***
60CHAPTER II
Lesson 2: Questionnaire & Sampling
111 Meaning Of Questionnaire
Drafting Of Questionnaire.
Size Of Questions
Clarity Of Questions
Logical Sequence Of Questions
Simple Meaning Questions
Other Requirements Of A Good Questionnaire
Meaning And Essentials Of Sampling.
Introduction:
Nowadays questionnaire is widely used for data collection in social
research. It is a reasonably fair tool for gathering data from large, diverse,
varied and scattered social groups. The questionnaire is the media of
communication between the investigator and the respondents. According
to Bogardus, a questionnaire is a list of questions sent to a number of
persons for their answers and which obtains standardized results that
can be tabulated and treated statistically. The Dictionary of Statistical
Terms defines it as a “group of or sequence of questions designed to elicit
61
information upon a subject or sequence of subjects from information.” A
questionnaire should be designed or drafted with utmost care and caution
so that all the relevant and essential information for the enquiry may be
collected without any difficulty, ambiguity and vagueness. Drafting of a
good questionnaire is a highly specialized job and requires great care skill,
wisdom, efficiency and experience. No hard and fast rule can be laid down
for designing or framing a questionnaire. However, in this connection, the
following general points may be borne in mind:
1.
Size Of The Questionnaire Should Be Small:
A researcher should try his best to keep the number of questions
as small as possible, keeping in view the nature, objectives and scope of
the enquiry. Respondent’s time should not be wasted by asking irrelevant
and unimportant questions. A large number of questions would involve
more work for the investigator and thus result in delay on his part in
collecting and submitting the information. A large number of unnecessary
questions may annoy the respondent and he may refuse to cooperate. A
reasonable questionnaire should contain from 15 to 25 questions at large.
If a still larger number of questions are a must in any enquiry, then the
questionnaire should be divided into various sections or parts.
2.
The Questions Should Be Clear:
The questions should be easy, brief, unambiguous, non-offending,
courteous in tone, corroborative in nature and to the point, so that much
scope of guessing is left on the part of the respondents.
3.
The Questions Should Be Arranged In A Logical Sequence:
Logical arrangement of questions reduces lot of unnecessary work
on the part of the researcher because it not only facilitates the tabulation
work but also does not leave any chance for omissions or commissions.
For example, to find if a person owns a television, the logical order of
questions would be: Do you own a television? When did you buy it? What
is its make? How much did it cost you? Is its performance satisfactory?
Have you ever got it serviced?
62
4.
Questions Should Be Simple To Understand:
The vague words like good, bad, efficient, sufficient, prosperity,
rarely, frequently, reasonable, poor, rich etc., should not be used since
these may be interpreted differently by different persons and as such might
give unreliable and misleading information. Similarly the use of words
having double meaning like price, assets, capital income etc., should also
be avoided.
5.
Questions Should Be Comprehensive & Easily Answerable:
Questions should be designed in such a way that they are readily
comprehensible and easy to answer for the respondents. They should not
be tedious nor should they tax the respondents’ memory. At the same time
questions involving mathematical calculations like percentages, ratios etc.,
should not be asked.
6.
Questions Of Personal & Sensitive Nature Should Not Be
Asked:
There are some questions which disturb the respondents and he/
she may be shy or irritated by hearing such questions. Therefore, every
effort should be made to avoid such questions. For example, ‘do you
cook yourself or your wife cooks?’ ‘Or do you drink?’ Such questions will
certainly irk the respondents and thus be avoided at any cost. If unavoidable
then highest amount of politeness should be used.
7.
Types Of Questions:
Under this head, the questions in the questionnaire may be classified
as follows:
(a) Shut Questions:
Shut questions are those where possible answers are suggested by
the framers of the questionnaire and the respondent is required to tick
one of them. Shut questions can further be subdivided into the following
forms:
63
(i) Simple Alternate Questions:
In this type of questions the respondent has to choose from the two
clear cut alternatives like ‘Yes’ or ‘No’, ‘Right or Wrong’ etc. Such questions
are also called as dichotomous questions. This technique can be applied
with elegance to situations where two clear cut alternatives exist.
