Exam 3 Flashcards
scatterplot
graph of relationship between two variables, X and Y.
one point per subject
correlation
Measure of how closely two variables are related
Population variable: p(rho)
Sample correlation variable : r
Independence between two variables
value of one tells nothing about the other
Linear Relationship
correlation measures how well data fit on a straight line
ie assumes linear relationship
Regression
finds best combination of predictors to explain outcome variable
- determines unique contribution of each predictor
- -can test whether each predictor has reliable influence
Regression equation
Yhat =
Intercept
value of Y when all X’s are zero
Regression coefficient
bi
- influence of Xi
- Sign tells direction; magnitude tells strength
- -can be any value (not standardized like correlation)
Sum of squares
all of the squared deviations from the mean all added together
Explained variability
the total sum of squares is the variability in Y therefore the explained variability
residual variability
the deviation between predicted and actual scores
F statistic
used for hypothesis testing
- -if F is larger than expected by H0, regression explains more variance than expected by chance
- Reject null hypothesis if F is large enough
Analysis of Variance (ANOVA)
single test for any group differences
- -Null Hypothesis: All means are equal
- -Works using variance of the sample means
- -Also based on separating explained and unexplained variance
grand mean
the mean of sample means. You take all the means add them together and divide them by how many subjects there are
Repeated-Measures Design
Multiple measurement for each subject
- -different stimulus types, conditions, times, etc
- -All measurements are of the same variable, but in different situations
- -Generalizes paired-samples design