Diamonds Exploration 1

From Sean_Carver
Revision as of 03:14, 30 January 2019 by Carver (talk | contribs)
Jump to: navigation, search

Instructor's Answer [Under Construction]

Today we considered data from a sample of 3000 round cut diamonds sold by a large retailer. We pulled three variables (cut, carat, and price) from a larger data set, including two of four of the famous 4 C's of diamonds: carat, cut, clarity, and color. We looked at each variable individually and did not consider relationships among the variables.

The "cut" variable is categorical with possible values: Fair, Good, Very Good, Premium, and Ideal; these are in order of least desirable to most desirable making the variable ordinal. An examination of the frequency table shows that the choicest diamonds are most frequent in the data set, and frequency drops off in a consistent manner: Ideal (1216), Premium (765), Very Good (662), Good (277), Fair (80).

The "carat" variable is quantitative ranging from 0.21 to 3.01, with median 0.71, mean 0.808, standard deviation 0.482, and quartiles 0.4 and 1.05. The implication is that almost 75% of diamonds sold by this retailer are under 1 carat.