1) calories is a function of # of grams of sugar; # of grams of sugar is the independent var;

calories is the dependent

2)

positive expected as calories increase as # of grams of sugar increase

3) slope is 5.1369 and 89.4945+e is the intercept

**ŷ = 5.13692 X + 89.48425**

4) sqrt ( sum of squares of residuals)/(n-2) * [ 1/n + meanX^2/[(n-1)*stndDevX]] = 88.60769

the difference is

doing a reverse table lookup or norminv in Excel, the z-score is < 1.96 at 95% confidence

5) goodness of fit coefficients show that the linear model is not very good