Choose the correct answer for each question. You must click on the link for the details of the analysis.

1. In view of the deviation from normality for PETAL_W in setosa and versicolor, do you think that there is any need to transform PETAL_W? Note that if you transform it for those 2 species you will also need to transform PETAL_W for virginica.

   1.   ?    No
   2.   ?    Yes

2. Using the scatter plots, which species looks the simplest to separate?

   1.   ?    Iris setosa
   2.   ?    Iris versicolor
   3.   ?    Iris virginica
   4.   ?    All three
   5.   ?    None can be separated on the plots.

3. Examine the descriptive statistics and ANOVA (analysis of variance) tables. If the variables are ranked in terms of their discriminating power which of the following is the correct order?

   1.   ?    PETAL_W, PETAL_L, SEPAL_L and SEPAL_W
   2.   ?    PETAL_L, PETAL_W, SEPAL_L and SEPAL_W
   3.   ?    SEPAL_L, PETAL_L, PETAL_W and SEPAL_W
   4.   ?    SEPAL_W, SEPAL_W, PETAL_L and PETAL_L

4. Which, if any variables, look like good candidates to separate versicolor and virginica?

   1.   ?    Sepal variables
   2.   ?    Length variables
   3.   ?    Petal variables
   4.   ?    Width variables

5. Examine the correlation matrix. Which, if any, variables are too highly correlated to include as joint predictors?

   1.   ?    None are too highly correlated.
   2.   ?    All are too highly correlated.
   3.   ?    The petal variables
   4.   ?    The sepal variables
   5.   ?    Sepal length and both petal measures

6. If you had to select a subset of predictors which would you choose?

   1.   ?    The two sepal characters
   2.   ?    Sepal width and petal length
   3.   ?    The two petal characters
   4.   ?    Sepal length and petal width