Chapter Four

Research Design

Step 5: 1
 Introduction
 A research design is the arrangement of conditions for the
collection and analysis of data in a manner that aims to address
the research problem.

 The research design should be inline with:

 What is the study about? (Problem definition)

 Why is the study being made? (Justification)

 Where will the study be carried out? (Location)

 What type of data is required? (Quanti, Qual ….)

 . . . Introduction
 Where can the required data be found (target population)
 What will be the sample design (technique chosen)
 What techniques of data collection will be used? (observation,
interview, questionnaire, or document analysis)
 How will the data be analyzed (Data Analysis techniques &
tools to be employed)
 . . . Introduction

 We may split the overall research design into three:

 The sampling design - which deals with the method of
selecting items to be observed.
 The statistical design - which concerns with the question of
how many items are to be observed and how the information
and data gathered are to be analyzed.
 The operational design - which deals with the techniques by
which the procedures specified in the sampling, Statistical and
observational designs can be carried out.
 Sampling Design

 Population: the entire group under study as defined by research

objectives.
 Sometimes called the ―universe.‖ or Reference population
 Researchers define populations in specific terms such as heads
of households, individual person types, families, types of retail
outlets, etc.
 Population, geographic location and time of study are also
considered
Sampling Design 6
 Sampling Design

 Sample: a subset of the population that should represent the entire

group.
 Sample unit: the basic level of investigation…consumers, store
managers, shelf-facings, adolescence, etc.
 The research objective should define the sample unit.
 Census: is the counting of the complete population.
 Sampling Design
 Practical considerations when taking samples:
 cost and population size
 Nature & purpose of the study
 Inability of researcher to analyze large quantities of data potentially
generated by a census
 Samples can produce sound results if proper rules are followed for the draw
 Sampling Methods

 Two Types of Sampling Methods:

 Probability sampling: members of the population have a known chance
of being selected

 Non-probability sampling: the chances of selecting members from the

population are unknown.
 Probability Sampling Methods
 Four common Type:-

Simple random sampling

Systematic Sampling

Cluster sampling

Stratified sampling
 Simple Random Sampling
 The probability of being selected is ―known and equal‖ for all members of
the population
 Blind Draw/Lottery Method (e.g. names ―placed in a hat‖ and then drawn
randomly)
 Random Numbers Method (all items in the sampling frame given numbers,
numbers then drawn using table or computer program)
 Advantages:
 Known and equal chance of selection
 Easy method when there is an electronic database
 Disadvantages:
 Complete accounting of population needed
 Very inefficient when applied to skewed population distribution
 Systematic Sampling
 It is the way to select a probability-based sample from a directory or list.
 This method is more efficient than simple random sampling.
 This is a type of cluster sampling method.
 Sampling interval (SI) = population list size (N) divided by a
pre-determined sample size (n)
 How to draw?
1) calculate SI,
2) select a number between 1 and SI randomly,
3) go to this number as the starting point and the item on
the list here is the first in the sample,
4) add SI to the position number of this item and the
new position will be the second sampled item,
5) continue this process until desired sample size is
reached.
 Systematic Sampling
 Advantages:
 Known and equal chance of any of the SI ―clusters‖ being selected
 Efficiency.
do not need to designate (assign a number to) every population
member, just those early on the list (unless there is a very large sampling
frame).
 Less expensive…faster than SRS
 Disadvantages:
 Small loss in sampling precision
 Potential ―periodicity‖ problems
 Cluster Sampling
 Method by which the population is divided into groups (clusters),
 Any of which can be considered a representative sample.
 These clusters are mini-populations and therefore are heterogeneous.
 Once clusters are established, a random draw is done to select one (or
more) clusters to represent the population.
 Cluster Sampling
 Advantages
 Economic efficiency … faster and less expensive than SRS
 Does not require a list of all members of the universe
 Disadvantage
 Clusterspecification error…the more homogeneous the cluster chosen,
the more imprecise the sample results.
 Non-Probability Sampling

