PSYC3042 Lecture Notes - Lecture 2: The Common Cause (Film), Dependent And Independent Variables, Construct Validity
Document Summary
Lecture 2 - constructs, variables & relationships: making causal inferences in research; the anatomy of a simple research study: constructs, relationships, operationalised variables, dependent variables. The purpose of research is to find a significant covariation to infer causality about how two or more variables interact. However, you cannot infer causality unless you can claim the. Three counts of validity: construct, internal and external. Construct validity the degree e to which an operation measures or manipulates the targeted construct. Internal validity the degree to which a study can establish that factor a actually causes factor x. Eg simpsons paradox; a tend to present in a sub group of data can disappear when the data are pooled over other sub groups. External validity the degree to which the results of the study can be generalised to other settings, times and participants so the real world. Reliability works at the level of the study.