Chapter six

Data Collection and Analysis

 Data Collection (a)
➢ Data refer to:
o facts, figures and other relevant materials, past
and present, serving as the basis for study,
analysis and conclusion.
➢ The search for answers to research questions calls for
collection of data.
➢ depends mainly upon the nature, purpose and
relevance to the subject matter of the study.
➢ data collection begins after a research problem has
been defined and research design/plan done.
Importance of Data
➢ Data serve as the bases or raw materials for analysis.
➢ Without an analysis of factual data, no specific
inferences can be drawn on the questions under study.
➢ The relevance, adequacy and reliability of data
determine the quality of the findings of a study.
➢ Thus, the scientific process of measurement, analysis,
testing and inferences depends on the availability of
relevant data and their accuracy.
 Sources of data
➢ Sources of data mainly refer to the type of data
required and how to access them.
➢ There are two types of data that are collected and
analyzed in research endeavors. These are:
 Secondary data
 Primary data
Secondary Data
• Secondary data refer to the data which have already
been collected and analyzed by some one else.
• Secondary data are collected by others and used for a
different purpose.
• The sources of secondary data can broadly be classified
into two categories:
➢ Published sources, and
➢ Unpublished sources
Advantages of Secondary Data
• Easily Accessible
• Relatively Inexpensive
• Quickly Obtained
• Better define the problem
• Formulate an appropriate research design
Disadvantages of Secondary Data
• Usefulness to the current problem may be limited
• Irrelevant
• Inaccurate
Primary Data
• Primary data are original observations collected by the
researcher or his agents for the first time and used in
the statistical analysis.
• are those data which are collected afresh and thus
happen to be original in character.
• collected through various methods such as observation,
surveys, interviews, experimentation, focus group
discussion, etc.
Survey Research
➢ A survey is a process of gathering information for statistical
analysis to the benefit of a group of individuals
➢ Survey refers to the collection, recording and analysis of data
on a particular subject, an area or a group of people.
➢ Questionnaire implies a form containing a list of ready-
made questions, delivered to people for obtaining statistical
information.
➢ Survey is a process of collecting and analyzing data, whereas
questionnaire is instrument of data collection
➢ Survey requires expert and imaginative planning, careful
analysis and rational interpretation of the findings.
The Questionnaire
• A questionnaire is defined as a formalized instrument for
collecting data from respondents
• A series of predetermined questions related to research questions
and/or objectives.
• Are to be completed by respondents.
• Advantages:
➢ lower costs
➢ large samples
➢ standardization
➢ respondent privacy (anonymity)
➢ It is free from the bias of the interviewers, answers are in
respondents own words
➢ Respondents have adequate time to give well thought answers.
➢ Respondents, who are not easily approachable, can also be
reached conveniently.
Questionnaire…
❖ Disadvantage
• Non-returns,
• Misinterpretation, and
• Validity problems.
• It can be used only when respondents are educated and
cooperating.
• The control over the questionnaire may be lost once it is
sent.
• There is inbuilt inflexibility because of the difficulty of
amending the approach once questionnaires have been
dispatched.
The Contents of Questionnaires
• The key to minimizing the disadvantages of the survey
questionnaire lies in the construction of the
questionnaire itself.
• A poorly developed questionnaire contains the seeds
of its own destruction.
• Each of the three portions of the questionnaire - the
cover letter, the instructions, and the questions -
must work together to have a positive impact on the
success of the survey.
Questionnaire Construction
➢ Follow the guidelines below while developing Q’s:
• Keep the language simple
• Keep the questions short
• Keep the number of questions to a minimum
• Limit each question to one idea or concept.
• Do not ask leading questions
• Use subjective terms such as good, fair, and bad
sparingly/economically, if at all.
• Allow for all possible answers
• Avoid emotional or morally charged questions and too
direct questions
Scheduled Questionnaire
 Proforma containing a set of questions
 are being filled in by the enumerators who are
specially appointed for the purpose.
 These enumerators along with schedules go to
respondents, ask them the questions from the
proforma in the order the questions are listed
 The enumerators record the replies in the space meant
for the same in the proforma.
 Interviews
➢ Interviewing is one of the major methods of primary data
collection.
➢ It may be defined as a two-way systematic conversation
between an investigator and an informant,
➢ Initiated for obtaining information relevant to a specific
study.
➢ It involves not only conversation, but also learning from the
respondent’s gestures, facial expressions and pauses, and his
environment.
➢ Interviewing requires face-to-face contact or contact over
telephone calls for interviewing.
➢ It is done by using a structured schedule or an unstructured
guide.
Interview: Suitability
• Interviewing is the only suitable method for gathering
information from illiterate or less educated
respondents.
• It is useful for collecting a wide range of data from
factual demographic data to highly personal and intimate
information relating to a person’s opinions, attitudes,
values, beliefs, past experience and future intentions.
• When qualitative information is required or probing is
necessary, then interviewing is better.
• Where the area covered for the survey is a compact,
interviewing is feasible.
Types of Interview
a. Structured or directive interview
➢ This is an interview made with a detailed
standardized schedule.
➢ The same questions are put to all the respondents
and in the same order.
➢ Each question is asked in the same way in each
interview, promoting measurement reliability.
Types of Interview

