Data collection and tools

How to choose the method for data collection

1. Nature, scope and object of enquiry: This constitutes the most
important factor affecting the choice of a particular method. The
method selected should be such that it suits the type of enquiry that is
to be conducted by the researcher. This factor is also important in
deciding whether the data already available (secondary data) are to be
used or the data not yet available (primary data) are to be collected.
2. Availability of funds: Availability of funds for the research project
determines to a large extent the method to be used for the collection of
data. When funds at the disposal of the researcher are very limited, he
will have to select a comparatively cheaper method which may not be
as efficient and effective as some other costly method. Finance, in fact,
is a big constraint in practice and the researcher has to act within this
limitation.
3. Time factor: Availability of time has also to be taken into account in
deciding a particular method of data collection. Some methods take
relatively more time, whereas with others the data can be collected in a
comparatively shorter duration. The time at the disposal of the
researcher, thus, affects the selection of the method by which the data
are to be collected.
4. Precision required: Precision required is yet another important factor
to be considered at the time of selecting the method of collection of
data.

Rules for data collection

1) Use multiple data collection methods to ensure accuracy and avoid

biases.
2) Make sure that the data collection method is relevant.
3) Ensure that the data collection method is valid and thus measures
what the study intends to measure.
4) Secondary data can be used but researcher needs to be aware of
how the study was conducted, how the measures were defined, the
limitation of the data, how accurate the data is.
5) When collecting data through primary resources, researcher must
ensure, that the method is bias free, it is accurate, definitions of
the measures are unambiguous, the chosen method is relevant to
the study.

Data can be collected through a structured or a semi

structured approach.
1) Structured approach: this is used when the data being collected
needs to be measured emipirically and quantified. All the data is
collected in the same manner. This can be used for a large sample
or population. the researcher needs to be clear and have an
 accurate knowledge of what is being measured. This method also
allows to draw comparisions across different interventions.
2) Semi Structured Approach: this involves a systematic procedure
but the data is not collected in the exact same manner. It is more
fluid and open and thus gives more freedom to the researcher. The
researcher can further elaborate his study or ask for more details
when conducting research through this method. Participants are
also free respond in their own way to the research being
conducted. Semi strucuted method can be used in exploratory
research. It can be beneficial to gain an indepth understanding of
themes or issues or the different narratives of people. The
researcher using this method is aiming to not only gather the data
that the study intends to gather, but also gather information that is
unique and unexpected.

Characteristics of Good Measure

 Relevance: A measure or a method of collecting data is considered
to be good when it is relevant to the study. Based on the study the
method of data collection can vary. It can also influence the kind of
information received. Thus, it is important to choose a method that
is relevant and consistent with what is being studied. Eg: You
cannot choose survey method for getting an indepth
understanding of people’s psychological experiences during
partition because it will not yield effective results.
 Credible: The method needs to be credible. It needs to be a
systematic process which has been acknowledged by the scientific
community. It needs to be reasonable and logical.
 Validity: The measure needs to be valid. Measning it should
measure what the study aims to measure.
 Reliability: The test should be reliable in terms of its internal
consistency. Items needs to internally consistent with each other.

Qualitative vs Quantitative Approach

Shared screenshots

Triangulation

Triangulation in research means using multiple datasets, methods,

theories and/or investigators to address a research question. It’s a
research strategy that can help you enhance the validity and credibility
of your findings.

Types:
 Methodological triangulation: When you use methodological
triangulation, you use different methods to approach the same
research question. This is the most common type of triangulation,
and researchers often combine qualitative and quantitative
research methods in a single study. Methodological triangulation is
 useful because you avoid the flaws and bias that come with reliance on a
single research technique.
 Data triangulation: In data triangulation, you use multiple data
sources to answer your research question. You can vary your data
collection across time, space, or different people. When you collect
data from different samples, places, or times, your results are
more likely to be generalizable to other situations.
 Investigator triangulation: With investigator triangulation, you
involve multiple observers or researchers to collect, process, or
analyze data separately. Investigator triangulation helps you
reduce the risk of observer bias and other experimenter biases.

