Research Design - VLE 2 Flashcards
What are the three traditional categories of research design?
Exploratory research: To gain background information, to define terms, to clarify problems and hypotheses, to establish research priorities.
Descriptive research: To describe and measure marketing phenomena.
Causal research: To determine causality, to make ‘if-then’ statements.
What is the difference between conclusive and exploratory research design?
Exploratory research tends to pull together ideas (some measurable and some which may be vague and immeasurable) in new and creative ways to develop new insights, to elicit meaning from participants and generate theoretical variables. Exploratory research may not necessarily be generalisable to large populations, but may uncover quite subtle differences between groups of individuals and offer new insights to decision-makers.
Conclusive research tends to measure phenomena in a focused and sometimes predictable manner. Conclusive research may either describe or uncover causal relationships which may be generalised to large populations.
Define research design.
Efficiency and effectiveness are keywords!!
Research design is defined as a framework or blueprint for conducting the market research project in which are specified the details of the procedures necessary for obtaining the required information to structure and solve the problem. Based on a broad approach to the management and research, the research design specifies the details, i.e. the practical aspects of implementing that approach. A good research design will ensure that the market research project is conducted effectively and efficiently.
What characteristics should the information research designs produce to aid decision makers?
Accuracy – i.e. a valid representation of the phenomena under investigation which has come from a reliable or consistent form of measurement and which is sensitive to the important differences in individuals being measured.
Be current – i.e. as up-to-date as possible.
Sufficiency – i.e. a complete ‘picture’ which reflects the characteristics of the market phenomena under study.
Availability – i.e. access can be made when a decision is imminent.
Relevance – i.e. the support given makes sense to decision-makers and builds on their existing knowledge.
How does the subject of a study affect research design?
Social Desirability Bias
Whether an issue is seen as being public or private, i.e. the extent to which a participant is willing to open up and be honest in front of others about a particular issue or whether they keep their views to themselves or will distort their views in the presence of others.
Articulability
Whether the nature of the subject of enquiry can be put into words, i.e. the extent to which a participant can explain how they feel about a particular issue. An example of this may be putting into words ‘why’ the taste, texture and smell of a brand of bread makes it preferable to another.
Awareness
Whether the participant is actually aware of the subject of enquiry, i.e. the extent to which a participant may have actually thought about, or wants to think about, an issue. Many forms of habitual behaviour may be included in this, as well as issues related to participants’ family relationships or how they are influenced by different forms of marketing communications.
What is the difference between research design and an approach to a problem?
The formulation of a research design differs from developing an approach to a problem in that a research design specifies the details of actually implementing the approach. Therefore, the approach sets the broad direction and rationale for a chosen direction, while the research design sets out the technical details to fulfil a desired approach.
List some of the uses of an exploratory research design (e.g. gaining background information, formulate hypothesis, etc.)
Background information – obtain background information where absolutely nothing is known about the problem area.
Formulate hypotheses – for further investigation and/or quantification.
Concept identification – explore concepts when developing new products or forms of marketing communications.
Screening – reduce a large number of possible projects into a smaller number of probable ones, such as in new-product development.
Salient behaviour and attitude patterns – develop structures of these constructs.
Belief and attitude structures – develop an understanding of these to assist with the interpretation of data structures in multivariate data analyses.
Explore statistical differences – investigate the reasons which lie behind statistical differences between groups which may emerge from secondary data or surveys.
Sensitive issues – explore sensitive or personally embarrassing issues from the perspective of the participant and/or interviewer.
Difficult to articulate – explore issues which are difficult to rationalise and/or articulate.
Data mine – explore quantitative data to reveal unknown connections between different measured variables.
What are some methods for exploratory research?
Secondary data analysis: what has been previously collected?
Experience surveys: for example, talk to those who have experience such as those who adopted Vista early, those who make biodiesel, those who have taken an online course etc.
Case analysis: was there a similar situation in the past (for example, Windows XP)?
