Sie sind auf Seite 1von 44




Mrs.Manupriya Pragati Katiyar
Roll No- 28
Suchitra Shishu
Roll No- 47
Nopur Srivastava
Roll No- 26



Data Collection is an important aspect of any type of research
study. Inaccurate data collection can impact the results of a
study and ultimately lead to invalid results.
Data collection methods for impact evaluation vary along a
continuum. At the one end of this continuum are quantitative
methods and at the other end of the continuum are Qualitative
methods for data collection.

Data can com


Formal or informal
assessment data pr
baseline informatio
specific tasks. 3
Factors That Affect Data Collection

• Ease of data collection

• Unexpected events

• Frequency of data collected

• Learning curve for student

• Observer reliability

Elements of the
Data Collection Plan

1. Define criteria for performance of

identified task.

• Select a functional, frequently-occurring activity from

identified tasks.

• Identify present level of performance (baseline) for the

task and what change is expected with tool/strategy use.

• Define what success will look like for this student.

• Specify when and how the student will use the device(s)
in the activity and supports needed.

2. Specify the variable to be measured.

• What aspect of student performance are you trying to


– Accuracy/Quality
– Rate - speed/frequency/amount
– Spontaneity
– Duration
– Latency

3. Identify how the data will be recorded.

– Customized forms to collect data

– Checklists
– Tally sheets
– Creative ways to tally
– Journals or logs
– Collected work samples
– Software with tracking features

4. Identify schedule for data collection.

• Identify times, places, and duration of the trial.

• Collect data when it is most appropriate and reflects actual


• Specify how and who will collect data.

• Identify when and what team members will reconvene to

discuss data.

5. Analyze/discuss data collected.

• Teams should reconvene to review and discuss data, then

make decisions regarding appropriate tools/strategies.

• Plan for further intervention or data collection.

P o s s ib le o

A s s is tiv e te c h n o lo
im p r o v e s th e s tu’sd
p e r fo r m a n c e to w a


• Primary Data
• Secondary Data


Primary Data are those which are collected afresh and for the
first time and thus happen to be original in character.


The Secondary Data on the other hand are those which have
already been collected by someone else and which have
already been passed through the statistical process.

Primary Data Collection Methods

• Observation Method

• Interview Method

• Questionnaires & Schedules

• Other Methods

• Warranty Cards
• Distributor Audits
• Pantry Audits
• Consumer Panels
• Through Mechanical Devices
• Through Projective Techniques

Quantitative and Qualitative Data collection
The Quantitative data collection methods rely on random
sampling and structured data collection instruments that fit
diverse experiences into predetermined response categories.
They produce results that are easy to summarize, compare, and
Quantitative research is concerned with testing hypotheses
derived from theory and/or being able to estimate the size of a
phenomenon of interest. Depending on the research question,
participants may be randomly assigned to different treatments.
If this is not feasible, the researcher may collect data on
participant and situational characteristics in order to
statistically control for their influence on the dependent, or
outcome, variable. If the intent is to generalize from the
research participants to a larger population, the researcher will
employ probability sampling to select participants.
Typical quantitative data gathering strategies include:
• Experiments/clinical trials.
• Observing and recording well-defined events (e.g.,
counting the number of patients waiting in emergency at
specified times of the day).
• Obtaining relevant data from management information
• Administering surveys with closed-ended questions (e.g.,
face-to face and telephone interviews, questionnaires etc).

Qualitative data collection methods: play an important role
in impact evaluation by providing information useful to
understand the processes behind observed results and assess
changes in people’s perceptions of their well-being.
Furthermore qualitative methods can be used to improve the
quality of survey-based quantitative evaluations by helping
generate evaluation hypothesis; strengthening the design of
survey questionnaires and expanding or clarifying quantitative
evaluation findings. These methods are characterized by the
following attributes:
• they tend to be open-ended and have less structured
protocols (i.e., researchers may change the data collection
strategy by adding, refining, or dropping techniques or
• they rely more heavily on interactive interviews;
respondents may be interviewed several times to follow
up on a particular issue, clarify concepts or check the
reliability of data
• they use triangulation to increase the credibility of their
findings (i.e., researchers rely on multiple data collection
methods to check the authenticity of their results)
• generally their findings are not generalizable to any
specific population, rather each case study produces a
single piece of evidence that can be used to seek general
patterns among different studies of the same issue
Regardless of the kinds of data involved, data collection in a
qualitative study takes a great deal of time. The researcher
needs to record any potentially useful data thoroughly,
accurately, and systematically, using field notes, sketches,
audiotapes, photographs and other suitable means. The data

collection methods must observe the ethical principles of
The qualitative methods most commonly used in evaluation
can be classified in three broad categories:
• In-depth interview
• Observation methods
• Document review