Purpose of Triangulation
To cross-check evidence
It’s important to gather high-quality data for rigorous research. When
you have data from only one source or investigator, it may be difficult to
say whether the data are trustworthy.
But if data from multiple sources or investigators line up, you can be
more certain of their credibility.
Credibility is about how confident you can be that your findings reflect
reality. The more your data converge, or or agree with each other, the
more credible your results will be.
For a complete picture
Triangulation helps you get a more complete understanding of your
research problem.
When you rely on only one data source, methodology, or investigator,
you may risk bias in your research. Observer bias may occur when
there’s only one researcher collecting data. Similarly, using just one
methodology means you may be disadvantaged by the inherent flaws
and limitations of that method.
It’s helpful to use triangulation when you want to capture the complexity
of real-world phenomena. By varying your data sources, theories, and
methodologies, you gain insights into the research problem from
multiple perspectives and levels.
To enhance validity
Validity is about how accurately a method measures what it’s supposed
to measure.
You can increase the validity of your research through triangulation.
Since each method has its own strengths and weaknesses, you can
combine complementary methods that account for each other’s
limitations.

Tools for Data Collection

Case Study: A case study in psychology is a descriptive research approach

used to obtain in-depth information about a person, group, or phenomenon. It is
different from survey research, which involves asking a group of participants
questions through interviews or questionnaires. Cast studies also tend to be far
more in-depth than observational research in that they use multiple measures
or records and focus on a single subject. (A multiple-case design can be used in
some instances.) Case studies may be prospective or retrospective; prospective
studies feature criteria that are established and include additional cases that
meet those criteria as they become available, while retrospective studies use
criteria to select cases from historical records. Case studies also tend to use
qualitative data, such as interviews, but may occasionally use quantitative data
as well, like questionnaires. They are often seen in clinical research, where the
treatment of a specific individual is monitored to determine what is effective.
Case studies use techniques such as personal interviews, direct
observation, psychometric tests, and archival records to gather
information. They are used to explore causation in order to find
underlying principles. However, they cannot be generalized to the overall
population, as can experimental research, and they cannot provide
predictive power, as can correlational research. Rather, they can provide
extensive information for the development of new hypotheses for future
testing, or about a rare or otherwise hard-to-study event or condition. As
such, they are often seen in clinical research, where the treatment of a
specific individual is monitored to determine what is effective.

Survey: Surveys are familiar to most people because they are so widely
used. This method enhances accessibility to subjects because they can be
conducted in person, over the phone, through the mail, or online, and are
commonly used by researchers to gather information on many variables in a
relatively short period of time.

Most surveys involve asking a standard set of questions to a group of

participants. In a highly structured survey, subjects are forced to choose
from a response set such as “strongly disagree, disagree, undecided,
agree, strongly agree”; or “0, 1-5, 6-10, etc.” One of the benefits of
having forced-choice items is that each response is coded so that the
results can be quickly entered and analyzed using statistical software.
While this type of survey typically yields surface information on a wide
variety of factors, they may not allow for an in-depth understanding of
human behavior.
Of course, surveys can be designed in a number of ways. Some surveys
ask open-ended questions, allowing each participant to devise their own
response, allowing for a variety of answers. This variety may provide
deeper insight into the subject than forced-choice questions, but makes
comparing answers challenging. Imagine a survey question that asked
participants to report how they are feeling today. If there were 100
participants, there could be 100 different answers, which is more
challenging and takes more time to code and analyze.
Surveys are useful in examining stated values, attitudes, opinions, and
reporting on practices. However, they are based on self-report, and this
can limit accuracy. For a variety of reasons, people may not provide
honest or complete answers. Participants may be concerned with
projecting a particular image through their responses, they may be
uncomfortable answering the questions, inaccurately assess their
behavior, or they may lack awareness of the behavior being assessed.
So, while surveys can provide a lot of information for many participants
quickly and easily, the self-reporting may not be as accurate as other
methods.

Rating Scales: Rating scale is defined as a closed-ended survey

question used to represent respondent feedback in a comparative form
for specific particular features/products/services. It is one of the most
established question types for online and offline surveys where survey
respondents are expected to rate an attribute or feature. Rating scale is
a variant of the popular multiple-choice question which is widely used to
gather information that provides relative information about a specific
topic.

