|
Lecture 4. Research Design MN5410 Qualitative Research Methods Chin-Ju Tsai School of Management RHUL
Lecture objectives
To introduce the three types of research designs used in management researchTo discuss key components involved in a research designTo help you think about your research plan
Outline
What is a research design? The three types of research designs --quantitative research designs --qualitative research designs --mixed methods research designsThe components involved in a research design --research philosophy --strategies of inquiry --research methods
Some important terms/concepts before we start…
QuantitativeCommonly refers to any data collection technique or data analysis procedure that generates or uses numerical data (numbers) e.g. age, income, number of children, scaled opinions (e.g. Likert scale from 1 to 5, where 1= strongly disagree and 5= strongly agree)Qualitative Commonly refers to any data collection technique or data analysis procedure that generates or uses non-numerical data (usually words) e.g. stories, opinions, descriptions
Some important terms/concepts before we start…
Deductive or inductive approach?Testing theory or developing theory?
Some important terms/concepts before we start…
Deductive approach: research approach involving the testing of a theoretical proposition by the employment of a research strategy specifically designed for the purpose of its testing.
Some important terms/concepts before we start…
Inductive approach: research approach involving the development of a theory as a result of the observation of empirical data
What is a research design?
A research design is the overall plan for your research (i.e. how you will go about answering your research questions)Provides a framework for the collection and analysis of dataNeed to specify the following in your plan/proposal: --what data to collect --sources from which you intend to collect data --methods of data collection --methods of data analysis
The three types of research designs
Quantitative research designsPhilosophical assumptions: positivism, objectivismUsually emphasize quantification in the collection and analysis of dataPredominantly use a deductive approach to the relationship between theory and researchQualitative research designsPhilosophical assumptions: interpretivism, subjectivism/constructionismUsually emphasize words rather than quantification in the collection and analysis of dataPredominantly use an inductive approach to the relationship between theory and researchMixed methods research designsPhilosophical assumptions: pragmatismUse both quantitative and qualitative data collection techniques and analysis proceduresUse a deductive approach and/or inductive approach
Quantitative Mixed methods Qualitative
Components involved in a research design
Component 1. Research philosophy
Refers to the way in which you view the world and your view of the relationship between knowledge and the process by which knowledge is developedYour research philosophy will influence your choice of research strategy and research methods. #p#分页标题#e#
Research design vs. research philosophy
Component 2. Strategies of inquiry
Quantitative strategies e.g.ExperimentSurveyQualitative strategies e.g.Case studyEthnographyMixed methods strategies e.g.Sequential mixed methodsConcurrent mixed methods
Experiment (1)
Allows for control of extraneous factors and manipulation of key variablesCan investigate effects of change
Rarely used in business and management research Why???Vast majority of independent variables cannot be manipulated Ethical concerns of experimental interventions
Provides a quantitative or numeric description of trends, attitudes or opinionsUsually sample-basedData are collected using : --Structured interviews --Structured observations --QuestionnairesUsually based on deductive approachGood at answering who, what, where and how many questions
Case study (1)
‘an enquiry that investigates a contemporary event within its real-life context, especially when the boundaries between phenomenon and context are not clearly evident’ (Yin, 2003: 13)‘a strategy for doing research which involves an empirical investigation of a particular contemporary phenomenon within its real life context using multiple sources of evidence’ (Robson, 2002: 178)
Case study (2)
Provides rich, in-depth, understandings of situations Uses multiple sources of evidence --often uses qualitative data collection techniques (e.g. interviews, observation, review of documents) --also uses quantitative techniques (e.g. questionnaires) (Details on Case Study will be covered in lecture 6)
Research strategy that focuses upon describing and interpreting the social world through first-hand field study.Originates from the field of Anthropology
Other research design considerations
Level of analysisTime dimension --cross-sectional --longitudinalCredibility of research findings --Reliability --Validity
Individual (e.g. managers or employees)Department or work groupOrganisation (e.g. organisational structure or culture)Market or societal context in which organisations are located
Data are collected form a sample at a single point in timeOften use survey-based methods (e.g. questionnaires, structured-interviews) but also use qualitative methods Examine relationships between variables, but hard to established a causal relationship
The data you collect must be credible in order to represent sound evidence for your researchResearchers identify two key aspects of credibility:ReliabilityValidityFor research results to be convincing, the data collection methods and evidence used must be reliable and valid.
refers to the extent to which your data collection methods or analysis procedures will yield consistent findings. Can be assessed by: 1. will your data collection tool give the same results on other occasions? 2. will other researchers obtain similar observations or results? 3. can readers understand clearly how the researcher has arrived at results from raw data?#p#分页标题#e#指导留学生作业
refers to (1) the extent to which data collection method (s) accurately measure what they were intended to measure. (2) the extent to which research findings are really about what they claim to be about.
Four common types of validity to be considered in management research are:Construct validity: refers to the extent to which your measurement questions actually measure the presence of those constructs you intended them to measure. Measurement validity: refers to the extent to which a scale or measuring instrument measures what it is intended to measure.
Internal validity: is concerned with whether the evidence presented justifies the claims of cause and effect. E.g. the “Hawthorne effect” (participants change their behaviour or performance when they know they are being observed)External validity: refers to the extent to which the research results from a particular study are generalisable to all relevant contexts.
1. Come up with three research questions on your topic of choice or on any one topic listed below. Identify suitable research designs to investigate your questions, explain your level of analysis and methods of data collection, and clarify issues of reliability and validity. Economic development and human rights Equal opportunities for women, ethnic minorities or disabled people in societySocietal perceptions of same sex marriages Crime in society2. Review the Dietz (2004) article posted on Moodle. Explain its research design, methods of data collection, issues of reliability, validity and generalizability of findings.
1. Come up with three research questions on your topic of choice or on any one topic listed below. Identify suitable research designs to investigate your questions, explain your level of analysis and methods of data collection, and clarify issues of reliability and validity. Economic development and human rights Equal opportunities for women, ethnic minorities or disabled people in societySocietal perceptions of same sex marriages Crime in society2. Review the Dietz (2004) article posted on Moodle. Explain its research design, methods of data collection, issues of reliability, validity and generalizability of findings.
|
