Chapter 3: Three Claims, Four Validities; Interrogation Tools for Consumers of Research Flashcards
Variable
Something that varies and has at least two levels/ values
a core unit of psychological research
Constant
In a study, has one level; however, can potentially vary
Manipulated Variable
The variable that is assigned levels by the researcher
Some variables cannot be manipulated, and can only be measured
Measured Variable
A variable in a study that has values and levels observed and recorded
Some variables cannot be manipulated, and can only be measured
Construct/ Conceptual Variable
The variable of interest; is stated in an abstract or conversational level
Operational Variables/ Definitions
the specific means of concept of interest is measured as a variable in a study (aka. operationalization)
Claim
The argument someone is trying to make
The Three Claims
Frequency, Association, Causal
Frequency Claim
- Particular rate or degree of a variable
- Often has a number in it
- One variable at a time
Association Claim
The levels of the variable are likely to be associated with the levels of another variable
*levels are correlationary; meaning they vary symmetrically *
Correlational Study
When the relationship between variables is tested
Positive Association
High Levels with High, Low with Low of Variable
*appears to have a positive slope/trend on a graph *
Negative Association
High with low, Low with High levels of variables
Appears to have negative slope/ trend on graph
Zero Association
No levels correlate
confetti, its all over the place on a graph
Causal Claims
Specific changes in one variable are responsible for influencing the change in another variable
- direct causation is suggested using more direct verbiage
Validity
Appropriateness of a conclusion of decision
Construct Validity
Indication of how well a variable was measured or manipulated in a study
must establish each variable was measured reliably and dif levels of variables are corresponding to true differences
Generalization
The extent to which subject in study represent the intended population
Questions external validity
Statistical Validity
The extent to which statistical conclusions derived from a study are accurate and resonable
Point Estimate
Single Estimate of some populational value based on a data sample (usually a percentage)
we use to evaluate statistical validity
External Validity
The extent to which the results generalize to some larger population
Internal Validity
The relationship between one variable and another, and the extent to which A causes B, rather than how C is/ is also responsible
Criteria for Causation
- How we justify a Causal Claim
1. Covariance: the extent to which two variables observed go together
2. Temporal Precedence: casual variable comes first in time
3. Internal Validity
