Comparative fixed design

Comparative designs differs from cross-sectional in that a second, comparison group is selected in addition to the originally referred one.

While relational and comparative designs may seem very different, the difference is largely in the way the study is conducted. For example, in relational design the focus may be on relations between gender and attitude, while on comparative the focus could be on differences between the two groups (male/female).

References:
Real World Research: A Resource for Social Scientists and Practitioner-Researchers, 2nd Edition. Colin Robson. (p.159-160)

Relational fixed designs: cross sectional studies

Relational fixed designs measure the relationship between two or more variables
In a cross-sectional study, the forcus is on relationships between and among variables of a single group. The pattern of relationships between variables may be of interest in its own right, or there may be a concern for establishing causal links. The variables to be included in the study are those needed to provide answers to your research questions (independent-explanatory, dependent-outcome variables) and they are included because of their relevance to the research question. A rule of thumb sometimes proposed is a minimum of 15 participants per variable.
An issue is the homogeneity of the group. For instance, while you may not be interested in gender issues per se, may be males and females are affected by different variables and hence there will be increased variability on the outcome variable. A solution here is to analyse the 2 genders separately, i.e. to perform a subgroup analysis.

Category membership
The identification of membership of particular categories or groups can be difficult and complex. This may appear straightforward for a variable such as age. However, there are situations where even age can be problematic. Gender, as social construct, can raise category difficulties in particular cases.

Possible challenges
Establishing the statistical significance of the relationship between gender and attitude does not enable us to conclude that these variables are causally related. Nor does it, in itself, help in understanding what lies behind this relationship. We need to come up with plausible mechanisms and seek evidence for their existence. Further sub-division of the group allows to control statistically for the effects of such variables (gender-knowledge-concern with safety, see p.159), providing the relevant information has been collected.


References:
Real World Research: A Resource for Social Scientists and Practitioner-Researchers, 2nd Edition. Colin Robson. (p.154-109)

Fixed designs: some fundamental features

Fixed designs are theory driven. The only way in which we can, as a fixed design requires, specify in advance the variables to be included in our study and the exact procedures to be followed, is by having a reasonably well articulated theory of the phenomenon we are researching.

Causal models (like the one here) help to make clear the multiple causality of most things studied in social research. It emphasizes that while some variables may have a direct effect on others (e.g. that of assessment beliefs on assessment methods), others mhave an indirect effect (that of epistemological beliefs on assessment methods through assessment beliefs). Hard thinking to establish this kind of model before data collection is invaluable.

Fixed designs should always be piloted. Fixed designs are usually concerned with aggregates, with group properties and with general tendencies. Most non-experimental research also deals with averages and proportions. The relative weakness of fixed designs is that they cannot capture the subtleties and complexities of individual human behaviour. Even single case designs are limited to quantative measures of a single, or a small number, of simple behaviours. The advantage of fixed designs lies in their ability to transcend individual differences and identify patterns and processes which can be linked to social structrures and group organizational features.

Generally, researchers using fixed design methods remain at a greater physical and emotional distance from the study than those using flexible, qualitative methods.

The concept of 'variable' is part of the quantative worldview central to fixed design research. In this worldview, reality is conceptualized as consisting of properties of things, properties that can vary and thus be measured and compared. These properties may be seen as categorical (i.e. gender, nationality, teaching style) or as continuous (i.e. age, knowledge of some topic). It is very important to identify what variables are being studied, and to distinguish different types of variables (such as independent and depentdent variables).
independent variables: those which the experimenter manipulates.
dependent variables: those were we look for change.


issues of Validity, generalisability objectivity, credibility (p.100-109).

References:
Real World Research: A Resource for Social Scientists and Practitioner-Researchers, 2nd Edition. Colin Robson. (p.96-109)

A framework for Research Design

Purposes
Theory
Research Questions
Methods
Sampling strategy


see: Real World Research: A Resource for Social Scientists and Practitioner-Researchers, 2nd Edition. Colin Robson. (p.81)