RESEARCH METHODS course

Dr. PETER NUWAGIRA

E-mail: pnuwagira@gmail.com
Mob : +256-788664972

1
DATA COLLECTION METHODS
Data collection methods
Session flow
 Introduction
 Secondary data vs. primary data
 Survey methods
 Survey instruments(the
questionnaire)
 Non-survey methods(observation)
 Secondary data
 Secondary data – data someone else
has collected.
 Examples
 Census
 Budgets-public, corporate etc
 Household surveys
 Hospital records
 Diaries
 Secondary data
Limitations
 When was it collected? For how long?
 May be out of date for what you want to
analyze.
 May not have been collected long enough
for detecting trends.
 E.g. Have new anticorruption laws
impacted
 Secondary data
Limitations
 Is the data set complete?
 There may be missing information on
some observations
 Unless such missing information is
caught and corrected
 Secondary data
Limitations
 Is the information exactly what you
need?
 In some cases, may have to use “proxy
variables” – variables that may approximate
something you really wanted to measure.
Are they reliable? Is there correlation to
what you actually want to measure?
 Secondary data
Advantages
 No need to reinvent the wheel.
 If someone has already found the data,
take advantage of it.
 Secondary data
Advantages
 It will save you money.
 Even if you have to pay for access, often
it is cheaper in terms of money than
collecting your own data. (more on this
later.)
 Secondary data
Advantages
 It will save you time.
 Primary data collection is very time
consuming. (More on this later,
 Secondary data
Advantages
 It may be very accurate.
 When especially a government agency
has collected the data, incredible
amounts of time and money went into it.
It’s probably highly accurate
 Secondary data
Advantages
 It has great exploratory value
 Exploring research questions and
formulating hypothesis
 Primary data
Primary data – data you collect
 Examples
 Surveys
 Focus groups
 Questionnaires
 Personal interviews
 Experiments and observational study
 Primary data
Limitations
 Do you have the time and money for:
 Designing your collection instrument?
 Selecting your population or sample?
 Pretesting/piloting the instrument to
work out sources of bias?
 Administration of the instrument?
 Entry/collation of data?
Primary data
Limitations
 Researcher error
 Sample bias
 Other confounding factors
 Data collection choice
 What you must ask yourself:
 Will the data answer my research
question(s)?
Data collection choices
 To answer that
 You must first decide what your research question is
 Then you need to decide what data/variables
are needed to scientifically answer the question
 Data collection choice
 If that data exist in secondary form,
then use them to the extent you can,
keeping in mind limitations.
 But if it does not, and you are able to
fund primary collection, then it is the
method of choice.
 Obtrusive vs. unobtrusive methods

Data can be collected unobtrusively or

obtrusively
 Unobtrusively: methods of studying
social phenomena without affecting it.
 e.g. Content analysis; statistical
analysis; historical comparative analysis
 Obtrusively: methods that affect the
social phenomena being studied.
Methods of data collection