Observation Method

• In this method the information is sought by way of

investigators on direct observation without asking from
the respondent.

• E.g. : In a study related to consumer behavior the

investigator instead of asking the brand of wrist
watch used by the respondent, may himself look at
the watch.

Observation involves recording the behavioral patterns of

people, objects and events in a systematic manner.
Observational methods may be:

Structured or unstructured
Disguised or undisguised
Natural or contrived
Participant, with the participant taking a number of different

Structured or unstructured:

In structured observation, the researcher specifies in detail

what is to be observed and how the measurements are to be
recorded. It is appropriate when the problem is clearly defined
and the information needed is specified.

In unstructured observation, the researcher monitors all

aspects of the phenomenon that seem relevant. It is appropriate
when the problem has yet to be formulated precisely and
flexibility is needed in observation to identify key components
of the problem and to develop hypotheses. The potential for
bias is high. Observation findings should be treated as
hypotheses to be tested rather than as conclusive findings.

Disguised or undisguised:

In disguised observation, respondents are unaware they are

being observed and thus behave naturally. Disguise is
achieved, for example, by hiding, or using hidden equipment or
people disguised as shoppers.

In undisguised observation, respondents are aware they are

being observed. There is a danger of the Hawthorne effect –
people behave differently when being observed.

Natural or contrived:

Natural observation involves observing behavior as it takes

place in the environment, for example, eating hamburgers in a
fast food outlet.

In contrived observation, the respondents’ behavior is

observed in an artificial environment, for example, a food
tasting session.


In personal observation, a researcher observes actual behavior

as it occurs. The observer may or may not normally attempt to
control or manipulate the phenomenon being observed. The
observer merely records what takes place.


Mechanical devices (video, closed circuit television) record

what is being observed. These devices may or may not require
the respondent’s direct participation. They are used for
continuously recording on-going behavior.

The observer does not normally question or communicate with
the people being observed. He or she does not participate.


In participant observation, the researcher becomes, or is, part of

the group that is being investigated. Participant observation has
its roots in ethnographic studies (study of man and races)
where researchers would live in tribal villages, attempting to
understand the customs and practices of that culture. It has a
very extensive literature, particularly in sociology
(development, nature and laws of human society) and
anthropology (physiological and psychological study of man).
Organizations can be viewed as ‘tribes’ with their own customs
and practices.
The role of the participant observer is not simple. There are
different ways of classifying the role:

Researcher as employee.
Researcher as an explicit role.
Interrupted involvement.
Observation alone.

Researcher as employee:
The researcher works within the organization alongside other
employees, effectively as one of them. The role of the
researcher may or may not be explicit and this will have
implications for the extent to which he or she will be able to
move around and gather information and perspectives from
other sources. This role is appropriate when the researcher
needs to become totally immersed and experience the work or
situation at first hand.
There are a number of dilemmas. Do you tell management and
the unions? Friendships may compromise the research. What
are the ethics of the process? Can anonymity be maintained?

Skill and competence to undertake the work may be required.
The research may be over a long period of time.

Researcher as an explicit role:

The researcher is present every day over a period of time, but
entry is negotiated in advance with management and preferably
with employees as well. The individual is quite clearly in the
role of a researcher who can move around, observe, interview
and participate in the work as appropriate. This type of role is
the most favored, as it provides many of the insights that the
complete observer would gain, whilst offering much greater
flexibility without the ethical problems that deception entails.

Interrupted involvement:
The researcher is present sporadically over a period of time, for
example, moving in and out of the organization to deal with
other work or to conduct interviews with, or observations of,
different people across a number of different organizations. It
rarely involves much participation in the work.