b. Unstructured or non-directive interview

➢ This is the least structured one.
➢ The interviewer encourages the respondent to talk
freely about a given topic with a minimum of
prompting or guidance.
➢ In this type of interview, a detailed pre-planned
schedule is not used.
➢ Questions are not standardized and not ordered
in a particular way.
Focus Group Discussion (FGD)
➢ A focus group is a situation where a focus group
moderator or researcher selects a small and
homogeneous group (of 6-12 people).
• Conduct the discussion on a research topic or issue.
• Focus group sessions generally last between one and
three hours and
• The discussion is recorded using audio and/or
videotapes.
• Focus groups are useful for exploring ideas and
obtaining in-depth information about how people
think about an issue
FGD…
➢ FGD in combination with other methods, will help us to apply
the fundamental principle of mixed research or triangulation
➢ Strengths of focus groups
• Useful for exploring ideas and concepts.
• Provides window into participants’ internal thinking.
• Can obtain in-depth information.
• Can examine how participants react to each other.
• Allows probing.
• Most content can be tapped.
• Allows quick turnaround
FGD…
❖ Weaknesses of focus groups
• Sometimes expensive.
• May be difficult to find a focus group moderator with good
facilitative and rapport building skills.
• May be dominated by one or two participants.
• Difficult to generalize results if small, unrepresentative samples
of participants are used.
• May include large amount of extra or unnecessary information.
• Measurement of validity may be low.
• Data analysis can be time consuming because of the open-
ended nature of the data.
Observation Methods
➢ Observation means viewing or seeing various phenomena.
➢ Most observations are just casual and have no specific
purpose.
➢ But observation as a method of data collection is different
from such casual viewing.
➢ may be defined as a systematic watching of a specific
phenomenon in its proper setting for the specific purpose of
gathering data for a particular study.
➢ Observation as a method includes both “seeing” and
‘hearing”.
Observation…
➢ Observation becomes scientific, when it
• serves a formulated research purpose,

• is planned deliberately,

• is recoded systematically,

• is subjected to checks and controls on validity and

reliability.
Application of Observation
➢ Observation is suitable for a variety of research
purposes.
➢ It may be used for studying
• the behavior of human beings and social groups: life
style, customs and manners, interpersonal relations,
group dynamics, crowd behavior, leadership styles,
managerial styles, other behaviors and actions.
• physical characteristics of inanimate things like stores,
factories, residences.
• flow of traffic and parking problems
• movement of materials/products through a plant.
Advantage of observation
 Actual or habits of a person are observed
 Obtain information from those who are unable to
effectively communicate in written or oral form
 No better way to gather information than through
observation
 Most reliable method of data collection
Disadvantages of Observation
• Result of observation depends on the skill of the
observer
• Opinions and attitudes cannot be obtained by
observation
• It should be expensive to tie up personnel in such tasks
• The researcher’s findings are limited to those observed
Selecting the Survey Methods
• Selecting the type of survey you are going to use is one of
the most critical decisions.

• You'll see that there are very few simple rules that will help
your decision.

