Lecture
The «testing» of theory against empirical data is the common feature that characterizes control over inferences on the basis of a discussion of research results (of an experiment, a correlational study, or observation).
Control over inference is the logic of discussing the possibilities of interpreting an established empirical dependency both within the study and as psychological generalizations beyond the situation.
Control over inference is the disclosure of the interrelation between the schemes of organizing empirical research and the possibilities of the psychological conclusions drawn on its basis.
The possibilities of generalization depend on the research method that has been implemented.
Within an individual study, conclusions may turn out to be sound (valid) or artifactual (unsound, invalid).
Errors in generalizations arise because the researcher violates the rules of logic (in correlating general and particular premises) and substitutes the acceptance of unfounded arguments for the norms of hypothetico-deductive reasoning.
Assessing the soundness of conclusions:
1) Assessing the correctness of decisions about the experimental effect. The problem of statistical inference.
- the reasoning carried out in the transitions between the various levels of the hypotheses being tested;
- the reasoning involved in grounding the interpretive link between the experimental and theoretical hypotheses.
2) Taking the experimental design into account – assessing the representativeness of individual data or of the «averaged» dependencies obtained for the samples. (Is it a matter of chance or of regularity?)
Internal and operational validity ensure the soundness of the conclusion about a dependency within the research situation.
3) Generalizations beyond the situation (external validity, population validity).
For an experiment with scientific aims, the generalization of the type of causal dependency proceeds in 3 stages (if a laboratory experiment took place):
We draw a conclusion about the type of dependency;
A conclusion about the soundness of the theoretical model being used;
Moving from theory to reality, a conclusion about the degree of correspondence.
For an experiment with practical aims, the logic of inference is sometimes simplified.
Stages of generalization (from the lecture):
- Generalization within the experimental situation.
Has the sought-after regular dependency (SRD) been established? Or is the result artifactual? Generalization of the type of dependency.
- Control of generalization in terms of who the subjects were.
Can the results be transferred to other samples?
- Evaluation of the hypothesis in terms of the data established.
Internal, operational validity.
- Hypothetico-deductive generalization.
modus tollens; falsification of incorrect hypotheses.
- Interpretation in terms of competing knowledge.
The logic of carrying out inference must include the following components:
- a hypothetico-deductive path of reasoning with an asymmetry of inference;
- the construction of experimental schemes, within the framework of inductive inference about the result of the action of the experimental factor and the possibility of a causal explanation of the change in the DV;
- a conclusion about the EH on the basis of an analysis of the obtained effect by correlating the result with the assessment of validity;
- grounding the substantive bases for generalizing the dependency beyond the experiment.
Comments