Chapter 2 - Research Design Flashcards
What is a research design and what are examples?
1.
2. (5)
- framework for collection and analysis of data
- e.g. experimental, cross-sectional, longitudinal, case study, comparative
What are the five experimental design elements?
1.
2.
3.
4.
5.
Time 0: - random assignment of subjects to experimental (treatment) and control groups
- PRE TESTING of both groups
Time 1: Treatment is given - treatment group: independent variable manipulated; all others held constant
Time 2: POST TESTING of both groups
- computation and analysis of group differences
What are possible threats to internal validity?
1.
2.
3.
4.
5.
H A M S T
- history: other events may have caused the changes observed
- “amibiguity about the direction of causal influence”
- maturation: people change over time in any event
- selection: non-random selection could explain differences
- testing: subjects may become sensitized to testing
What may be threats to external validity?
1.
2.
3.
4.
5.
- interaction of selection and treatment
- interaction of setting and treatment
- interaction of history and treatment
- interaction of effects of pretesting
- reactive effects of experimental arrangements
What is a cross sectional design? What are the key principles?
1.
2.
3.
4.
5.
6.
7.
8.
- collection of data on more than one case and at a single point in time
- e.g. patients symptoms on one single day
- collection of a body of quantiative or quantifiable data
- two or more variables
- detection of patterns of association
- mostly associated with surves method
- other methods: structured observation, content analysis, official statistics, and diaries
- key principles: more than just one case; at a single point in time; quantiative or quantifiable data; patterns of association
How can we evaluate cross-sectional research?
- reliability and measurement validity
- replicability
- internal validity
- external validity
- ecological validity
- not connected to the design as such
- will be high as long as he researcher specifies all the procedures
- is weak, because correlations are much more likely to be found than causality
- will be strong if the sample is truly random
- may be compromised by the intruments used
What is a Longitudinal Design? Where is it used?
1.
2.
3.
- survey of the same sample on more than one occasion
- e.g. patients symptoms on many days
- typically used to map change in business and management research in a panel study or cohort study (e.g. all graduates from a business studies course in the same year)
What are similarities between cross sectional and longitudinal research? What are sepcial problems in longitudional research?
1.
2.
3.
4.
5.
- ## both very similar.problems:
- attrition (abnutzung)
- whether it is the right time for the next wave of data collection?
- the first round badly thought out (later rounds in a bit of a mess)
- a panel conditioning effect
What is a case study design ?
1.
2.
3.
4.
What are examples of cases?
1.
2.
3.
4.
5.
6.
- detailed and intensive analysis of one case (e.g. specific person, event or community)
- often involves qualitative research
- case is the focus of interest in its own right - location/ setting just provides a background
- ## e.g. patient zero
- critical case
- unique case
- revelatory case
- representative or typical case
- longitudinal case
- single vs multiple site case
What is the biggest issue concern about cases?
Can cases be extended?
1.
2.
3.
- biggest concern: external validity
- is the point of the research to examine particulars rather than generalization?
- extension of cases: longitudinally or through a comparative design
What is a Comparative Design? What is a problem that might arise?
1.
2.
3.
4.
5.
- same methods used for meaningfully contrasting cases
- qualitative or quantitative
- often cross- cultural comparisons (e.g. hofstedes study of IBM managers in different countries
- includes multiple case studies
- problem of translating research instruments and finding comparable samples
What can be said regarding the evaluation of Comparative Designs?
What can be said regarding the level on analysis?
1.
2.
3.
4.
5.
- identical to cross sectional design (essentially two or more cross sectional studies; carried out at same point in time)
- comparing two or more cases (does the theory hold?)
- what is primary unit of measurement and analysis? (individuals, societies etc.)
- quantifiable or quantitative data
- patterns of association
Bringing together Research Strategy and research Design
- execution of both quantitative and qualitative strategies strategies through any of the research design ( but, experimentation rarely used in qualitative research)
- e.g. use of comparative design: quantitative: studying how many people go shop | qualitative: studying the role of design in the HNS
