Chapter 9: Correlational Research Flashcards
What are psychology’s two main dsciplines?
correlational and experimental psychology
Describe the method of concomitant variation
changes in the value of one variable are accompanied by predictable changes in a second variable.
The strength of a correlation is indicated by the size of the coefficient of correlation, the most common one being Pearson’s r.
What are the most common correlation coefficients and what kind of data is each one used for?
Pearson’s r is calculated for data measured on an interval or a ratio scale.
Spearman’s rho is calculated for ordinal data.
A chi-square test of independence works for nominal data.
What is a drawback of Pearson’s r?
It fails to identify non-linear relationships
Range restriction ____ the observed correlation
weakens
What type of error would be observed if an outlier is included when calculating Pearson’s r?
Type I error
What is the coefficient of determination (r2)?
the portion of variability in one of the variables in the correlation that can be accounted for by variability in the second variable
What is regression analysis used for?
making predictions based on correlational research
What do variables X and Y represent in a regression line?
X: predictor
Y: criterion
What are two problems a researcher is faced with when interpreting correlations?
the directionality problem and third variable problem
explain the directionality problem
if there’s a correlation between variables A and B, it is equally possible that A is causing B (A → B) or that B is causing A (B → A)
explain the third variable problem
rather than A causing B or B causing A, an unknown third variable C might be causing both A and B
variable C is also called a confounder
How do you counter the directionality problem?
by using a cross-lagged panel correlation
what is a cross-lagged panel correlation?
a longitudinal procedure which investigates correlations between variables at several points in time
How do you counter the third variable problem?
By using partial correlation
What is partial correlation?
A procedure that statistically controls for third variables if you suspect a specific measurable third variable
name some fields where correlational research is used
- assessing validity and reliability of psychological tests
- personality psychology
- abnormal psychology
- twin studies
What is the difference between a bivariate and multivariate analysis?
A bivariate approach investigates the relationships between any two variables.
A multivariate approach examines the relationships among more than two variables.
What is shown in the following image?
y = dependent variable
x = independent variable
b = regression weight
R → correlation between the combined predictors and the criterion
R2 → variation in criterion variable that can be accounted for by the combined predictors
What is a factor analysis?
Multiple variables are measured and correlated with each other. It is then determined whether groups of these variables cluster together to form factors. Pearson’s r can be calculated for all possible pairs of tests, yielding a correlation matrix. The analysis also determines factor loadings - correlations between each of the measures and factors.
what is the advantage of multiple regression analysis
predictive validity improves when the influences of several predictor variables are combined, compared to single regression analysis