• you have to use your judgment to balance the advantages

and disadvantages of different survey types.
Selecting the Survey Methods
 Population Issues
 Sampling Issues
 Question Issues
 Content Issues
 Bias Issues
 Administrative Issues
Primary vs Secondary Data: Choice?
➢ The investigator must decide from the outset whether
to use primary data or secondary data in an
investigation.
➢ The choice between the two depends mainly on the
following considerations:
• Nature and scope of the enquiry,
• Availability of financial resources,
• Availability of time,
• Degree of accuracy desired, and
• The collecting agency, i.e., whether an individual, an
institution or a government body.
Measurement and Scaling
❖ Measurement
• The process of describing some property of a
phenomenon of interest, usually by assigning numbers
in a reliable and valid way.
• It is easy to assign numbers in respect of properties of
the study subjects; e.g., weight, height, etc.
• the researcher should know that the measurement
scale measures the characteristics of the objects or
events, but not the objects or events.
Measurement and Scaling…
❖ Scaling
 A process of providing a range of values that
correspond to different values in a concept being
measured.
 A concept can be thought of as a generalized idea that
represents something of meaning. E.g.; age
 Variable is anything that may assume different
numerical values; the empirical assessment of a concept.
 Operationalization is the process of identifying scales
that correspond to variance in a concept to be involved
in a research process.
 A construct is a term used for concepts that are
measured with multiple variables
Levels of Scales
 Scales, can be classified into four different levels,
based on their properties (characteristics of order,
distance, and origin:
 Nominal
 Ordinal
 Interval
 Ratio
Nominal Scale
• A nominal scale enables the classification of individuals,
objects or responses into subgroups based on a
common/shared property or characteristics.
• The variables measured on this scale may have one, two or
more subcategories depending upon the extent of
variation.
• Assigning the numbers does not indicate any order (no
meaningful order) or position to the group it represents.
• They only serve as labels for identification or
classification.
➢ Eg.
• Gender (male, female)
• Position (Top manager, middle manager, subordinate)
Ordinal Scale
 Ordinal scale is a ranking scale that indicates ordered
relationship among the objects or events.
 Arranges objects or alternatives according to their
magnitude in an ordered relationship either in ascending
or descending order.
 In research, ordinal scales are used to measure relative
attitudes, opinions, perceptions etc.,
 E.g.
✓ Rating career opportunities as excellent, good, average
poor or very poor.
✓ Income (High, Medium, Low)
✓ Attitude (Strongly Agree, Agree, Neutral, Disagree,
Strongly Disagree)
Interval Scale
 Interval scale involves the use of numbers to rate
objects or events.
 In this scale, numerically equal distances on the scale
represent equal values in the characteristic being
measured.
 Interval scales not only indicate order, but also
measure order or distance in units of equal
intervals.
 Have relative meanings.
 Eg. Celsius scale : 00 C to 1000 C
Fahrenheit scale: 320F to 2120F
Ratio Scale
• A ratio scale has all the properties of nominal, ordinal,
interval scales and its own additional features.
• Has a true zero - possible to indicate the complete
absence of a property.
• The numerals of the ratio scale have the qualities
of real numbers and can be added, subtracted,
multiplied, divided and expressed in ratio relationships.
• Eg. Income, sales, costs, number of customers, age,
height, weight are examples of this scale.
• In all these cases, natural zero exists.
• All statistical techniques can be applied on ratio data.
Types of Variables
• Variables can be categorized into continuous and
categorical forms.
• Continuous variables:
▪ Always take numeric values .
▪ assume any range of values and usually result from
measurement.
▪ Can be any number, positive or negative
▪ Examples: age in years, weight, blood pressure readings,
temperature, concentrations of pollutants and other
measurements
• Categorical variables:
• Information that can be sorted into categories
• Types of categorical variables – ordinal, nominal and
dichotomous (binary)
Categorical Variables: Nominal
 Nominal variable – a categorical variable without
an intrinsic order
 Examples of nominal variables:
 Where a person lives in Adama. (01, 02, 03, 04)
 Sex (male, female)
 Nationality (Ethiopian, Kenyan, American, Mexican,)
 Race/ethnicity (African American, Hispanic, White,
Asian American)
 Favorite pet (dog, cat, etc.)
Categorical Variables
▪ Ordinal variable- a categorical variable with some
intrinsic order or numeric value
▪ Examples of ordinal variables:
• Education (high school, Diploma, First Degree, Second
Degree)
• Agreement (Strongly Disagree, Disagree, Neutral, Agree,
Strongly Agree)
• Rating (excellent, good, fair, poor)
• Frequency (always, often, sometimes, never)
• Any other scale (“On a scale of 1 to 5.”)
Categorical Variables: Dichotomous
 Dichotomous (or binary) variable – a categorical
variable with only 2 levels of categories
 Often represents the answer to a ‘yes’ or ‘no’
question
 For example:
 “Did you attend the church picnic on May 24?”
 “Did you eat potato salad at the picnic?”
 Anything with only 2 categories
 Types Variables: Independent vs Dependent
❖ Independent Variable:
 is one that influences the dependant variable in either a
positive or negative way.
 That is, when the independent variable changes, the
dependent variable also changes (with each unit of change
in the independent variable, there is a change in the
dependent variable also).
 also known as the predictor variable
 Example: service level

