Widow(er)


2. Open-ended questions: In these questions, no possible answers are suggested. Moreover, it
allows for more individualized responses but it is difficult to interpret and hard to score, since
there are a lot of variations in the responses.
For example,
What is your view about globalisation?

Mode of enquiry
The methods of data collection are:

1. Personal Interview method: In this method, either the investigator or the enumerators
appointed by him collect the data from the respondent personally.

Advantages

a) The objective and importance of study can be explained to the respondents.


b) Cooperation of the respondents and correct answers to the questions can be obtained.
c) Respondents can be helped by way of correct interpretation of the questions and correct
recording of answers.
d) The respondents can be kept in good humour.

However, it has the following disadvantages.

Page 3 of 8
1. It is expensive.
2. A large team of enumerators needs to be trained.

2. Mail Questionnaire method: In this method, questionnaires are sent by mail to the respondents
who are expected to fill in and send the questionnaires back.
Advantages
1. It is less expensive.
2. A large geographical area can be covered.
3. The need for appointing and training a large team of enumerators does not arise.

Disadvantages
1. The respondents might not understand the questions or may miss to interpret the questions
correctly.
2. The respondents may not take enough care to answer all the questions correctly.
3. Unless it is compulsory by to provide data, the respondents may ignore and not return the
questionnaire at all.
4. Some of the questionnaires may be lost in the mail.

3. Telephone Interview method: In a telephone interview method, the investigator asks questions
over the telephone.

Advantages
1. They are cheaper than the personal interviews.
2. Questions can be clarified by the interviewer.
3. It is better in cases where respondents are reluctant to answer certain questions in personal
questions.
4. Quick results can be obtained.
Disadvantages:
1. It is expensive compared to mail questionnaire method.
2. It is feasible only when all the respondents can be contacted through telephone.

Page 4 of 8
Training of Enumerators

Besides appointing a team of enumerators, they need to be trained on how to interpret the
questions correctly, how to explain the objectives and the Importance of the survey and how he
must be polite.

Pilot Survey

It is a small scale survey conducted before a large scale field study is conducted. The merits of a
pilot survey are that the survey will help
- to pretest the suitability of the questions in the questionnaire.
- to avoid any unforeseen problems that may arise during the large scale survey.
- to assess the performance of the enumerators and remove any difficulty they may be facing.
- to assess the time the actual survey might take
- to assess the cost of the large scale survey and to get a preliminary idea about certain aspects
of the data.

Types of Survey

A statistical survey can be collected either from all the units in the universe or only a part of it.

Census Survey
It is that type of survey in which all the units in the universe are studied and the data are collected
from all the units. That is why census method is also called the method of ‘complete
enumeration’.
A few examples of census survey taken in India are:
- The Population Census (once in 10 years)
- The Livestock Census (once in 5 years)

Sample Survey

It is the type of survey in which only a par of the universe is studies and data collected from those
units. Instead of enumeration of all the units in the universe, an estimate of the universe with the
help of representative units, known as samples, is done.

Page 5 of 8
Census survey Sample survey
It is the survey in which data are collected It is the survey in which data are
from all the units in the universe. collected from only a part of the units
of the universe.
It is time-consuming. It is time-saving.
It is expensive. It is relatively less expensive.
A large team of enumerators may be Only a less number of enumerators will
required. be required
Non-sampling errors may affect the Non-sampling errors can be controlled
study. but sampling errors may arise.
Quick results cannot be obtained. Quick results can be obtained.
It is not a scientific method. It uses scientific techniques.
Destructive testing is not possible. Destructive testing is possible.

Types of Sampling
1. Random Sampling Method
It is a method in which samples are chosen in such a way that every individual unit in the universe gets
an equal chance of being included in the sample. Selection of the sample can be chosen by:
a) Lottery method: Similar to a lottery, names of all the units in the universe are written in chits/cards,
with one chit/card for each name. Then, they are placed in a box and shuffled well. Without looking
into the box, the required number of chits/cards is selected. Those units whose names appear in the
chits are selected as samples.
Even though it is a scientific method, it cannot be used
i) when the universe is large and
ii) when the population is infinite as in the case of number of fish in a lake or a birds in a sanctuary.
b) Use of Tippet’s Random Number Table: Tippet’s table of random numbers can be used to draw
samples. The numbers can be chosen either row-wise or column-wise. For example, in order to draw a
random sample of 5 students from a class of 50 students, we assign numbers (01, 02, 03…) to the

Page 6 of 8
students. We use the two digit random number table. Suppose we start reading numbers in the tenth
row of the random number table of the first page. The numbers obtained are 57, 60, 86, 32 and 44.

Some of the numbers have not been assigned to any student. Therefore, we frame a rule that
whenever in the numbers in the tables are more than 50, we select the students with the numbers 57-
50 = 7, 60-50 = 10, 86 – 50 = 36. And, if the numbers obtained are less than 50, we select the student
bearing that number.

3. Non-Random Sampling method or Deliberate Sampling method: In this method, samples are
chosen by the investigator, using his own judgement (bias), purpose, convenience or quota.

If 10 samples are to be chosen among 100 units in the universe, the investigator himself decides
which units to be selected and which units to be rejected.

Unlike the Random Sampling method, all the units of the population do not have an equal chance of
being selected. Convenience or judgement of the investigator plays an important role in selection of
the samples.

CENSUS OF INDIA AND NSSO


There are some agencies both at the national and state level to collect, process and tabulate the
statistical data. Some of the agencies at the national level are Census of India, National Sample Survey
Organisation (NSSO), Central Statistics Office (CSO), Registrar General of India (RGI), Directorate
General of Commercial Intelligence and Statistics (DGCIS) and Labour Bureau.

The Census of India provides the most complete and continuous demographic record of population.
The Census is being regularly conducted every ten years since 1881. The first Census after
Independence was conducted in 1951. The Census officials collect information on various aspects of
population such as the size, density, sex ratio, literacy, migration, rural-urban distribution, etc. Census
data is interpreted and analysed to understand many economic and social issues in India.

Page 7 of 8
The NSSO was established by the Government of India to conduct nationwide surveys on socio-
economic issues. The NSSO does continuous surveys in successive rounds. The data collected by NSSO
are released through reports and its quarterly journal Sarvekshana.

NSSO provides periodic estimates of literacy, school enrolment, utilisation of educational services,
employment, unemployment, manufacturing and service sector enterprises, morbidity, maternity,
child care, utilisation of the public distribution system etc. The NSSO 60th round survey (January–June
2004) was on morbidity and healthcare. The NSSO 68th round survey (2011-12) was on consumer
expenditure. The NSSO also collects details of industrial activities and retail prices for various goods.
They are used by Government of India for planning purposes.

Page 8 of 8

You might also like