(ii) Multiple Choice Questions:
Many a times it becomes difficult to define a clear cut alternative
and accordingly in such a situation additional answers between Yes and
No, like Do not know, No opinion, Occasionally, Casually, Seldom etc.,
are added. For example, in order to find if a person smokes or drinks, the
following multiple choice answers may be used:
Do you smoke?
(a) Yes regularly [ ] (b) No never [ ]
(c) Occasionally [ ] (d) Seldom [ ]
Multiple choice questions are very easy and convenient for
the respondents to answer. Such questions save time and also facilitate
tabulation. This method should be used if only a selected few alternative
answers exist to a particular question.
8.
Leading Questions Should Be Avoided:
Questions like ‘why do you use a particular type of car, say Maruti
car’ should preferably be framed into two questions-
(i) which car do you use?
(ii) why do you prefer it?
It gives smooth ride [ ]
It gives more mileage [ ]
It is cheaper [ ]
It is maintenance free [ ]
64
9
Cross Checks:
The questionnaire should be so designed as to provide internal
checks on the accuracy of the information supplied by the respondents by
including some connected questions at least with respect to matters which
are fundamental to the enquiry.
10
Pre Testing The Questionnaire:
It would be practical in every sense to try out the questionnaire on
a small scale before using it for the given enquiry on a large scale. This
has been found extremely useful in practice. The given questionnaire can
be improved or modified in the light of the drawbacks, shortcomings and
problems faced by the investigator in the pre test.
11
A Covering Letter:
A covering letter from the organizers of the enquiry should
be enclosed along with the questionnaire for the purposes regarding
definitions, units, concepts used in the questionnaire, for taking the
respondent’s confidence, self addressed envelop in case of mailed
questionnaire, mention about award or incentives for the quick response,
a promise to send a copy of the survey report etc.
SAMPLING
Though sampling is not new, the sampling theory has been
developed recently. People knew or not but they have been using the
sampling technique in their day to day life. For example a house wife tests
a small quantity of rice to see whether it has been well-cooked and gives
the generalized result about the whole rice boiling in the vessel. The result
arrived at is most of the times 100% correct. In another example, when
a doctor wants to examine the blood for any deficiency, takes only a few
drops of blood of the patient and examines. The result arrived at is most
of the times correct and represent the whole amount of blood available in
the body of the patient. In all these cases, by inspecting a few, they simply
believe that the samples give a correct idea about the population. Most of
our decision are based on the examination of a few items only i.e. Sample
studies. In the words of Croxton and Cowdon, “It may be too expensive
65
or too time consuming to attempt either a complete or a nearly complete
coverage in a statistical study. Further to arrive at valid conclusions, it
may not be necessary to enumerate all or nearly all of a population. We
may study a sample drawn from the large population and if that sample is
adequately representative of the population, we should be able to arrive at
valid conclusions.”
According to Rosander, “The sample has many advantages over a
census or complete enumeration. If carefully designed, the sample is not
only considerably cheaper but may give results which are just accurate
and sometimes more accurate than those of a census. Hence a carefully
designed sample may actually be better than a poorly planned and executed
census.”
Merits:
1. It saves time:
Sampling method of data collection saves time because fewer items
are collected and processed. When the results are urgently required, this
method is very helpful.
2. It reduces cost:
Since only a few and selected items are studied in sampling, there is
reduction in cost of money and reduction in terms of man hours.
3. More reliable results can be obtained:
Through sampling, more reliable results can be obtained because
(a) there are fewer chances of sampling statistical errors. If there is
sampling error, it is possible to estimate and control the results.(b) Highly
experienced and trained persons can be employed for scientific processing
and analyzing of relatively limited data and they can use their high technical
knowledge and get more accurate and reliable results.
