Chapter 12: Correlational Research Flashcards
Which correlation would you use depending on form of the relationship and data type?
Pearson-> linear relationship/ interval or ratio data
Spearman-> monotonic relation/ ordinal or non-normal
Which correlation technique is more sensitive to outliers?
Pearson correlation is more sensitive to outliers than Spearman correlation
Which statistical test if one numerical and one non-numerical score?
- use non numerical variable to organize scores
- use of t test
- can also calculate special correlation (point biserial correlation)
Which statistical test if both non-numerical scores?
- use of matrix
- chi-square hypothesis test
What does r^2 represent?
- correlation squared (r^2)
- how much of the variability in one variable is predictable from its relationship with the other variable
- shared variance
—>r^2=0.25-> 25% of the time, X predict accurately the variance in Y
What are the different value of r that show a different significance?
Small-> r=0.10/ r^2=0.01
Medium-> r=0.30/ r^2=0.09
Large-> r=0.70/ r^2=0.49
What is the difference between the predictor and criterion variable?
Predictor variable→ used to predict the other variable
- ex: SAT score
Criterion variable→ variable being predicted
- ex: university success
What are the strengths of a correlation?
- often use for area that has not received a lot of research attention
- opportunity to investigate variables that would be impossible or unethical to manipulate
- no manipulation/ high external validity
What are the weaknesses of a correlation?
- low internal validity
- third variable problem
- directionality problem→ which is cause and which is effect
- sensitive to outliers
What are the three timepoint-based correlations?
Cross-sectional correlations
Tests of whether 2 variables measured at the same timepoint are related to each other
—> if significant, one variable covaries with the other variable
Lag Cross-Correlations
Def→ Tests whether a variable at an EARLIER timepoint is associated with another variable at a LATER timepoint
- Temporal precedence
- ex: Infants learn language→ parent names an object at time X and infant turn heads at objects at time X+Lag
- Negative Lag Values→ Parent’s naming time occurs 5-10 seconds before infant’s response
Autocorrelations
Def→ Test whether a single variable at one timepoint is related to the same variable at another timepoint
- ex: circadian rhythms→ negative auto-correlation at 12hour lag but positive auto-correlation at 24hour lag.