Unit 4: Data Collection

 Primary Data Sources are original works of research or raw data

without interpretation or pronouncement that represents an official
opinion or position.
 Memos, letters, interviews, speeches, laws, regulations, court
decisions or standards, most government data such as census,
economic and labour data.
 Primary sources are more authoritative because the information has
not been filtered or interpreted by a second party.
 Internal sources of primary data would include inventory records,
personnel records, purchasing requisition forms, statistical process
control charts, etc.
 Secondary data sources are interpretations of primary
data.
 Encyclopedias, textbooks, handbooks, magazine and
newspaper articles and newscasts. All reference materials,
sales analysis summaries, investor annual reports are
compiled from a variety of primary sources.
 Tertiary sources may be interpretation of a secondary source but
generally are represented by indexes, bibliographies, and other
finding aids (Internet search engines).
 It is important to remember that - All information is not of equal
value. As the source level indicate, primary sources have more
value than secondary sources, and secondary sources have more
value than tertiary sources.
Primary Data Collection Methods

Observations

Survey

Interview and Questionnaire

Observations
 Observation qualifies for scientific inquiry when it is conducted
specifically to answer a research question, is systematically planned
and executed, uses proper controls, and provides a reliable and valid
account of what happened.
 The versatility of observation makes it an indispensable primary
source method.
 Besides collecting data visually, observation involves listening,
reading, smelling, and touching.
 Observation includes full range of monitoring behavioural and non-
behavioural activities and conditions.
Behavioural Observation
 Nonverbal analysis-body movement; motor expressions; exchanged glances
 Linguistic analysis-tally of ahs or other annoying sounds or words a professor
makes or uses during a class; study of a sales presentations content or the study
of what, how, and how much information is conveyed in a training situation;
interaction processes that occur between two or more people
 Extralinguistic analysis- The four dimensions are 1. vocal, including pitch,
loudness and timbre; 2. temporal, including the rate of speaking, duration of
utterance, and rhythm; 3. interaction, including tendencies to interrupt,
dominate, or inhibit and 4. Verbal stylistic, including vocabulary and
pronunciation peculiarities, dialect, and characteristic expressions.
 Spatial analysis –how a person relates physically to others. One form of this
study, proxemics, concerns how people organize the territory about them and
how they maintain discrete distances between themselves and others.
Non-behavioural Observation

 Record analysis – historical /current; public/private; written,

printed, sound-recorded, photographed, or video taped; content
analysis of competitive advertising and analysis of personnel
records.
 Physical condition analysis – store audits of merchandise
availability; studies of plant safety compliance; analysis of
inventory conditions; analysis of financial statements
 Physical process analysis –time and motion studies; analysis of
traffic flows in a distribution system; paperwork flows in an office;
financial flows in the banking system
Evaluation of Observation Method
 It is the only method available to gather certain types of information
such as study of records, mechanical processes and young children, etc.
 We can collect the data at the time they occur.
 We can secure information that most participants would ignore either
because it is so common and expected or because it is not relevant.
 It alone can capture the whole event as it occurs in its natural
environment .
 Participants seem to accept an observational intrusion better than they
respond to questioning.
 It is also possible to conduct disguised and unobtrusive observation
studies much more easily than disguised questioning.
Limitations of the Observation Method
 The limitations are the observer normally must be at the scene of the event
when it takes place, yet it is often not possible.
 Observation is a slow and expensive process that requires either human
observers or costly surveillance equipment.
 Its most reliable results are restricted to information that can be learned by
overt action or surface indicators. To go below the surface, the observer
must make inferences.
 The research environment is more likely suited to subjective assessment
and recording data than to controls and quantification of events.
 Observation is limited as a way to learn about the past or distant place.
 It is difficult to gather information on such topics as intentions, attitudes,
opinions, or preferences.
Classification of Observation in terms of
Observer-Participant Relationship
The observation may be viewed from three perspectives:
1. Is the observation direct or indirect?
2. Is the observer’s presence known or unknown?
3. Is the observer a participant or non-participant?
Research Process and Design of an observation
study
 Investigative questions
 Measurement questions
 Research Design
 Select type of observation
 Prepare error reduction plan
 Prepare observation checklist and Design Observer Training
 Select sample element an schedule observation and train observers
 Collect and Process Data and verify observation protocol
Surveys
 We can gather primary data through observation and communication method.
 Attitudes, motivations, intentions, expectations and information about past events
which cannot be revealed through observation method, can be obtained through
surveying and interviewing people.
 A survey is a measurement process used to collect information during a highly
structured interview-sometimes with a human interviewer and other times
without.
 Questions are carefully chosen or crafted, sequenced, and precisely asked of each
participant.
 The goal of the survey is to derive comparable data across subsets of the chosen
sample so that similarities and differences can be found.
Merits and Demerits of Survey

