Benedictine BALT6102 Quiz

 

Your work has been saved and submitted

Attempt Score	25 / 25 - 100 %
Overall Grade (Highest Attempt)	25 / 25 - 100 %

Question 1

3 / 3 points

Which is NOT a primary option for addressing missing data?  

Question options:

	A)  ​To discard observations with any missing values
	B)  ​To discard any variable with missing values
	C)  ​To fill in missing entries with estimated values
	D)  ​To generate random data to replace the missing values

Feedback Rationale:

Question 2

3 / 3 points

Euclidean distance can be used to calculate the dissimilarity between two observations. Let u = (25, $350) correspond to a 25-year old customer that spent $350 at Store A in the previous fiscal year. Let v = (53, $420) correspond to a 53-year old customer that spent $4,100 at Store A in the previous fiscal year. Calculate the dissimilarity between these two observations using Euclidean distance.

Question options:

	A)  66.21
	B)  72.28
	C)  75.39
	D)  88.57

Feedback Rationale:

Question 3

3 / 3 points

Which of the following is true of Euclidean distances?

Question options:

	A)  It is used to measure dissimilarity between categorical variable observations.
	B)  It is not affected by the scale on which variables are measured.
	C)  It increases with the increase in similarity between variable values.
	D)  It is commonly used as a method of measuring  dissimilarity between quantitative observations.

Feedback Rationale:

Question 4

3 / 3 points

Jaccard's coefficient is different from the matching coefficient in that the former

Question options:

	A)  measures overlap while the latter measures dissimilarity.
	B)  does not count matching zero entries while the latter does.
	C)  deals with categorical variable while the latter deals with continuous variables.
	D)  is affected by the scale used to measure variables while the latter is not.

Feedback Rationale:

Question 5

3 / 3 points

​In k-means clustering, k represents the

Question options:

	A)  number of variables.
	B)  number of clusters.
	C)  number of observations in a cluster.
	D)  mean of the cluster.

Feedback Rationale:

Question 6

5 / 5 points

Redo the k-means problem step by step as class by selecting customers 1, 8 and 18 as initial centroids.

You may refer to Chapter 4 Customer Segmentation K Means.xls. Feel free to use my spreadsheet: Chapter 4 Customer Segmentation K Means_hw.xls.

After Iter1, which cluster does customer 1 belong to?

Question options:

	A)  cluster 1
	B)  cluster 2
	C)  cluster 3
	D)  none of above

Feedback Your answer is CORRECT.

Question 7

5 / 5 points

See Q6.

After iter1, we recalculate the centriods.

What is the new centroid 1 (used by iter2)?

Question options:

	A)  (0 0 1 1)
	B)  (1 1 0 1)
	C)  (0.25 0.125 1 0.75)
	D)  none of above

Feedback Your answer is CORRECT.