 Surveys
 Nonsurveys
 Data collection methods
Surveys
 What is a survey?
 Means of collecting quantitative data
from a particular population about a
particular topic
 May be structured or unstructured
 Data collection methods
Types of surveys
 Personal interview(face- to- face).
 Mail
 E-mail
 Telephone
 Surveys
Personal interviews
 Conversation with a purpose
 Persons selected to be part of the
sample are interviewed in person by
trained interviewer
 The interview could be formal/
structured or unstructured/informal
 Surveys
Personal interviews
 Where conducted
 Door-to-door-interviews conducted at
respondents’ houses
 Mall Intercept Interviews-intercepting
respondents at a central location in a
shopping mall
 Prearranged meetings-interviewing
respondents at other mutually agreed
upon places
 Survey methods
Personal interviews
 Advantages
 Cooperation from respondents
 Interviewer can answer questions about
the survey
 Allows for probes
 Respondents can be prescreened to
ensure they fit the population profile
 Surveys
Personal interviews
 Advantages cont.
 High response rate
 Possibility of using visual aids and props
 Most appropriate method for studying
attitudes, values, beliefs and motives
Survey methods
Personal interviews
 Disadvantages
 High costs
 Longer time
 Some respondents unwilling to talk
 Some neighbourhoods are difficult to
visit
 Surveys
Interviews
 Disadvantages cont.
 Less anonymous
 Interview rules are rigid
 Survey
Self-administered surveys
 Respondents are responsible for
reading and filling questionnaire
 Present special challenges-reliance on
the efficiency of the written word rather
than skill of the interviewer
 Classed into paper-based(printed) or
electronic(non-printed)
 Surveys cont.
Mail
 Paper(printed) self-administered
questionnaire
Distribution methods
 Mail or postal survey using regular mail
system( now called “Snail Mail Survey”
 Drop off/pick-up method
 Fax surveys
 Inserts, e.g. news papers, product
packages, etc
 Direct distributions e.g. in buses,
restaurants, banks
Surveys
Mail cont.
 Advantages
 “Questionnaires can be sent through
the mail, interviewers cannot”
 Lower cost
 Reduction of biasing error
 Greater anonymity
 Considered answers and consultations
 Geographic flexibility-accessibility
 Surveys cont.
The Mail survey cont.
Disadvantages
 Requires simple questions
 No opportunity for probe
 No control over who fills the
questionnaire
 Lower response rates
 Surveys
Mail cont.
 Response issues
 Response rate:
 Number of completed and
returned questionnaires divided
by number of eligible people
contacted.
 Survey
Mail cont.
 Methods of increasing response rate
 Cover letter-study importance, request
for help, importance of respondent,
promise of confidentiality etc
 Rewards(monetary and nonmonetary)
 Advance notification
 Survey
Mail cont.
 Methods of increasing response rate
 Advance notification
 Follow-ups
 Prestige of sponsoring institution
 Colour of questionnaire paper
 Type of postage
 Interesting questions
 Survey
Electronic questionnaire
 Distribution methods
1.E-mail
2.Internet
 Surveys
Electronic survey
 Advantages
 Speed of distribution
 Low cost
 Wide coverage
 Medium response rate
 Faster response time
 Greater flexibility
 Less handling of paper
 Survey
Electronic mail survey
 Disadvantages
 Lack of security(eavesdropping)
 Lack of anonymity
 Differences in respondents’
computer and e-mail software
 Surveys
Telephone interview
Interviewer-administered interviews
that are conducted over the
telephone.
Telephone interviews are the most
widely used method in commercial
survey research
 Surveys
Telephone Interviewing Systems
Central Location Interviewing.
Computer-Assisted Telephone
Interview.
Computerized Voice-Activated
Telephone Interviewing.
 Surveys
Telephone
(a) Central Location Interviewing:
Conducting telephone interviews from a
single central location from which all
interviewers work
 Usually through WATS (Wide Area
Telecommunications Service) contracts that
provide fixed long-distance rates, and
allow unlimited calls within a specific
geographic area.
Surveys
(b)Computer-Assisted Telephone Interviewing
(CATI):
Telephone interviewing system in which the
interviewer reads questions from a computer screen
and enters the answers directly into the computer
 Surveys
(b) cont.
 Usually incorporate telephone
management systems that handle:
 Phone number selection.
 Automatic dialing.
 Sample selection.
 Automatic callback scheduling.
 Reporting on number of completed
interviews.
 Surveys
(c) Computerized Voice-Activated
Telephone Interviews
 Computer assumes responsibility for
all aspects of the interview
administration
 It dials the respondent, asks the
questions, and records the
responses.
Surveys
Telephone
 Advantages
 Relatively high speed of data
collection.
 Inexpensive compared to personal
interviews.
Survey
Telephone
Advantages
 Better respondent anonymity than
personal interviews.
 Relatively higher respondent
cooperation
 lower non-response compared to
personal interviews.
 Inexpensive
Surveys
 Disadvantages
 Problems in getting representative
samples; unlisted phone numbers.
 Problem of answering machines & faxes.
 Need for callbacks.
 Respondent can easily hang up.
 Inability to use visual aids.
 Need for shorter forms of questioning.
Questionnaire
 Research instrument consisting of a series of
questions and other prompts for the purpose of
gathering data from respondents. The
questionnaire was discovered by Sir Francis
Galton.
 A survey instrument
 Surveys
Survey instruments
 Three types of questionnaires
 A set of questions, which are used to
elicit information from a respondent.
 Interview schedule or response
schedule.
 Interview Guide – a set of topics and or
questions about which the interview is
conducted
 Questionnaire
 Questionnaires can also be classified
by the way they are administered.
 Personally administered
 Mailed questionnaires
 Questionnaire

Advantages
 It is generally cheaper than other
methods of data collection.
 It avoids problems associated with
interviews e.g. response errors
 Easy for people to answer personal
questions
 Questionnaire
Limitations
 Can only be used where the questions
are simple and answers
straightforward
 The answers to mail questionnaires
have to be accepted as final
 Inappropriate where spontaneous
answers are needed
 Questionnaire
Limitations
 Cannot ensure that the person
selected actually filled the
questionnaire
 No opportunity to supplement
respondents observations
 Non-response
 Basic principles on questionnaire
construction
 Four major decision areas
1.Question content
2. Question wording
3. Response structure
4. Question sequence
 Questionnaire
1. Question content
 Should the question be asked?
 Scope and coverage?
 Can respondent answer adequately?
 Will respondent answer willingly?
 Questionnaire construction
2.Questionnaire wording
 Shared vocabulary
 Clarity(any, could, should, fair, near,
often ,average)
 Biased wording e.g. fundamentalist,
politically correct
 Personalisation.e.g. What would you do
about…?or What should people do about?
 Questionnaire construction
3. Response structure
 From open(free choice of words) to
closed(specified alternatives)
 Closed responses are categorized
as dichotomous or multiple
choice.
 Questinnare
 Type of question open or closed
 Open-ended questions
E.g. What is the main reason for you
to consult your lecturer?
Advantages Disadvantages
-Complete answers -coding
-Find unanticipated
ideas
Questinnaire
 Closed-ended
E.g. Think of the last time you had
homework assignment. Did you consult
a lecturer?
 Yes/No
Advantages Disadvantages
-Easy to code -Limits response
-Rater reliability -Some alternative
may not apply
Questionnaire
4.Question sequence
 Each question should be related to the others
 Must quickly awaken interest and motivate
respondent
 Early questions should not be seen as personal
 Begin from simple to complex or from general to
specific
 Questionnaire scales
Self report Response scales
 Numerical scales
 Semantic differential
 Graphic rating scales
 Behaviorally anchored scales
 Forced choice
 Likert Scale
 Questionnaire
Numerical
 Any rating scale in which numbers
rather than semantic space or verbal
descriptions are used as response
options
Questionnaire
 Numerical rating scale
Examples:
Poor Excellent
Durability 1 2 3 4 5 6 7

