Flashcards in Chapter 3 Deck (24):
Something that varies
Has at least 2 levels
Something that could potentially vary but is kept the same for the study
The one whose levels are just observed and recorded
Researcher controls it
Certain variables cannot be manipulated like gender or iq
Abstract concepts such as shyness or. Intelligence
Also called a construct
Must be carefully defined at a theoretical level
The definition for a conceptual variable
Turning a concept into a measured or manipulated variable
Gives the ability to test a hypothesis
The argument someone is trying to make
Describe a particular rate or degree of a single variable
Claim how frequent or common something is
Percentage of a variable
Number of people involved
Focus on 1 variable
Measured not manipulated
Argues one level of a variable is likely to be associated with a particular level of another
Correlate or covary
Contains 2 variables
Measured not manipulated
High goes with high
Low goes with low
High goes with low
Low goes with high
Argues 1 of the variables is responsible for changing the other
Has 2 variables which covary
Goes beyond associations
Has 3 criteria
1- relationship between 2 variables not 0
2- causal variable must be shown to be first
3- no other explanation for the relationship
Appropriateness of a conclusion or a decision
A valid claim
How well a conceptual variable operationalized
The extent to which the operational variables used in a study are a good approximation of the conceptual variables
Frequency Claim: how well did the researcher measure the variable?
Association Claim: how well did the researcher measure all the variables?
Causal Claim: how well has the researcher measured or manipulated the variables in the study?
The extent to which the results generalize to a large population or other times/ situations
Frequency Claim: How well the results of a study generalize to or represent people it context besides those in the study? How representative is the sample?
Association Claim: to what populations,settings, and times can we generalize this claim? How representative is the sample? To What other problems might the association be generalized?
Casual Claim: to what populations, settings, and times can we generalize the casual claim? How representative is the sample? How representative are the manipulations and measures?
Addresses the strength of an effect and it's statistical significance. Also addresses the extent to which a study minimizes the prob of 2 errors: concluding that there is an effect when there isn't 1 ( type 1 error) or concluding there is no effect when there is 1 ( type 2 error)
Frequency Claim: what is the margin of error of the estimate?
Association claim: what is the effect size? How strong is the association? Is it statistically significant? If a relationship found what is prob of false positive (type 1) ? If no relationship what is prob of miss ( type 2)
Causal Claim: what is the effect size? Is there a difference between groups? How large? Statistically significant?
Is a relationship between 1 variable and another, the extent to which the first rather than a random variable is responsible for the second
Frequency claim: not relevant
Association claim: no causality asserted therefore not relevant
Causal Claim: was the study an experiment? Does the study achieve temporal precedence ? Does the study control for alternative explanations by randomly assigned participants to groups? Does the study avoid several internal validity threats?
What is needed to make a causal claim
Internal validity ( third variable rule of confounds)
What can help with a causal claim
An experiment where we control the IV to get temporal precedence and internal validity