Question

Lipids provide much of the dietary energy in the bodies of infants and young children. There is a growing interest in the quality of the dietary lipid supply during infancy as a major determinant of growth, visual and neural development, and long-term health. An article reported the following data on total polyunsaturated fats (%) for infants who were randomized to four different feeding regimens: breast milk, corn-oil-based formula, soy-oil-based formula, or soy-and-marine-oil-based formula. (Use i = 1, 2, 3, and 4 respectively.)

Sample Regimen Sample Size Sample Mean Sample SD

Breast milk 15 42.9 1.3
CO 17 43.1 1.5
SO 8 43.7 1.2
SMO 14 43.9 1.2

Required:
a. What assumptions must be made about the four total polyunsaturated fat distributions before carrying out a single-factor ANOVA to decide whether there are any differences in true average fat content?
b. Carry out the test suggested in part (a). State the appropriate hypotheses.
c. Find the value of the test statistic in this test.

Answer 1

A.

This assumption is that the distribution of polyunsaturated fat % of each if these four regimes must be with equal variances as well as uniform.

B.

The null hypothesis

H0: μ1 = μ2 = μ3 = μ4

The alternate hypothesis:

H1: at least 2 means are unequal

C.

First we calculate the grand mean

= 1/54[15(42.9)+17(43.1)+8(43.7)+14(43.9)]

= (643.5 +732.7 + 349.6 + 614.6)/54

= 2340.4/54

= 43.341

Sum of squared treatment

= [15(42.9-43.341)²+17(43.1-43.341)²+8(43.7-43.341)²+14(43.9-43.341)²]

= 9.3104

Mean square of treatment

= SST/I-1

= 9.3104/4-1

= 9.3104/3

= 3.1035

Error sum of squared

= (15-1)*(1.3)² + (17-1)*(1.5)² + (8-1)*(1.2)² + (14-1)*(1.2)²

= 88.46

Error mean square

MSE = 88.46/54-4

= 1.7692

Test statistic

= 3.1035/1.7692

= 1.75