Refer to the Journal of Applied Ecology study of the feeding habits of baby snow geese, Exercises 10.11 and 10.29 (pages 577,59l).The MINITAB printout for the first-order model relating gosling weight change y to digestion efficiency x1and acid-detergent fiber x2 is reproduced above. Both a confidence interval for E(y) and a prediction interval for y when x1 = 5% and x2= 30% are shown at the bottom of the printout
a. Interpret the confidence interval for E(y).
b. Interpret the prediction interval for y.
Exercise 10.29
Refer to the Journal of Applied Ecology study of the feeding habits of baby snow geese, Exercise 10.11 (p. 577).The MINITAB printout for the model relating weight change (y) to digestion efficiency (x1) and acid detergent fiber (x2) is reproduced on page 590.
a. Locate R2 and 
on the MINITAB printout. Interpret these values. Which statistic is the preferred measure of model fit? Explain.
b. Locate the global F value for testing the overall model on the MINITAB printout. Use the statistic to test the null hypothesis Ha: ß1, = ß2 = 0.
Exercise 10.11
Refer to the Journal of Applied Ecology (Vol. 32,1995) study of the feeding habits of baby snow geese, Exercise 9.56 (p. 514). The data on gosling weight change, digestion efficiency, acid-detergent fiber (all measured as percentages) and diet (plants or duck chow) for 42 feeding trials are reproduced in the table above. The botanists were interested in predicting weight change (y) as a function of the other variables. The first-order model
is digestion efficiency and x2 is acid-detergent fiber, was fit to the data. The MINITAB printout is provided on page 578.
a. Find the least squares prediction equation for weight change, y
b. Interpret the ß-estimates in the equation, part a.
c. Conduct a test to determine if digestion efficiency x1, is a useful linear predictor of weight change. Use α = .01
d. Form a 99% confidence interval for ß2. Interpret the result.
e. Explain how to include the qualitative variable diet into the model
Exercise 9.56
Researchers at the University of Toronto conducted a series of experiments to investigate whether a commercially sold pet food could serve as a substitute diet for baby snow geese (Journal of Applied Ecology,Vol.32. 1995). Goslings were deprived of food until their guts I were empty, then were allowed to feed for 6 hours on i a diet of plants or Purina Duck Chow. For each feeding trial, the change in the weight of the gosling after 2.5 hours was recorded as a percentage of initial weight. ! Two other variables recorded were digestion efficiency (measured as a percentage) and amount of acid-detergent fiber in the digestive tract (also measured as a percentage). The data for 42 feeding trials are listed in the I table on page 517
a. The researchers were interested in the correlation between weight change (y) and digestion efficiency (x). I Plot the data for these two variables in a scattergram. Do you observe a trend?
b. On the SPSS printout on page 516, locate the coefficient of correlation relating weight change y to digestion efficiency x. Interpret this value.
c. Conduct a test (at α = .01) to determine whether weight change y is correlated with digestion efficiency x. (Note: The SPSS printout reports p-values for a test of the null hypothesis of zero correlation.)
d. Repeat parts b and c, but exclude the data for trials that used duck chow from the analysis. What do you t conclude?
e. The researchers were also interested in the correlation between digestion efficiency ('y) and acid-detergent fiber (x). Repeat parts a-d for these two variables.