1. Conveniences Samples
2. Judgment Samples
3. QuotaSampling
Reading Assignment
4. Snowball Sampling
 Convenience Sampling
 Samples drawn at the convenience of the interviewer.
 People tend to make the selection at familiar locations
 Taking of samples that are readily available
 E.g. those that arrive on a scene by coincidence
 Appropriate for some less demanding research
 Error occurs
 1) in the form of members of the population who are infrequent or
nonusers of that location and
 2) who are not typical in the population
 Judgment Sampling
 Samples that require a judgment or an “educated guess” on the part
of the interviewer as to who should represent the population.
 Also, “judges” (informed individuals) may be asked to suggest who
should be in the sample.
 Subjectivityenters in here, and certain members of the
population will have a smaller or no chance of selection
compared to others
 Steps in Sampling Process 20

 Defining the population

 Specifying the sampling unit

 Specifying the sampling frame ( the means of representing the elements

of the population)

 Specifying the sampling method

 Determining the sampling size

 Specifying the sampling plan

 Selecting the sample

 Measurement & Measurement Scales

 Measurement is the process through which researchers

describe, explain, and predict the phenomena and constructs of
our daily experiences
 The concept of measurement is important in a research in two
key areas:
 Enables researchers to quantify abstract constructs &
Variables.
 Used to analyze sophisticated statistical data
 Non metric Data vs. Metric Data

 Non-metric data (also referred to as qualitative data)-which

cannot be quantified and are predominantly used to describe and
categorize.
 Metric data (also referred to as quantitative data)-are used to
examine amounts and magnitudes
 Scales of Measurement 23

 Four main type of scales measurement

1. Nominal scales
2. Ordinal scales
3. Interval scales, and
4. Ratio scales.
 Nominal and ordinal scales are non metric
 Interval & ratio scales  metric
 Nominal Scales 24
 are the least sophisticated type of measurement and are used only to qualitatively
classify or categorize.
 Measures identity only
 They have no absolute zero point and cannot be ordered in a quantitative
sequence, and there is no equal unit of measurement between categories.

 They do not imply amounts of an attribute or characteristic.

 This makes it impossible to conduct standard mathematical operations such as

addition, subtraction, division, and multiplication.

 Examples of nominal scale data include gender, religious and political affiliation,
place of birth, city of residence, ethnicity, marital status, eye and hair color, and
employment status
 Ordinal Scales 25

 measurement is characterized by the ability to measure a variable in terms of

both identity and magnitude.
 This makes it a higher level of measurement than the nominal scale
 Measures relative magnitude in relation to other variables.
 Variables can be ranked in relation to the amount of the attribute
possessed.
 Ordinal scales represent the rank or ordering of variables
 Example - finishing position of runners in a race.
 Lack the mathematical properties necessary for sophisticated statistical
analyses.
 26
Interval Scales
 builds on ordinal measurement by providing information about both order and
distance between values of variables.

 The numbers on an interval scale are scaled at equal distances, but there is no
absolute zero point. Instead, the zero point is arbitrary.

 Examples: include temperature measured in Fahrenheit and Celsius.

 Lack of an absolute zero point makes division and multiplication impossible
 Ratio Scales 27

 The properties of the ratio scale are identical to those of the interval scale,
except that the ratio scale has an absolute zero point, which means that all
mathematical operations are possible.
 Example –Money- It is possible to have no (or zero) money—a zero balance in
a checking account is an example of an absolute zero point.
 Characteristics:
 Identical to the interval scale, except that they have an absolute zero point.
 Unlike with interval scale data, all mathematical operations are possible.
 Examples include height, weight, and time.
 Highest level of measurement.
 Allow for the use of sophisticated statistical techniques.
 Instrument Design 28