Merits:
 It is versatile. Abstract information of all types can be gathered by questioning others
 A few well-chosen questions can yield information that would take much time and effort to
gather by observation
 A survey that uses the telephone, mail, a computer, email, or the internet as the medium of
communication can expand geographic coverage at a fraction of the cost and time required
by observation.
Demerits:
 All communication research has some error.
Errors in Communication Research (Surveys &
Interviews)
Three major sources of error in communication research:

1. Measurement questions and survey instruments

2. Interviewers
3. Participants
Measurement questions error

 select or craft wrong questions;

 asked in inappropriate order;
 inappropriate instructions
Interviewer error

 Failure to secure full participant cooperation;

 failure to record answers accurately and completely;
 failure to consistently execute interview procedures;
 Failure to establish appropriate interview environment;
 Falsification of individual answers or whole interviews
 Inappropriate influencing behaviour
 Physical presence bias
Participant Error

Three factors influence participation:

The participant must believe that-
1. The experience will be pleasant and satisfying
2. The answering the survey is important and worthwhile of his/her
time
3. The participant must dismiss any mental reservations that he or she
might have about participation.
Communication Methods

1. Self-administered surveys or computer delivered self-administered

questionnaires; intercept surveys at malls, conventions
2. Survey via Telephone Interview – they are cost effective and long
distance interviewing is possible
3. Survey via personal interview – the ability to explore topics in
great depth, achieve a high degree of interviewer control, and
provide flexibility, however it is costly and time consuming
Qualitative Techniques for Data Collection

The interview is the primary data collection technique for gathering

data in qualitative methodologies.
Interviews vary based on the number of people involved during the
interview, the level of structure, the proximity of the interviewer to the
participant, the number of interviews conducted during the research.
An interview can be conducted individually (individual depth
interview) or in groups.
Interviews
 The researcher chooses either an unstructured interview (no specific questions or
order of topics to be discussed, with each interview customized to each
participant; generally, starts with a participant narrative) or
 a semi-structured interview (generally starts with a few specific questions and
then follows the individual’s tangents of thought with interviewer probes) or
 a structured interview (often uses a detailed interview guide similar to a
questionnaire to guide the question order and the specific way the questions are
asked, but the questions generally remain open-ended). Structured interviews
permit more direct comparability of responses; question variability has been
eliminated and thus, answer variability is assumed to be real. Also, Interviewer’s
neutrality is maintained.
 Most qualitative research relies on unstructured and semi-structured
interview.
 Many interviews are conducted face-to-face, with the obvious
benefit of being able to observe and record non-verbal behaviour.
 It can also be conducted by phone and online. Phone and online
interviews offer the opportunity to conduct more interviews within
the same time frame and draw participants from a wider geographic
area. There is savings on travel expenses. Non availability of
participants also force the use of phone and online techniques.
 Projective Techniques used in Interviews
 Word and picture association  Imaginary universe
 Sentence completion  Visitor from another planet
 Cartoons or empty balloons  Personification
 Thematic Apperception Test  Authority figure
 Component Sorts  Ambiguities and paradoxes
 Sensory sorts  Semantic mapping
 Laddering or benefit chain  Brand mapping
 Imagination exercises
Individual Depth Interviews (IDI)
 An individual depth interview is an interaction between an individual interviewer
and a single participant. IDI generally take between 20 mins (telephone
interviews) and 2 hours (prescheduled, face-to-face interviews) to complete,
depending on the issues or topics of interest and the contact method used. Some
techniques such as life histories may take as long as five hours. Participants are
usually paid to share their insights and ideas. Interviewees are often provided
with advance materials via mail, fax, or the internet. Advances in technology
have enabled computer-assisted personal interviews.
 Unstructured individual depth interviews are common in marketing research,
including oral histories, cultural interviews, life histories, etc.
 Participants are chosen because their experiences and attitudes will
reflect the full scope of the issue under study. Participants need to
be articulate to provide the desired detail.
 Purposive sampling is used to select the participants.
 IDIs are usually recorded and transcribed to provide the researcher
with the rich detail that the methodology is used.
 IDIs take extensive interviewer time in conducting and analysing
and evaluating the data collected.
Group Interviews