Observation alone:
The observer role is often disliked by employees since it
appears to be ‘eavesdropping’. The inevitable detachment
prevents the degree of trust and friendship forming between the
researcher and respondent, which is an important component in
other methods

Choice of roles:
The role adopted depends on the following:
• Purpose of the research: Does the research require
continued longitudinal involvement (long period of time),
or will in-depth interviews, for example, conducted over
time give the type of insights required?
• Cost of the research: To what extent can the researcher
afford to be committed for extended periods of time? Are
there additional costs such as training?
• The extent to which access can be gained: Gaining access
where the role of the researcher is either explicit or covert
can be difficult, and may take time.
• The extent to which the researcher would be comfortable
in the role: If the researcher intends to keep his identity
concealed, will he or she also feel able to develop the type
of trusting relationships that are important? What are the
ethical issues?
• The amount of time the researcher has at his disposal:
Some methods involve a considerable amount of time. If
time is a problem alternate approaches will have to be


• Structured

• Unstructured

Advantages of Personal Interview:

• More information and in greater depth.

• Interviewer by his own skills can over come the
resistance, if any.
• There is greater flexibility under this method as
restructuring of questions can be done.
• Observation method can also be applied with this method.
• The interviewer can control which persons will answer the

• The language of the interview can be adopted to the
ability or educational level of the person interviewed and
as such misinterpretations can be avoided

Telephonic Interview:

• These methods of collecting information consist of

contacting respondents on telephone itself.

Methods of Telephonic Interviewing:

• Central Location Telephone Interviews (CLTI).

• Computer Assisted Telephone Interviewing (CATI).
• Completely Automated Telephone Surveys (CATS).

Central Location Telephone Interviews

• For these interviews the interviewers make calls from a

centrally located marketing research facility to reach and
interview respondents.
• Wide Area Telecommunications Service (WATS) lines
are used for making the calls.

Computer Assisted Telephone Interviewing


• The process in which the telephonic interview responses

can be directly entered into the computer is known as
• The telephonic interviewer is seated at a computer
terminal and questions appear on the computer screen.

Completely Automated Telephone Surveys

• This process combines computerized telephone dialing

and voice activated computer messages which makes use
of Interactive Voice Response (IVR) technology to record
the responses of interviewees.


• It is more flexible in comparison to mailing method.

• It is faster.
• It is cheaper than personal interviewing method.
• Call backs are simple and economical.

• Replies can be recorded.
• No field staff is required.


• Little time is given to respondent for answers (not likely

to exceed 5 minutes in most cases).
• Service are restricted to respondents who have telephone
• Extensive geographical coverage may be restricted by cost
• Not suitable where comprehensive answer is required.
• Questions have to be short and to the point

Comparison of postal, telephone and
personal interview surveys
The table below compares the three common methods of
postal, telephone and interview surveys – it might help you to
decide which one to use.

Postal Telephone Personal

survey survey interview
Cost Often lowest Usually in- Usually
(assuming a between highest
response rate)
Ability to No personal Some Greatest
probe contact or chance for opportunity
observation gathering for
additional observation,
data building
through rapport, and
elaboration additional
on probing
but no
Respondent Yes Perhaps, Perhaps, if
ability to but usually interview
complete at no time is
own prearranged
convenience with

Interview bias No chance Some, Greatest
perhaps chance
due to
Ability to Least Some Greatest
decide who
responds to
the questions
Impersonality Greatest Some due Least
to lack of
Complex Least Somewhat More
questions suitable suitable suitable
Visual aids Little No Greatest
opportunity opportunity opportunity
Potential ‘Junk mail’ ‘Junk calls’ Invasion of
negative privacy
Interviewer Least Some in Greatest
control over selection of
interview time to call
Time lag Greatest Least May be
between considerable

soliciting and if a large
receiving area
response involved
Suitable types Simple, Some Greatest
of questions mostly opportunity opportunity
dichotomous for open- for open-
(yes/no) and ended ended
multiple questions questions
choice especially
if interview
is recorded
Requirement Least Medium Greatest
for technical
skills in
Response rate Low Usually High
Table 3.1: Comparison of the three common methods of