Focus groups: talk to a few persons in the population.
Projective techniques: used for topics which are sensitive or difficult to articulate (for example, personal hygiene or status-seeking topics!).
What are two basic classifications of descriptive research designs?
cross-sectional design: Cross-sectional studies measure units from a sample of the population at only one point in time. Cross-sectional studies take ‘snapshots’ of the population at a point in time.
longitudinal design: repeatedly measures the same sample units of a population over time. Longitudinal studies often make use of a panel which represents sample units who have agreed to answer questions at periodic intervals.
What is single, multiple cross-sectional and cohort analysis?
In a single cross-sectional design there is only one sample of participants, and information is obtained from this sample only once.
In a multiple cross-sectional design there are two or more samples of participants, and information from each sample is obtained only once
Cohort analysis consists of a series of surveys conducted at appropriate time intervals, where the cohort serves as the basic unit of analysis. A cohort is a group of participants who experience the same event within the same time interval.
What are the major purposes of descriptive research?
to describe the characteristics of relevant groups of units such as consumers, sales people, organisations and market areas
to estimate the percentage of units in a specified population exhibiting a certain behaviour
to determine the perceptions of product characteristics
to determine the degree to which marketing variables are associated
to make specific predictions.
Compare and contrast cross-sectional and longitudinal designs.
A cross-sectional design involves the collection of data from a sample at a single point in time. For example, if a researcher observes the buying behaviour of shoppers selected in a street interview scenario and then analyses the data gathered, then such a study will be called a cross-sectional study. On the other hand, longitudinal design involves collecting data periodically from a fixed sample of participants. Therefore, a longitudinal study provides a series of ‘snapshots’, which, when viewed together, portray a vivid illustration of the situation and the changes which are taking place.
Compared to a cross-sectional design, a longitudinal design is more effective in detecting change, can be more accurate due to the rapport which can be built up with participants, and provides a larger amount of data. A cross-sectional design can have advantages in creating a ‘one-off’ sample which is more representative of a target population, compared to a longitudinal sample where participants may drop out and particular types of participant become under-represented. The disadvantage of building up a rapport with participants in a longitudinal design is the bias which may be introduced through an over-familiarity with the study and the interviewers/researchers working on it.
What is a continuous and a discontinuous panel?
Continuous panels ask panel members the same questions on each panel measurement.
Discontinuous panels vary questions from one panel measurement to the next. They are sometimes referred to as omnibus (‘including or covering many things or classes’).
What are potential sources of error in market research?
Total error
The variation between the true mean value in the population of the variable of interest and the observed mean value obtained in the market research project.
Random sampling error
The error arising because the particular sample selected is an imperfect representation of the population of interest. It may be defined as the variation between the true mean value for the sample and the true mean value of the population.
Non-sampling error
An error which can be attributed to sources other than sampling and which can be random or non-random.
Non-response error
A type of non-sampling error which occurs when some of the participants included in the sample do not respond. This error may be defined as the variation between the true mean value of the variable in the original sample and the true mean value in the net sample.
Response error
Describe the advantages and disadvantages of access panels.
A panel consists of a sample of participants, generally households, who have agreed to provide information at specified intervals over an extended period.
Advantages:
Over a period of time, panel data can reveal changes in market share and/or changes in consumer attitudes and behaviour.
Relatively large amounts of data can be gathered.
The researcher can collect more detailed data regarding the primary variables of interest.
The data collected are more accurate because of the support given to participants and the development of a relationship between panel members and the sponsoring organisation.
Disadvantages:
Panels may not necessarily be any more representative than a single cross-sectional survey. This may arise due to participants refusing to cooperate, ‘mortality’, i.e. participants dropping out of the panel due to lack of interest, and the nature of payments or tangible rewards which may attract a certain type of participant.
New panel members are often biased in their initial responses, and seasoned panel members may provide biased responses through being tired or bored with the process.
