Multi-sample inference: One-way analysis of variance, Two-way analysis of variance, The Kruskal –Wallis Test, One-Way ANOVA-The Random Effects Model, The Intraclass Correlation Coefficient.

1. Birthweight of an infant has been hypothesized to be associated with smoking status of the mother during first trimester of pregnancy. This hypothesis is tested by recording birthweights of infants and smoking status of mother during pregnancy for all mothers who register at the prenatal clinic at a particular hospital within a 1-month period. The mothers are divided into four groups according to smoking habit, and the sample of birthweights in pounds within each group is as follows:
   Group 1: Mother is nonsmoker (NON):
   7.5 6.2 6.9 7.4 9.2 8.3 7.6
   Group 2: Mother is ex-smoker (smoked at some time before pregnancy but not during pregnancy) (EX):
   5.8 7.3 8.2 7.1 7.8
   Group 3: Mother is current smoker and smokes less than 1 pack per day (CUR<1)
   5.9 6.2 5.8 4.7 8.3 7.2 6.2
   Group 4: Mother is current smoker and smokes 1 pack per day or more (CUR \[\ge \] 1):
   6.2 6.8 5.7 4.9 6.2 7.1 5.8 5.4
   1. Are the mean birthweights different overall in the four groups?
   2. Test for all differences between each pair of groups, and summarize your results using the LSD procedure (Least significant difference)
   3. Perform the same tests in problem b using the method of multiple comparisons. (use Bonferroni).
2. Refer to the data set hormone.dat included
   1. Use analysis-of-variance methods to test if the change in biliary-secretion levels is comparable for the five hormone groups. Identify and test for any specific group differences.

Price: $14.78

Solution: The downloadable solution consists of 9 pages, 578 words and 10 charts.
Deliverable: Word Document