Lecture
An experimental plan (design) includes specifying the scheme for presenting the conditions of the independent variable to different groups of participants, or the sequence of levels of the independent variable presented to a single participant, as well as the number of trials or participants (n). It is also the plan for recording the dependent variable.
Classifications:
1. The classification of experimental schemes into intra-individual, between-group, and cross-individual is one of the main criteria for classifying experiments, and the choice of scheme is the result of planning any experiment.
Intra-individual schemes
Ensuring internal validity is the main goal of experimental planning when developing an intra-individual comparison of changes in the dependent variable.
At least two trials corresponding to the levels of the independent variable are required. Identity is impossible here, since there is only one participant.
The factors of time, sequence, and task appear – the main threats of confounding (of these extraneous variables) with the influence of the experimental factor.
Types of schemes:
1. The scheme of regular alternation.
A1B1A2B2…AnBn (A and B are levels of the independent variable).
In each new trial there is a successive change of conditions. The number of trials is set in advance by the experimenter.
Such a scheme controls for changes in the dependent variable over time.
A sequence effect here may manifest itself in that some trial will gain by contrast, which will distort the magnitude of the effect.
Another threat comes from the extraneous variable of the «participant's knowledge», or their bias. Having grasped that the levels alternate, the participant may choose their answer in advance in each trial.
The scheme of regular alternation is justified when it helps to control threats from non-systematic variability. The drawback of the scheme: the emergence of additional sequence effects (e.g., contrast).
2. The scheme of a randomized (random) sequence.
The random distribution of the two levels of the experimental factor within the overall sequence of trials, limited by the number n.
The control of extraneous variables related to the time factor is here based on the principle of the equiprobable assignment of different levels of the extraneous variable to the experimental and control conditions.
3. The scheme of positional counterbalancing.
The forward and reverse order of presenting the levels: ABBA and BAAB.
The task factor is controlled. The time factor is controlled if the changes over time are linear in nature.
It controls symmetrical sequence effects well.
There are sequence effects that are controlled by none of these schemes – heterogeneous sequence effects.
Questions of external validity are related not to the scheme but to the representativeness of the methods and of the participant.
The representativeness of a participant is how typical a representative of the population they are.
Between-group schemes.
An essential element of planning is the way in which the groups are formed. The most rigorous criterion requires randomization, a random order of forming the groups.
Inter-individual differences, or differences between subjects and inequality between groups, are the main source of threats to internal validity in between-group schemes. They may affect the dependent variable or interact with the independent variable, which distorts the form of the causal dependence under study.
Sometimes increasing the samples is considered as a way of controlling non-systematic confoundings. But the problem of the non-equivalence of samples is not thereby solved.
Types of between-group designs (comparison schemes):
1. A simple design for the experimental and control groups without pretesting.
Randomization – R – here acts as a strategy for selecting participants into groups from the population; it allows the groups to be regarded as equivalent and the difference in the dependent variable to be attributed specifically to the action of the independent variable.
2. A design with pretesting and posttesting and a control group.
Pretesting partially solves the problem of accounting for and controlling the initial level of the dependent variable, but the non-equivalence of the groups may be hidden in unmeasured variables.
Such designs may have insufficient external validity.
3. The Solomon design.
A comparison of four groups: two experimental and two control, with the introduction of the factor «presence or absence of pretesting».
The factor of inter-individual differences is controlled by strategies for selecting and matching participants. The aspect of the representativeness of participants is external validity; the equivalence of groups is internal validity.
In the case of the randomization strategy for selection from a population (see above), the external and internal validity of the experiment turn out to be interrelated.
4. The strategy of stratified selection or matching of participants (the strategy of random distribution of strata).
As a result, each level of the extraneous variable is equally represented in each of the selected (or matched) groups.
This strategy is often used to control an additional variable.
5. The strategy of pairwise matching.
Used in the case of matching, when the sample of participants has already been determined and they can be subjected to pretesting.
This strategy is mainly used with small samples.
6. Random selection of groups.
Used when approximating an experiment of full correspondence presupposes implementing the X-influences under the real conditions of life activity. For example, comparing different methods of instruction.
Comments