Questionnaire Method

• A questionnaire consist of a number of questions printed

or typed in a definite order on a form or set of forms.
• The questionnaire is mailed to respondents who are
expected to read and understand the questions and write
down the reply in the space meant for the purpose

Paper-pencil-questionnaires: can be sent to a large

number of people and saves the researcher time and money.
People are more truthful while responding to the questionnaires
regarding controversial issues in particular due to the fact that
their responses are anonymous. But they also have drawbacks.
Majority of the people who receive questionnaires don't return
them and those who do might not be representative of the
originally selected sample.

Web based questionnaires: A new and inevitably

growing methodology is the use of Internet based research.
This would mean receiving an e-mail on which you would
click on an address that would take you to a secure web-site to
fill in a questionnaire. This type of research is often quicker
and less detailed. Some disadvantages of this method include
the exclusion of people who do not have a computer or are
unable to access a computer. Also the validity of such surveys
are in question as people might be in a hurry to complete it and
so might not give accurate responses.


• There is low cost even when the universe is large and is

widely spread geographically.
• It is free from the bias of the interviewer; answers are in
respondents’ own words.
• Respondents have adequate time to give well thought out
• Respondents, who are not easily approachable, can also be
reached conveniently.
• Large samples can be made use of and thus the results can
be made more dependable and reliable.

• Low rate of return of the duly filled in questionnaires; bias
due to no-response is often indeterminate.

• It can be used only when respondents are educated and
• The control over questionnaire may be lost once it is sent.
• There is inbuilt inflexibility because of the difficulty of
amending the approach once questionnaires have been
• There is also the possibility of ambiguous replies or
omission of replies altogether to certain questions;
interpretation of omissions is difficult.
• It is difficult to know whether willing respondents are
truly representative.
• This method is likely to be the slowest of all.

Closed questions:
A question is asked and then a number of possible answers are
provided for the respondent. The respondent selects the answer
which is appropriate. Closed questions are particularly useful
in obtaining factual information:
Sex: Male [ ] Female [ ]

Did you watch television last night? Yes [ ] No [ ]

Some ‘Yes/No’ questions have a third category ‘Do not know’.
Experience shows that as long as this alternative is not
mentioned people will make a choice. Also the phrase ‘Do not
know’ is ambiguous:
Do you agree with the introduction of the EMU?
Yes [ ] No [ ] Do not know [ ]

What was your main way of traveling to the hotel? Tick one
box only.
Car [ ]
Coach [ ]
With such lists you should
Motor bike [ ]
always include an ‘other’
Train [ ] category, because not all
Other means, please specify possible responses might
have been included in the
list of answers.
Sometimes the respondent can select more than one from the
list. However, this makes analysis difficult:
Why have you visited the historic house? Tick the relevant
answer(s). You may tick as many as you like.

I enjoy visiting [ ]
historic houses
The weather was [ ]
bad and I could
not enjoy
I have visited [ ]
the house
before and
wished to
Other reason,
please specify


S o u rc e C a te

In te r n a l


The process of assigning numbers or labels to different

objects under study to represent them quantitatively or
qualitatively is called measurement.

A measurement scale can be defined as a set of numbers

or symbols developed in a manner so as to facilitate the
assigning of these numbers or symbols to the units under
research following certain rules.

Different types of measurement scales are:

Nominal scale
Ordinal scale
Interval scale
Ratio scale.

Nominal Scale:

A nominal scale uses numbers or letters so as to identify

different objects. The scale helps segregate data into categories
that are mutually exclusive and collectively exhaustive. This
scale assigns numbers to each of these categories and these
numbers do not stand for any quantitative value, and hence
they cannot be added subtracted or divided. For example, a
nominal scale designed to measure the nature of occupation
(employment status) may be given as below:

Occupation: - [1] Pubic sector

[2] Private sector
[3] Self employed
[4] Unemployed
[5] Others

In the above example, the numbers 1, 2, 3, 4, and 5 only

serve as labels to the various categories of employment status.
For a nominal scale the only quantitative measure is the
frequency of items appearing under each category. One can
only calculate the mode for the data collected using nominal

Ordinal Scale

An ordinal scale is used to arrange objects according to

some particular order. Thus, the variables in the ordinal scale
can be ranked. Ordinal variables can only give us the
information regarding relative position of the participants in the
observation, but they do not give any information regarding the
absolute magnitude of the difference between any two

For example, an ordinal scale used to measure the

preference of customers (in Delhi) for various mobile
telephone service providers on the basis of Ranking.