66
4. It provides more detailed information:
As it saves time, money and labor, more detail information can be
collected in a sample survey.
5. Sometimes only sampling method to depend upon:
Some times it so happens that one has to depend upon sampling
method alone because if the population under study is finite, sampling
method is the only method to be used. For example, if someone’s blood has
to be examined, it will become fatal to take all the blood out from the body
and study depending upon the total enumeration method.
6. Administrative convenience:
The organization and administration of sample survey are easy for
the reasons which have been discussed earlier.
7. More scientific:
Since the methods used to collect data are based on scientific theory
and results obtained can be tested, sampling is a more scientific method of
collecting data.
It is not that sampling is free from demerits or shortcomings. There are
certain shortcomings of this method which are discussed below:
1.
Illusory conclusion:
If a sample enquiry is not carefully planned and executed, the
conclusions may be inaccurate and misleading.
2.
Sample Not Representative:
To make the sample representative is a difficult task. If a
representative sample is taken from the universe, the result is applicable
to the whole population. If the sample is not representative of the universe
the result may be false and misleading.
67
3.
Lack Of Experts:
As there are lack of experts to plan and conduct a sample survey, its
execution and analysis, and its results would be
Unsatisfactory and not trustworthy.
4.
Sometimes More Difficult Than Census Method:
Sometimes the sampling plan may be complicated and requires
more money, labor and time than a census method.
5.
Personal Bias:
There may be personal biases and prejudices with regard to the
choice of technique and drawing of sampling units.
6.
Choice Of Sample Size:
If the size of the sample is not appropriate then it may lead to untrue
characteristics of the population.
7.
Conditions Of Complete Coverage:
If the information is required for each and every item of the
universe, then a complete enumeration survey is better.
Essentials of sampling:
In order to reach a clear conclusion, the sampling should possess
the following essentials:
1. It must be representative:
The sample selected should possess the similar characteristics of
the original universe from which it has been drawn.
68
2. Homogeneity:
Selected samples from the universe should have similar nature and
should mot have any difference when compared with the universe.
3.
Adequate samples:
In order to have a more reliable and representative result, a good
number of items are to be included in the sample.
4. Optimization:
All efforts should be made to get maximum results both in terms
of cost as well as efficiency. If the size of the sample is larger, there is
better efficiency and at the same time the cost is more. A proper size of
sample is maintained in order to have optimized results in terms of cost
and efficiency.
STATISTICAL LAWS
One of the basic reasons for undertaking a sample survey is to
predict and generalize the results for the population as a whole. The logical
process of drawing general conclusions from a study of representative items
is called induction. In statistics, induction is a generalization of facts on the
assumption that the results provided by an adequate sample may be taken
as applicable to the whole. The fact that the characteristics of the sample
provide a fairly good idea about the population characteristics is borne
out by the theory of probability. Sampling is based on two fundamental
principles of statistics theory viz, (i) the Law of Statistical Regularity and
(ii) the Law of Inertia of Large Numbers.
THE LAW OF STATISTICAL REGULARITY
The Law of Statistical Regularity is derived from the mathematical
theory of probability. According to W.I.King, “the Law of Statistical
Regularity formulated in the mathematical theory of probability lays down
that a moderately large number of items chosen at random from a very
large group are almost sure to have the characteristics of the large group.”
For example, if we want to find out the average income of 10,000 people,
69
we take a sample of 100 people and find the average. Suppose another
person takes another sample of 100 people from the same population and
finds the average, the average income found out by both the persons will
have the least difference. On the other hand if the average income of the
same 10,000 people is found out by the census method, the result will be
more or less the same.
Characteristics
1. The item selected will represent the universe and the result is
generalized to universe as a whole.
