3.1) (Ch. 7) Explain what a residual is (also known as residual of prediction).
e idea of “least squares” in regression (you need to fully read pp. 200-208 to understand).
3) What does it mean if b = 0?
4) What does it mean when r-squared is 0? What does it mean when r-squared is 1?
5) What is the difference in an unstandardized regression coefficient and the standardized regression coefficient?
6) If a report says test performance was predicted by number of cups of coffee (b = .94), what does the .94 mean? Interpret this. (For every one unit increase in ___,There is an increase in ___ )
7) If F (2,344) = 340.2, p < .001, then what is this saying in general about the regression model? (see p. 217)
8) Why should you be cautious in using unstandardized beta? (p. 218)
9) (Ch. 8) Explain partial correlation in your own words. In your explanation, explain how it is different from zero-order correlation (aka Pearson r).
10) (Ch. 9) What is the F statistic used to determine in multiple regression?
11) What is F when the null hypothesis is true?
12) In Table 9.4, which variable(s) are statistically significant predictors?
13) In Table 9.4, explain what it means if health motivation has b = .36 in terms of predicting number of exercise sessions per week.
14) What is the benefit of interpreting standardized beta weights? (see p. 264).
15) What happens if your predictor variables are too closely correlated?
16) Reflect on your learning. What has been the most difficult? How did you get through it? What concepts are still fuzzy to you? Is there anything you could share with me that would help me address how you learn best?