 Based on hypotheses identified in the stages of research process

 Most important question researcher can ask before begin writing
 Survey-type instruments can yield three types of information.
A. Reports of Fact - self-disclosure of some objective information (e.g., age,
gender, education, behavior)
B. Ratings of Opinion or Preference -evaluative response to statement (e.g.,
satisfaction, agreement, like\dislike)
C. Reports of Intended Behavior - self-disclosure of motivation or intention
(e.g., likeliness, willingness)
 How will administration be accomplished? 29
A. Self-administered surveys
subject responds to printed questions (e.g., group or mail surveys)
 Advantages
 Ask questions with long, complex or visual response categories
 Ask sequences of similar questions
 Respondent does not share answers with immediate person

 Disadvantages
 Carefulquestionnaire design is required
 Open response questions not useful
 Good reading and writing skills by respondents are needed
 Very little quality control over administration
 30
B. Other-administered surveys
 Subject responds to questions directly posed by researcher (e.g., interview,
phone survey)
 Advantages
 Most effective in joining cooperation (initial and length)
 Opportunity to answer respondent questions and ensure quality of data
(e.g., probe adequate answers, answer all questions)
 Rapport and confidence building possible
 Disadvantages

 Cost and time requirements

 Adequate training of staff
 Accessibility of sample
 Formats of questions 31
A. Open-ended Questions - permits subject freedom to answer question in own
words (without pre-specified alternatives)
 Advantages
 Obtain unanticipated answers
 May better reflect respondents thoughts\beliefs
 Appropriate when list of possible answers is excessive
 Disadvantages
 Flexibilityin responses difficult to code and analyze
 Provide incomplete or unintelligible answers
B. Close-ended Questions - subject selects from list of pre-determined,
acceptable responses
 Type of Closed ended Questions 32
1.Checklists - respondent selects certain number of pre-specified categories
(nominal data)
 eg. type of exercises
_____ Aerobics
_____ Basketball
_____ Swimming
_____ Football
2. Two-way (Forced Choice) -Respondent must select between two
alternatives (crude ordinal\nominal) ____Yes or ____ No type
 eg. Do you always make up before 8:00 AM? Yes/No
 Type of Closed ended Questions 33
3. Ranked - respondent must place items in order of importance or value
(ordinal)
eg. Rank in order of important
_____ Coursework
_____ Part-time Employee
_____ Party hard
_____ Close relationship
4. Multiple-Choice (Likert Scale) – respondent selects between range of
alternatives along pre-specified continuum (ordinal\interval?)
Eg.
 Strongly Agree Agree Neutral Disagree Strongly Disagree
1 2 3 4 5
 Writing good survey Questions 34

 Differences in answers should stem from differences among

respondents rather than differences in the stimuli
 Question's wording is obviously a central part of the stimulus.

 Good question wording:

 Simple sentences

 No double negatives

 Eliminate vagueness (poorly defined terms)

 Eliminate Objectionable\Irrelevant questions

 Writing good survey Questions 35

 No double negatives
 It is not the case that I have never cheated on my tax
returns.
 Never should one not help others
 Eliminate vagueness
 poorlydefined terms
 ensure consistent meaning for all respondents
 E.g.
 How many times in the past year have you talked with a doctor about your
health?
 Tests are stressful
 Writing good survey Questions 36

 Objectionable\Irrelevant questions
ruin relationship with respondent
yield missing data
E.g.
How old are you?
have you ever tested positive for HIV virus?
Have you answered each question truthfully?
How many years of education were you able to complete?
 Writing good survey Questions 37

 Discrete questions\responses
No double-barrel questions
Balanced questions\responses
Exhaustive\mutually exclusive categories
 E.g.
Is your doctor friendly and reasonably priced?
Were your caregivers courteous and friendly?
I find that I am more attentive and remember more
if I have eaten before a study session.
 Writing good survey Questions 38

What is your age?

under 10 , 10-20 , 20-30 , 30-40 . 40-50
How was the service at this hospital?
Excellent
Very good
Great
 How did you last travel to the supermarket?
Car
bus
foot/ walking
public transportation
Good day!