Chapter 9: Correlation Flashcards
(16 cards)
Correlation
Relationship b/w variables
Correlation Coefficient
Measure of the relationship b/w variables
Pearson Product-Moment Correlation Coefficient (r)
Most common correlation coefficient
Scatter Diagrams
Figure in which data points are plotted in 2D space
Predictor Variable (Independent)
- Variable from which a prediction is made
- Knowing something about X should help you predict something about Y
Criterion Variable (dependent)
Variable to be predicted
Regression Line
- Line of best fit
- Represented by a straight line drawn through all data points
- Must look for a line which minimizes the sum of the squared errors
Linea Relationship
Situation where the best fitting regression line is straight
Collinear Relationship
Situation best represented by something other than a straight line
Covariance
Statistic representing the degree to which two variables vary together
Spearman’s Correlation Coefficient
Correlation coefficient on ranked data
- Why Rank?
- -You either don’t trust the nature of the underlying scale, or want to down-weight extreme scores
Monotonic Relationship
Represented by a line that’s continually increasing (or decreasing) but doesn’t need to be straight
Effect of Range Restrictions & Non-linearity
The range over which X & Y vary
Range Restrictions
Cases where the range over which X & Y vary = artificially limited
-Visual effect of restricting range X or Y = reduced correlation
Regression
- Statistical technique which uses a single, independent variable (X) to estimate a single, dependent variable (Y)
- -Ie. How well do scores on one variable predict on another?
- The predictor of one variable from knowledge of one or more other variables
- Prediction/ representation of what we should expect to find
Least Squares Criterion
- Sum of squared deviations b/w Y and the regression line is less than between Y and any other line
- -When we meet this criterion, we obtain the line of best fit
- –50% values are above & 50% values are below