Service level Sales

 Independent Vs Dependent…
❖ Dependant variable :
• Is the primary interest to the researcher.
• This variable is the effect
• It varies with respect to the IVs
• The researcher’s goal is to understand and describe the
change (s) in dependant variable, or to explain its
variability or to predict it.
• Also known as criterion variable
Ex: What is the effect of service level on sales volume ?

Service level Sales volume

➢ Dependant variable = sales volume
 Types of variable: Moderating
 The moderating variable is one that has a strong
contingent effect on the independent-dependent
relationship.
 affects the strength and direction of that
relationship
 That is, the presence of a third variable (the
moderating variable) modifies the original
relationship between the independent and the
dependent variables.
 Intervening/Mediating variable
 explains the relation between the independent (predictor) and
the dependent (criterion) variable
 What is the effect of service level on sales?

Service level Sales

Independent Vs intervening Vs Dependant variable

GRQ: What is the effect of service level on sales?
⚫ SRQ1: What is the effect of service level on customer satisfaction?
⚫ SRQ2: What is the effect of customer satisfaction on sales?

Service Customer Sales

level satisfaction Volume
Data Quality Assurance
 The instrument you select for data collection affects
your entire study.
 Therefore, the validity and reliability of instruments
need to be ensured.
❖Validity
• indicates the degree to which an instrument measures
what it is supposed to measure.
• is the extent to which a measurement gives the correct
answer to a research question.
• refers to the extent to which our data provide the true
measurement of the objective reality
Types of Validity
 The four common types of instrument validity are:
a. Face validity- refers to the subjective agreement among
professionals that a scale logically reflects the concept
being measured.
b. Content- the extent to which a measuring instrument
provides adequate coverage of the topic under study.
c. Criterion related- The ability of a measurement to
correlate with other standard measures of similar
constructs or established criteria.
d. Construct- ability to reliably measure and truthfully
represent a unique concept.
❖ Reliability
 is the extent to which a measurement procedure yields the
same answer whenever it is carried out by different
authors.
It is about consistency, i.e.,
◼ your research would be reliable, if it brings the same
results, when it is repeated, using the same methods,
◼ Example, a thermometer should show the same
temperature in a room whenever it is plugged under
the same condition.
Reliability…
 the consistency with which an instrument
measures the construct or content area it is intended
to measure.
 Reliability of the data is the main concern of the
scientific community.
 If the data are not reliable, the conclusions reached
on their basis will be quite useless.
Reliability/Internal Consistency
▪ Questions on tests should be equally difficult
throughout entire instrument
• Split-half: used with dichotomous tests
• Cronbach’s Alpha– is used with instruments with
more than two scores (e.g., Likert Scales)
➢ Reliability is reported as an alpha coefficient ranging
from 0.00 (low) to +1.00 (high).
➢ A value of alpha above 0.70 is considered sufficient for
most cases
Reliability…

• Reliable measuring instrument does contribute to

validity, but a reliable instrument need not be a valid
instrument.
• For instance, a scale that consistently overweighs
objects by five kgs., is a reliable scale, but it does not
give a valid measure of weight.
• But the other way is not true i.e., a valid instrument is
always reliable.
• Both validity and reliability must be checked for data
quality assurance.
➢ Data Analysis continues…