2. Since sample size is large, it is representative of the universe.
3. There is a very remote chance of bias.
LAW OF INERTIA OF LARGE NUMBERS
The Law of inertia of Large Numbers is an immediate deduction
from the Principle of Statistical Regularity. Law of Inertia of Large Numbers
states, “Other things being equal, as the sample size increases, the results
tend to be more reliable and accurate.” This is based on the fact that the
behavior or a phenomenon en masse. I.e., on a large scale is generally
stable. It implies that the total change is likely to be very small, when a
large number or items are taken in a sample. The law will be true on an
average. If sufficient large samples are taken from the patent population,
the reverse movements of different parts in the same will offset by the
corresponding movements of some other parts.
Sampling Errors:
In a sample survey, since only a small portion of the population
is studied its results are bound to differ from the census results and thus,
have a certain amount of error. In statistics the word error is used to denote
the difference between the true value and the estimated or approximated
value. This error would always be there no matter that the sample is drawn
at random and that it is highly representative. This error is attributed
to fluctuations of sampling and is called sampling error. Sampling error
exist due to the fact that only a sub set of the population has been used
to estimate the population parameters and draw inferences about the
population. Thus, sampling error is present only in a sample survey and is
completely absent in census method.
70
Sampling errors occur primarily due to the following reasons:
1.
Faulty selection of the sample:
Some of the bias is introduced by the use of defective sampling
technique for the selection of a sample e.g. Purposive or judgment sampling
in which the investigator deliberately selects a representative sample to
obtain certain results. This bias can be easily overcome by adopting the
technique of simple random sampling.
2. Substitution:
When difficulties arise in enumerating a particular sampling unit
included in the random sample, the investigators usually substitute a
convenient member of the population. This obviously leads to some bias
since the characteristics possessed by the substituted unit will usually
be different from those possessed by the unit originally included in the
sample.
3.
Faulty demarcation of sampling units:
Bias due to defective demarcation of sampling units is particularly
significant in area surveys such as agricultural experiments in the field of
crop cutting surveys etc. In such surveys, while dealing with border line
cases, it depends more or less on the discretion of the investigator whether
to include them in the sample or not.
4.
Error due to bias in the estimation method:
Sampling method consists in estimating the parameters of the
population by appropriate statistics computed from the sample. Improper
choice of the estimation techniques might introduce the error.
5.
Variability of the population:
Sampling error also depends on the variability or heterogeneity of
the population to be sampled.
Sampling errors are of two types: Biased Errors and Unbiased Errors
71
Biased Errors:
The errors that occur due to a bias of prejudice on the part of the
informant or enumerator in selecting, estimating measuring instruments
are called biased errors. Suppose for example, the enumerator uses the
deliberate sampling method in the place of simple random sampling
method, then it is called biased errors. These errors are cumulative in
nature and increase when the sample size also increases. These errors arise
due to defect in the methods of collection of data, defect in the method of
organization of data and defect in the method of analysis of data.
Unbiased Errors:
Errors which occur in the normal course of investigation or
enumeration on account of chance are called unbiased errors. They may
arise accidentally without any bias or prejudice. These errors occur due to
faulty planning of statistical investigation.
To avoid these errors, the statistician must take proper precaution and
care in using the correct measuring instrument. He must see that the
enumerators are also not biased. Unbiased errors can be removed with the
proper planning of statistical investigations. Both these errors should be
avoided by the statisticians.
Reducing Sampling Errors:
Errors in sampling can be reduced if the size of sample is increased.
This is shown in the following diagram.
From the above diagram it is clear that when the size of the sample
increases, sampling error decreases. And by this process samples can be
made more representatives to the population.
Testing of hypothesis:
As a part of investigation, samples are drawn from the population
and results are derived to help in taking the decisions. But such decisions
involve an element of uncertainty causing wrong decisions. Hypothesis is
an assumption which may or may not be true about a population parameter.
For example, if we toss a coin 200 times, we may get 110 heads and 90 tails.
72
At this instance, we are interested in testing whether the coin is unbiased
or not.
Therefore, we may conduct a test to judge the significance o