Research Design

RESEARCH METHODOLOGY MODULE 3 – PART A DESIGN STRATEGIES

RESEARCH DESIGN  MEASUREMENT PROBLEMS  SCALING DESIGN  SAMPLING DESIGN  PROBABILITY SAMPLING METHODS  NON-PROBABILITY SAMPLING METHODS 

What is Research Design? Activity- & time-based plan  Based on research question  Guides selection of sources and types of information  Framework for specifying the relationships among the study variables  Blueprint that outlines each procedure from the hypothesis to the analysis 

CLASSIFICATIONS OF DESIGNS

A. CRYSTALLISATION OF RESEARCH QUESTION EXPLORATORY STUDIES

FORMAL STUDIES

3.1 EXPLORATORY STUDIES



Exploratory study is usually to develop hypotheses or questions for further research



Formal study is to test the hypotheses or answer the research questions posed

B. METHODS OF DATA COLLECTION



Monitoring, which includes observational studies



Interrogation / Communication studies

C. POWER TO PRODUCE EFFECTS



In an experiment, the researcher attempts to control and / or manipulate the variables in the study



In an ex post facto design, the researcher has no control over the variables; they can only report what has happened

D. PURPOSE OF THE STUDY



Descriptive study tries to explain relationships among variables



Causal study is how one variable produces changes in another

E. THE TIME DIMENSION



Cross-sectional studies are carried out once and represent a snapshot of one point in time



Longitudinal studies are repeated over an extended period

F. THE TOPICAL SCOPE (Breadth & Depth)



Statistical studies attempt to capture a population’s characteristics by making inferences from a sample’s characteristics



Case studies place more emphasis on a full contextual analysis of fewer events or conditions and their interrelations

G. THE RESEARCH ENVIRONMENT

 Field

conditions

 Laboratory

conditions

 Simulations

H. PARTICIPANT’S PERCEPTIONS



Usefulness of a design may be reduced when people in the study perceive that research is being conducted



Participants’ perceptions influence the outcomes of the research

Why do Exploratory Studies? Exploration is particularly useful when researchers lack a clear idea of the problems

Data Collection Techniques 

Qualitative techniques



Secondary data



Focus groups



Two-stage design

3.2 QUALITATIVE TECHNIQUES

          

In-depth interviews (Laddering ***) Observation Films, photographs, videotapes Projective techniques & Pyschological testing Case studies Street ethnography Elite / Expert interviews Document analysis Proxemics and Kinesics Hidden issue questioning *** Symbolic analysis ***

PROJECTIVE TECHNIQUES *** Association techniques (Word)  Completion techniques (Sentence, Story)  Construction technique (Picture response, Cartoons)  Expressive Techniques (Role playing, Third-person) 

3.3 SECONDARY DATA ANALYSIS ***



Internal  Databases



External  Published

Materials  Computerised Databases  Syndicated services

Published External Sources ***         

Guides Directories Indexes Non-Governmental Statistical Data Government Sources – Census Other Government Publications Books, Booklets, Monographs, Handbooks Periodicals & Dailies Brochures, Pamphlets

Computerised Databases *** 

Online, Internet & Offline  Bibliographic

databases  Numeric databases  Full-text databases  Directory databases  Special-purpose databases

Syndicated Sources ***      



Survey Reports Purchase panels Media panels Scanner Volume Tracking Data Audit Services Industrial Product Syndicated Services Computer mapping (Thematic maps)

3.4 EXPERIENCE SURVEY

What is being done?  Past? Success?  Any Change?  Catalysts?  Decision process?  Costs involved?  Who will assist?  Priority areas? 

 Representatives

of different

positions  “Pure” Cases  Individuals in transition  Deviants / isolates  Newcomers  Marginal / Peripheral individuals

3.5 FOCUS GROUP

Homogeneity  Specific Topic  6-10 respondents  Telephone F. C.  Online F. C.  Videoconferencing F. C.  Content Analysis  Advantages?  Limitations?  Two-way F. C. ****  Dual-Moderator F. C. *** 

Advantages of F. C. *** Synergy  Snowballing  Stimulation  Security  Spontaneity  Serendipity  Scientific scrutiny  Speed 

Disadvantages of F. C. *** Misuse  Misjudge  Moderation  Messy  Misrepresentation 

3.6 TWO STAGE DESIGN

 Stage

1:

Clearly

define the research question

 Stage

2:

Developing

design.

the research

3.7 DESCRIPTIVE STUDIES

Descriptions of phenomena (Who, what, when, where, how?)  Estimates of proportions of a population that have characteristics  Discovery of associations among different variables (correlational study) 

3.8 CAUSAL STUDIES

Causation 

The essential element of causation is A “produces” B or A “forces” B to occur

Causal Study Relationships 

Symmetrical



Reciprocal



Asymmetrical

Some Terms: Stimulus: Event or Force.  Property: Enduring characteristic that does not depend on circumstances for its activation.  Disposition: Tendency to respond in a certain way.  Behaviour: An action. 

Asymmetrical Relationships 

Stimulus-Response



Property-Disposition



Disposition-Behavior



Property-Behavior

Stimulus-Response  An

event or change results in a response from some subject

 Example:

An increase in price will result in fewer units sold.

Property-Disposition  An

existing property causes a disposition

 Example:

Gender and Attitudes towards social issues.

Disposition-Behaviour A

disposition causes a specific behaviour

 Example:

Job Satisfaction and Productivity.

Property-Behaviour  An

existing property causes a specific behaviour

 Example:

in sports.

Age and participation

Achieving the Ideal Experimental Design 

Control Random

Assignment

Matching 

Randomization Manipulation

and control of variables

POTENTIAL SOURCES OF ERRORS *** Random Sampling Error Non-Response Error Researcher Errors Interviewer Errors

Non-Sampling Error Response Error Respondent Errors

Researcher Errors *** Surrogate Information Error  Measurement Error  Population Definition Error  Sampling Frame Error  Data Analysis Error 

Interviewer Errors ***    

Respondent Selection Error Questioning Error Recording Error Cheating Error

Respondent Errors *** Inability Error  Unwillingness Error 