 A group interview is a data collection method using a single

interviewer with more than one research participant.
 Group interviews can be described by -
 group’s size – dyads (2 people); triads (3 people); mini-groups (2 to
6 people); small groups (focus groups-6 to 10 people); and
supergroups (up to 20 people) and
 group’s composition – heterogeneous or homogenous; experts or
non-experts
Merits and demerits of Group Interviews

 Group interviews are one of the few research techniques in which the participants
are encouraged to interact. However, given time constraints, group interviews
permit spending only limited time extracting detail from each participant.
 Another difficulty is recruiting, arranging, and coordinating group discussions.
But this problem can be solved by engaging the services of a specialist researcher.
 Interviewers have the challenge of managing the group’s conversation while
avoiding interjecting themselves into the group’s process. The extroverts and
dominant personalities need to be controlled to ensure meaningful contribution
from all.
 An interviewer may create bias by his verbal and non-verbal cues thus directing
the discussions elsewhere.
Focus Groups
 The focus group is a panel of people, led by a trained moderator, who meet for 90 minutes
to 2 hours. The facilitator or moderator uses group dynamics in an exchange of ideas,
feelings and experiences on a specific topic.
 Focus groups are often unique in research due to the research sponsor’s involvement in the
process. Most permit the sponsor to observe the group and its dynamics in real time, and
also allow the client to supply the moderator with new topics or questions that are
generated by those observing in real time.
 Facilities provide for isolation do avoid distractions. Some facilities allow product
preparation and testing, as well as creative exercises like free association, picture sort,
photo sort, role plays, etc.
 They are often used as an exploratory technique but may be a primary data collection
method.
 There are telephone focus groups, online focus groups and videoconferencing focus groups
Case Study Method
 The case study method, also referred to as the case history, is a powerful research
methodology that combines individual and group interviews with record analysis and
observation. Researchers extract information from company brochures, annual reports,
sales receipts, and newspaper and magazine articles, along with direct observation (usually
done in the participant’s natural setting), and combine it with interview data from
participants. The objective is to obtain multiple perspectives of a single organization,
situation, event, or process at a point in time or over a period of time.
 Case study methodology or case analysis or case write-up can be used to understand
particular marketing processes.
 The research problem is usually a how and why problem, resulting in a descriptive or
explanatory study.
 Researchers select the specific organizations or situations to profile
because these examples or subjects offer critical, extreme, or
unusual cases.
 Researchers most often choose multiple subjects, rather than a
single subject, to study because of the opportunity for cross-case
analysis. In studying multiple subjects, a deeper understanding of
the subject emerges.
 In the case study, interview participants are invited to tell the story
of their experience.
 The flexibility of this approach and the emphasis on understanding
the context of the subject being studied allow for a richness of
understanding.
Action Research
 Action research is designed to address complex, practical problems about which
little is known-thus no known heuristics exist.
 So the scenario is studied; a corrective action is determined, planned and
implemented; the results of the action are observed and recorded; and the action is
assessed as effective or not.
 The process is repeated until a desired outcome is reached, but along the way
much is learned about the processes and about the prescriptive actions being
studied.
 Action researchers investigate the effects of applied solutions.
 Whatever, theories are developed are validated through practical application.
Merging Qualitative and Quantitative
Methodologies
 Triangulation is the term used to describe the combining of several
qualitative methods or combining qualitative with quantitative
methods.
 This increases the perceived validity of the research, especially
when a quantitative study follows a qualitative one and provides
validation for the qualitative findings.
Questionnaire Design

 Meaning
 Process of Designing Questionnaire
Secondary Data Sources

 Advantages
 Disadvantages
Measurement and Scaling Techniques