Airtel --------
Hutch -------- 1 => Most Preferred
Idea ------- 5=> Least Preferred
BSNL -------
Reliance ------

A respondent may Rank these players depending on his

experience perception of them. If a respondent ranks Airtel as I
and Idea as 2, a researcher can know that the respondent
prefers Airtel. However, the researcher cannot be sure as to
how strong the respondents’ liking is for Airtel when compared
to Idea.

Interval Scale

Interval scales are similar to ordinal scales to the extent

that they also arrange objects in a particular order. However, in
an interval scale the intervals between the points on the scale
are equal. This is the scale where there is equal distance
between the two points on the scale.
In Fahrenheit and Celsius scale the difference between
the intervals is the same i.e. the difference between 40°and 60°
is the same as the difference between 25° and 45°. But the base
point, freezing of water is represented by 32° F and 0° C. Thus
there is no natural zero (base) for these scales.
Similarly we can design an interval scale with points at an
interval of 1 point

[10] ---- [9] ----- [8] ------ [7] ------[6] ----- [5] ------[4]
------[3] -----[2] -------[1]

And ask the respondents to place the mobile telephone

service providers on this scale of 10 to 1. If Idea is assigned 8
and BSNL 4 we can say that the value of difference in
preference is 4. But we cannot say that the liking for Idea is
twice that for BSNL because we did not define a point of no
liking i.e. 0. Interval scales are suitable for the calculation of an
arithmetic mean, standard deviation, and correlation

Ratio Scale
Ratio scales have a fixed zero point and also have equal

A very good example of ratio scale is Distance; for

instance, not only can we say that the difference between 4
miles and 6 miles is the same as the difference between 6 miles
and 8 miles but we can also say that 8 miles is Twice as long as
4 miles.

Age, height, money scales are other common examples or

ratio scales. The data collected can be subjected to any type of
mathematical operation.



Researchers normally develop their own scales for

measuring variables for different attributes as it is very
difficult to find readily available scales. The scales that they
develop should primarily stand the tests of reliability,
validity, sensitivity, generalizability and relevance.

• Reliability

Reliability can be defined as the degree to which the

measurements of a particular instrument are free from errors
and as a result produce consistent results.
But sometimes the quality of the data may become poor if
the respondents
Do not understand the questions properly and they give
irrelevant answers to the researchers.

 Validity

The ability of a scale or a measuring instrument to measure

what it is intended to measure can be termed as the validity
of the measurement.

 Sensitivity

It refers to an instrument’s ability to accurately measure

variability in stimuli or

Responses. When there is a need to be more sensitive to
subtle changes, the instrument is altered appropriately.

 Generalizability

It refers to the amount of flexibility in interpreting the

data in different research designs.
The generalizability of a multiple item scale can be
analyzed by its ability to collect data from a wide variety of
respondents and with a reasonable flexibility to interpret
such data.
 Relevance

Relevance refers to the appropriateness of using a

particular scale for measuring a variable. It can be
represented as: Relevance = reliability * validity.


Scaling is the process of measuring quantitative aspects of

subjective or abstract concepts. It is a method to assign
numbers or symbols to some attributes of an object. It
involves developing a continuum, based on which measured
objects are located


 Uni-dimensional-: are used to measure one particular

attribute of an object.

 Multi-dimensional-: used to measure several attributes of

an object.


An attitude scale is a set of items (questions or statements)

that probe single aspects of human behaviour, attitudes or


 There are two major types of scales used to measure

the attitudes of respondents.

 Single item scales

 Multi-item scales

 Continuous scales


 Consist of Five sub types

 Likert scale
 Semantic scale
 Thurstone scale
 Associative scale
 Stapel scale