Observation: The observational method involves the watching and

recording of a specific behavior of participants. In general, observational
studies have the strength of allowing the researcher to see for themselves how
people behave. However, observations may require more time and man-power
than other data collection methods, often resulting in smaller samples of
participants. Researchers may spend significant time waiting to observe a
behavior, or the behavior may never occur during observation. It is important to
remember that people tend to change their behavior when they know they are
being watched (known as the Hawthorne effect).

Observations may be done in a naturalist setting to reduce the likelihood

of the Hawthorne effect. During naturalistic observations, the
participants are in their natural environment and are usually unaware
that they are being observed. For example, observing students
participating in their class would be a naturalist observation. The
downside of a naturalistic setting is that the research doesn’t have
control over the environment. Imagine that the researcher goes to the
classroom to observe those students, and there is a substitute teacher.
The change in instructor that day could impact student behavior and
skew the data.
If controlling the environment is a concern, a laboratory setting may be a
better choice. In the laboratory environment, the researcher can manage
confounding factors or distractions that might impact the participants’
behavior. Of course, there are expenses associated with maintaining a
laboratory setting, increasing the cost of the study, that would not be
associated with naturalist observations. And, again, the Hawthorne effect
may impact behavior.
Interview: An interview is generally a qualitative research technique
which involves asking open-ended questions to converse with
respondents and collect elicit data about a subject. The interviewer in
most cases is the subject matter expert who intends to understand
respondent opinions in a well-planned and executed series of questions
and answers.
3 types of interviews
 Structured Interviews:
Structured interviews are defined as research tools that are extremely
rigid in their operations are allows very little or no scope of prompting
the participants to obtain and analyze results. It is thus also known as a
standardized interview and is significantly quantitative in its approach.
Questions in this interview are pre-decided according to the required
detail of information.
Structured interviews are excessively used in survey research with the
intention of maintaining uniformity throughout all the interview sessions.
They can be closed-ended as well as open-ended – according to the type
of target population. Closed-ended questions can be included to
understand user preferences from a collection of answer options
whereas open-ended can be included to gain details about a particular
section in the interview.
Advantages of structured interviews:
 Structured interviews focus on the accuracy of different responses
due to which extremely organized data can be collected. Different
respondents have different type of answers to the same structure
of questions – answers obtained can be collectively analyzed.
 They can be used to get in touch with a large sample of the target
population.
 The interview procedure is made easy due to the standardization
offered by structured interviews.
 Replication across multiple samples becomes easy due to the
same structure of interview.
 As the scope of detail is already considered while designing the
interview, better information can be obtained and the researcher
can analyze the research problem in a comprehensive manner by
asking accurate research questions.
 Since the structure of the interview is fixed, it often generates
reliable results and is quick to execute.
 The relationship between the researcher and the respondent is not
formal due to which the researcher can clearly understand
the margin of error in case the respondent either degrees to be a
part of the survey or is just not interested in providing the right
information.
Disadvantages of structured interviews:
 Limited scope of assessment of obtained results.
  The accuracy of information overpowers the detail of information.
 Respondents are forced to select from the provided answer
options.
 The researcher is expected to always adhere to the list of decided
questions irrespective of how interesting the conversation is
turning out to be with the participants.
 A significant amount of time is required for a structured interview.
Learn more: Market Research
 Semi-Structured Interviews:
Semi-structured interviews offer a considerable amount of leeway to the
researcher to probe the respondents along with maintaining basic
interview structure. Even if it is a guided conversation between
researchers and interviewees – an appreciable flexibility is offered to the
researchers. A researcher can be assured that multiple interview rounds
will not be required in the presence of structure in this type of research
interview.
Keeping the structure in mind, the researcher can follow any idea or take
creative advantage of the entire interview. Additional respondent
probing is always necessary to garner information for a research study.
The best application of semi-structured interview is when the researcher
doesn’t have time to conduct research and requires detailed information
about the topic.
Advantages of semi-structured interviews:
 Questions of semi-structured interviews are prepared before the
scheduled interview which provides the researcher with time to
prepare and analyze the questions.
 It is flexible to an extent while maintaining the research guidelines.
 Researchers can express the interview questions in the format
they prefer, unlike the structured interview.
 Reliable qualitative data can be collected via these interviews.
 Flexible structure of the interview.
Learn more: Quantitative Data
Disadvantages of semi-structured interviews:

 Participants may question the reliability factor of these
interviews due to the flexibility offered.
 Comparing two different answers becomes difficult as the
guideline for conducting interviews is not entirely followed.
No two questions will have the exact same structure and the
result will be an inability to compare are infer results.
 Unstructured Interviews:
Also called as in-depth interviews, unstructured interviews are usually
described as conversations held with a purpose in mind – to gather data
about the research study. These interviews have the least number of
questions as they lean more towards a normal conversation but with an
underlying subject.
The main objective of most researchers using unstructured interviews is
to build a bond with the respondents due to which there are high
chances that the respondents will be 100% truthful with their answers.
There are no guidelines for the researchers to follow and so, they can
approach the participants in any ethical manner to gain as much
information as they possibly can for their research topic.
Since there are no guidelines for these interviews, a researcher is
expected to keep their approach in check so that the respondents do not
sway away from the main research motive. For a researcher to obtain
the desired outcome, he/she must keep the following factors in mind:
 Intent of the interview.
 The interview should primarily take into consideration the
participant’s interest and skills.
 All the conversations should be conducted within permissible limits
of research and the researcher should try and stick by these limits.
 The skills and knowledge of the researcher should match the
purpose of the interview.
 Researchers should understand the do’s and don’ts of unstructured
interviews.
Advantages of Unstructured Interviews:
 Due to the informal nature of unstructured interviews – it becomes
extremely easy for researchers to try and develop a friendly
rapport with the participants. This leads to gaining insights in
extreme detail without much conscious effort.
 The participants can clarify all their doubts about the questions
and the researcher can take each opportunity to explain his/her
intention for better answers.
 There are no questions which the researcher has to abide by and
this usually increases the flexibility of the entire research process.
Disadvantages of Unstructured Interviews:
 As there is no structure to the interview process, researchers take
time to execute these interviews.
 The absence of a standardized set of questions and guidelines
indicates that the reliability of unstructured interviews is
questionable.
 In many cases, the ethics involved in these interviews are
considered borderline upsetting.

Psychometric Tests: Many variables studied by psychologists—perhaps the

majority—are not so straightforward or simple to measure. These kinds of
variables are called constructs and include personality traits, emotional states,
attitudes, and abilities. Psychological constructs cannot be observed directly.
One reason is that they often represent tendencies to think, feel, or act in
certain ways. For example, to say that a particular college student is highly
extroverted does not necessarily mean that she is behaving in an extroverted
way right now. Another reason psychological constructs cannot be observed
directly is that they often involve internal processes, like thoughts or feelings.
For these psychological constructs, we need another means for collecting data.
Tests will serve this purpose.

A good test will aid researchers in assessing a particular psychological

construct. What is a good test? Researchers want a test that is
standardized, reliable, and valid. A standardized test is one that is
administered, scored, and analyzed in the same way for each participant.
This minimizes differences in test scores due to confounding factors,
such as variability in the testing environment or scoring process, and
assures that scores are comparable. Reliability refers to the consistency
of a measure. Researchers consider three types of consistency: over
time (test-retest reliability), across items (internal consistency), and
across different researchers (interrater reliability). Validity is the extent
to which the scores from a measure represent the variable they are
intended to. When a measure has good test-retest reliability and internal
consistency, researchers should be more confident that the scores
represent what they are supposed to.
There are various types of tests used in psychological research. Self-
report measures are those in which participants report on their own
thoughts, feelings, and actions, such as the Rosenberg Self-Esteem Scale
or the Big Five Personality Test. Some tests measure performance,
ability, aptitude, or skill, like the Stanford-Binet Intelligence Scale or the
SATs.There are also tests that measure physiological states, including
electrical activity or blood flow in the brain.

Focus group: focus group is a carefully planned discussion that is

designed to obtain perceptions about a defined area of interest in a
permissive and nonthreatening environment. It can be used to explore a
multitude of issues, and it is a very popular technique in the worlds of
both market research and psychology. Although there is much to be said
about focus groups, given their widespread use, three topics will be
emphasize here: (a) focus group basics, (b) other important factors, and
(c) applications of focus groups.