Durable 1 2 3 4 5 6 7 Not durable

 Questionnaire
Graphic
 Rating scales in which respondents
rate an object on a graphic
continuum, usually a straight line.
 Modified versions are the ladder scale
and happy face scale.
 Questionnaire
Graphic
 Example:
Rate each employee on this scale
 5 = Outstanding – one of the best
 4 = Above average
 3 = Average
 2 = Needs improvement
 1 = Unsatisfactory
 6 = Not applicable
 Questionnaire
Behaviorally anchored scale
 Combines traditional rating scales and
critical incidents methods
Questionnaire
 Example
 7 = can be expected to come to work 5
days a week
 5= can be expected to inform supervisor
in the event of absenteeism
 3 = can be expected to miss 2-3 days
per month
 1 = expected to come to work randomly
 Questionnaire
Likert Scale
 A multiple item rating scale in
which the degree of an attribute
possessed by an object is
determined by asking respondents
to agree or disagree with a series
of positive and/or negative
statements describing the object.
 Questionnaire
Semantic differential
 A rating scale in which bipolar
adjectives are placed at both ends
(or poles) of the scale, and
response options are expressed as
“semantic” space.
Questionnaire
Example:
Please rate car model A on each of the following
dimensions:
Durable ---:-X-:---:---:---:---:--- Not durable
Low fuel consumption ---:---:---:---:---:-X-:--- High
fuel consumption
 Questionnaire
Likert scale
 A multiple item rating scale in
which the degree of an attribute
possessed by an object is
determined by asking respondents
to agree or disagree with a series
of positive and/or negative
statements describing the object.
 Questionnaire

 Likert

AttitudetowardbuyingfromtheInternet
Totally Totally
disagree Disagree Neutral Agree agree
a) ShoppingtakesmuchlongerontheInternet [ ] [ ] [ ] [ ] [ ]
b) Itis agoodthingthatSaudiconsumershave
theopportunity tobuyproductsthroughthe [ ] [ ] [ ] [ ] [ ]
c) BuyingproductsovertheInternetis nota
sensiblethingtodo [ ] [ ] [ ] [ ] [ ]
 Questionnaire
Forced choice
 presents sets of statements
describing behavior; you choose
must choose which statement is most
characteristic of the and which is
least characteristic.
 e.g.
 Very bad, bad, neither good nor bad,
good, very good
Nonsurvey methods- Observation

 Observation: few options available for studying

records, lower animals, small children, or
complex interactive processes
 Data gathered as the event occurs and closer
to it than questioning
 Must be present to catch the event or have som
recording device on the scene
 Observation
 Observation important to
 Nonverbal behaviours
 Spatial behaviour-attempts of individuals
to structure the space around them
 Extra-linguistic behaviour-rate of
speaking, loudness, tendency to
interrupt, pronunciation peculiarities
 Types of observation
 Controlled observations
 Laboratory experimentation
 Field experimentation
 Participant observation
 Observation
 There is a continuum in observation
techniques between the covert and
the overt observer, and the observer
who participates completely in the
activity and the one who is purely a
"fly on the wall".
Observation
 Biases in observation
 Recording error
 Memory lapse
 Errors in interpreting activities,
behaviours, events or non-verbal
clues.
 Where several observers are
involved, inter-observer reliability
may cause error.
 Fatigue boredom.
 Observation
Strengths of observation
 Securing information about people
and activities that cannot be done
through surveys
 Avoiding respondents' filtering and
forgetting
 Securing environmental context
information
 Observation
Strengths cont.
 Optimizing the naturalness of the
setting
 Directness-study behaviour as it
occurs, no need to ask questions
 Observation
Limitations
 Waiting for long go capture relevant
phenomena
 Costly
 Reliability of inference from surface
indicators
 Problem of quantification-large data
 Respondent introduced error
END