3 Psychology Statistics 3010 Utah State University Exam 3

What does an ANOVA test for?

Whether the means of multiple groups are different from each other

The F-statistic is a ratio of what two things?

The variance between means and the variance within groups

What is the difference between a one-way ANOVA and a factorial ANOVA?

One way has one grouping variable (with multiple levels) and the factorial has multiple groups (with multiple levels)

What does the F test tell you?

If the means of the groups differ from each other

What is the null distribution for the ANOVA

How frequently the ratio of between-to-within variance gives you a particular number between 0 and infinity, assuming the null is true

What is moderation (AKA interaction)?

When the relationship between two variables depends on the value of a third variable

What is correlation a measure of?

How related two variables are

What does it mean to reject the null when testing correlation?

To conclude that the relationship between the two variables is not due to chance--there is a non-zero relationship in the population

What does negative correlation mean?

 

As one variable goes up, the other goes down

Which of the following can invalidate or bias your correlation?

Truncated scores, Curvilinear Relations

Which is used as the criterion for creating an OLS regression line?

Minimizing the error, or squared difference from the predicted amount

What is the relationship between the correlation coefficient r and the regression coefficient b?

r is standardized b

What is the relationship between r and the proportion of explained variance

r squared is the proportion of explained variance

What does a significant b mean?

The relationship between x and y (the slope) is probably not due to chance

What is b?

The slope

How do you interpret r as a slope?

A one SD change in X is associated with an r SD change in Y

When do you use a paired-sample t-test?

When you can meaningfully and correctly match observations (participants) across samples

A paired sample t-test looks at which kind of information?

within-pair

How do you account for paired data?

remove the variability due to the relatedness of the pairs by subtracting out the correlated variance