PSY 242 - Research Methods II

bivariate correlation

association of two variables

four types of variables

• nominal (categorical)

• ordinal (order; distance between varies)

• interval (likert type scale)

• ratio (true zero)

correlation coefficient

• a value between -1 and 1

• strength: close to -1 or 1 = close relationship

• direction: positive, negative, or zero

statistical significant (p-value)

the probability that results are due to chance (p < 0.05 is ideal)

effect size

the strength of a relationship between two or more variables (how close the dots are to the line of best fit)

confidence interval (CI)

a range of values that is likely to contain the true value of a population parameter

spurious association

variables that seem connected but are being influenced by a third variable

to establish causation, a study must satisfy;

• covariance of cause and effect

• temporal precedence

• internal validity

moderator/mediator

moderator: stronger/changes direction of relationship

mediator: actual third variable affecting the relationship

internal/external validity

internal: causal inferences based on association

external: can findings be generalized

construct/statistical validity

construct: study measures concepts accurately

statistical: conclusions are accurate

normal vs skewed

normal: pearson correlation

skewed: spearmen correlation