Formulating the research design
1. Introduction
This chapter uncovers three layers: research strategies, research choices and time horizons.
These three layer can be thought of as focusing on the process of research design, that is,
turning your research question into a research project.
Research design will be the general plan of how you will go about answering your research
questions.
It contains clear objectives, derived from research questions, specifies the sources from
which you intend to collect data, and considers the constraints (access to data, time,
location and money) as well as discussing ethical issues.
Design and tactics are distinct. Design is concerned with the overall plan for research.
Tactics is about the finer detail of data collection and analysis, the center of the research
onion.
Tactics will involve the clear about the different quantitative and qualitative data collection
techniques and subsequent quantitive and qualitative data analysis procedures.
In this chapter:
The purpose of research (5.2)
Research strategies (5.3)
Multiple research choices (5.4)
Time horizon (5.5)
Research credibility (5.6)
2. The purpose of your research
Classification of research purpose: threefold one of exploratory, descriptive and explanatory.
The purpose may change over time.
Exploratory Studies
to seek new insights, to ask questions and to assess phenomena;
used when you want to clarify your understanding of a problem;
3 principal ways of conducting: a search of the literature, interviewing ‘experts’, and
focus group interview.
Advantage: flexible and adaptable to change as a result of new data.
Descriptive Studies
to portray an accurate profile of persons, events or situations.
should have a clear picture of the phenomena on which you wish to collect data.
skills developed: evaluating and synthesising ideas.
Explanatory Studies
to establish causal relationships between variables
to study a situation/ problem to explain the relationships between variables.
3. The need for a clear research strategy
Experiment
Purpose: to study causal links between variables; or consider the size of the change and
the relative importance of variables.
Used in exploratory and explanatory research => answer “how” and “why” questions
How to conduct:
definition of a theoretical hypothesis;
selections of samples of individuals from known populations;
random allocation of sample to the experimental and control group;
introduction of planned intervention or manipulation to one or more of the
variables;
control of all other variables.
Often used on captive populations: university students, employees of a particular
organisation and the like.
Survey
Purpose: to answer who, what, where, how much and how many questions.
Used for exploratory and descriptive research.
How to conduct:
using a questionaire administered to a sample => easy comparison.
analysing data quantitatively using descriptive and inferential statistics.
Advantages:
Data can be used to suggest possible reasons for relations between variables.
More control over research process
Findings generated are representative of the whole population at a low cost.
Case study
To do research involving an investigation of a particular contemporary phenomenon
within its real life context;
Used for explanatory and exploratory research.
To gain a rich understanding of the context of the research and the processes;
To answer why, what, how questions;
Data may be collected through interviews, observation, documentary analysis, etc.,
4 case study strategies:
Single case: represents a critical/ extreme/ unique case. => defining the actual
case
Multiple cases: focuses on the need to establish whether the outcomes of the
first casr occur in other cases and the need to generalise the findings.
Holistic case: research is concerned with the organisation as a whole.
Embedded case: research is concerned with a number of logical sub-units within
the organization.
Action research
4 common themes
Focusing upon and emphasises the purpose of the research
Relating to the involvement of practitioners in the research
Emphasising the iterative nature of the process of diagnosing, planning, taking action
and evaluating
Implicating beyond the immediate project
2 distinct foci
Fulfilling the agenda of those undertaking the research rather than that of the sponsor
Focusing on the needs of the sponsor and involving those undertaking the research in
the sponsor’s issues
Grounded theory
Grounded theory is helpful for research to predict and explain behaviour
In grounded theory, theory is developed from data generated by observations
6 commons misconceptions about grounded theory
- Grounded theory is not an excuse to ignore the literature, or defer reading
existing theory until the data are collected and analysed
- Grounded theory is not presentation of raw data
- Grounded theory is not theory testing, content analysist, or word counts
- Grounded theory is not simply routine application of formulaic procedures to
data
- Grounded theory requires researchers to develop a tatic knowledge of their data
- Grounded theory is the product of considerable experience, hard work,
creativity, and occasionally, a healthy of good luck
Ethnography
Purpose: To describe and explain the social world the research subject inhabit
Used for researching the phenomenon
To gaining insight about particular context and better understanding and interpret it
from the perspective(s) of those involved
How to conduct:
- Find a setting group or group to answer research question; meet and negotiate full
access with research objectives
- Develop strategies to cope with being both a full time member in the social context
Disadvantages:
- Changeable time and time consuming
- Need flexible and responsive research process
- Having contradictory meaning in the term naturalism
Archival research
Make use of administrative records and documents as the principal source of data
Used for explanatory and exploratory or descriptive research
Collect data with different purpose and the administrations of organizations =>Archival
research is conflated with secondary data analysis
Focus on changeable answers in changeable time
How to conduct: establish available data and design research
4. Multiple method choices – combing data collection techniques and analysis
procedures
Difference between data collection techniques (quantitative and qualitative) and data
analysis procedures: focus on numeric (number) and non-numeric (words)
- Quantitative (questionnaires) or data analysis procedure(graphs or statistics)
- Qualitative (interview) or data analysis procedure (categorizing)
Combining quantitative and qualitative and data analysis is research choice
- Individual methods don’t not exist isolation
- Can mix single data collection method and single data analysis procedure or multiple
data collection methods and data analysis procedure
Questionnaires + structured observation analyzing + statistical procedure
multiple method quantitative study
In-depth interview + dairy accounts + non –numerical procedure
multiple method qualitative study
2 mixed method approaches
- Using quantitative and qualitative collection techniques and data analysis procedures at
the same time (parallel)
- One after the other
5. The credibility of research findings
Two particular emphases on research design: reliability and validity.
5.1. Reliability:
Can be assessed through three questions
- Will the measures yield the same results on other occassions?
- Will similar observations be reached by other observers?
- Is there transparency in how sense was made from the raw data?
4 threats to reliability
- Subject or participant error
- Subject or participant bias
- Observer error
- Observer bias
5.2. Validity
Is concerned with whether the findings are really about whatthey appear to be about.
Threats to validity
- History
- Testing
- Instrumentation
- Mortality
- Maturation
- Ambiguity about causal irection
Generalisation (sometimes referred as external calidity) = whether your findings may be
equally applicable to other research settings try to explain what is going on in your
particular research setting
Logic leaps and false assumptions: Your research design will be based on a flow of logic
and a number of assumptions, all of which must stand up to the closest scrunity
Identification of the research population: Similar to generalisation
Data collection
Data interpretation: It is important to choose an appropriate theoretical framework
which will shape your conclusions
Development of conclusions