Term
|
Definition
Describing associations between 2 measured variables.
Can include both quantitative and qualitative variables.
Uses scatterplots. |
|
|
Term
| Small or Weak Effect Size |
|
Definition
|
|
Term
| Medium or Moderate Effect Size |
|
Definition
|
|
Term
| Large or Strong Effect Size |
|
Definition
|
|
Term
| Describing associations with Categorical Data |
|
Definition
Use the x-axis for the categorical data and the y-axis for the numerical data.
May be better represented as a bar graph than a scatterplot.
Typically look at the difference between the means or group averages and use a t-test. |
|
|
Term
2 _____________ , not any particular statistics, make a study
_______________. |
|
Definition
| Measured variables; Correlational |
|
|
Term
|
Definition
Construct
Statistical
Internal
External |
|
|
Term
|
Definition
How well did we measure each variable?
Was it properly operationalized?
Was is measured reliably and with validity?
What about face validity? |
|
|
Term
|
Definition
What is the effect size?
Is the correlation statistically significant?
Could outliers have affected the outcome? |
|
|
Term
|
Definition
Describes the strength of an association.
Depending on the context, even a small effect size can be important. EX- Baby aspirin is associated with reduced heart attacks even though r=.03 |
|
|
Term
|
Definition
Helps evaluate the probability that the result comes from a population where the association noes not exist ( is really zero).
Process of inference from sample to population.
Significant report p<.05
Non-significant report p>.05 |
|
|
Term
|
Definition
| The result is unlikely to have come from a population where the true association is zero. p>.05 means you can not rule it out. |
|
|
Term
| True or False: Small correlations will be significant from large samples(1,000) more than small samples (30) because of chance events in the sample. |
|
Definition
|
|
Term
|
Definition
An extreme score.
Have more impact when the sample is small and they occur in both of the measures. |
|
|
Term
|
Definition
| In a correlational study, if there is not a full range of scores on one of the variables in the association, it can make the correlation appear smaller than it is. |
|
|
Term
|
Definition
The relationship between 2 variables is not straight line. The r will be close to 0 even though there is a relationship between the 2 variables.
EX- A curvilinear association exists between age and use of health care. |
|
|
Term
| The 3 Criteria for Establishing Causation |
|
Definition
Covariance
Temoral Precedence
Internal Validity |
|
|
Term
|
Definition
| There must be a correlation, or association between the cause variable and the effect variable. A<-->B |
|
|
Term
|
Definition
| The causal variable must precede the effect variable. It must come first in time. A--->B |
|
|
Term
|
Definition
| There must be no plausible alternative explanations for the relationship between the two variables. Third variable C affects A or B. |
|
|
Term
|
Definition
| An association only exists between A and B because of some third variable C. |
|
|
Term
|
Definition
| In association research, when the relationship between two variables changes depending on the level of another variable. |
|
|
